# Abstract

The complexity and rise of data in healthcare means that artificial intelligence (AI) will increasingly be applied within the field. The key categories of applications involve diagnosis and treatment recommendations, patient engagement and adherence, and administrative activities.

There are already a number of research studies suggesting that AI can perform as well as or better than humans at key healthcare tasks, such as diagnosing disease. Today, algorithms are already outperforming radiologists at spotting malignant tumours, and guiding researchers in how to construct cohorts for costly clinical trials.

**As a DeSci data infrastructure, BitDoctor AI collects decentralised health data through AI-driven health screenings accessible via smartphone, utilizing blockchain and advanced imaging technology.** **In just under a minute from your mobile phone's front camera, BitDoctor AI gives a comprehensive health analysis (potentially up to 30 health parameters) and can anticipate problems like heart attacks, diabetes, liver failure and many more other potential diseases, at the same time prescribing potential solutions with just a smart phone.**\
\
Examples of parameters available:

<figure><img src="/files/Vt5KkCXvU2uorYjkauGu" alt=""><figcaption></figcaption></figure>

**BitDoctor is revolutionizing healthcare access by cultivating hyper-personalised AI Doctor agent, designed to serve communities lacking medical support and individuals striving for longevity. Leveraging blockchain technology and unique DePIN facility, it enables users to contribute their health data securely to cultivate the AI Doctor agent.** This collective intelligence not only enhances hyper-personalized medical support but also paves the way for universal healthcare access globally creating a future where quality healthcare is accessible and affordable.

BitDoctor AI transforms health signals into a crucial insights for the medical industry while keeping your identity anonymous. It starts as a Medical AI Research & Development corporation. The advance machine learning (AI) algorithms is to create non-linear computational models for predicting non-invasive blood biomarkers. The technology is to determine the predictive power of the overall feature set.&#x20;

**Continuous data contribution is important to train the model to better identify the feature with the strongest relations with each biomarkers objectively is to saves lives and save millions if not billions of dollars out of pocket medical expenses for its users. The savings that is brought to protocol, so everyone gets to keep their health in check while securing governance token (DAO) to determine the funding direction on medical longevity researches.**


# Introduction

BitDoctor is a comprehensive medical AI that tackles the world's healthcare disparities, providing life-saving diagnoses and vital medical support to even the most underserved communities. **With over 4.1 billion people currently unable to afford or access healthcare services, the need for innovative solutions has never been more pressing as the disparities getting higher and higher.**

Looking ahead to 2030, experts project a significant increase in the average age population, reaching approximately 70 years old. This demographic shift is poised to intensify the demand for healthcare services, rendering them increasingly unaffordable for many. Against this backdrop, the global health landscape faces mounting challenges, from the emergence of new diseases to the ravages of wars, viruses, and environmental crises.

Even in times of conflict and turmoil, basic healthcare rights hang in the balance, with countries grappling with hyperinflation and the collapse of essential services. In a world rife with healthcare disparities, BitDoctor emerges as a beacon of hope, leveraging advanced AI technology to bridge the gap and provide essential medical support to underserved communities worldwide.

At the core of BitDoctor.ai's mission lies the commitment to democratizing healthcare, making it freely accessible to all. By harnessing the power of medical data and intelligent AI technology, BitDoctor.ai delivers consistent, accurate health and wellness insights, transcending geographical and socioeconomic barriers.

What began as a visionary idea has now gained momentum, with BitDoctor.ai securing backing from prominent figures. Bolstered by a dedicated team of medical professionals, BitDoctor.ai sets out to realize its ambitious vision through a three-stage approach, aimed at establishing a comprehensive, inclusive healthcare ecosystem. In a world beset by health crises and inequities, BitDoctor.ai stands as a testament to the transformative potential of AI-driven innovation in healthcare, offering hope for a future where quality medical support that knows no bounds.\
\
**STAGES**

**1. Intensive public train the Doctor AI to while offer a free diagnostic tool.**\
**2. Provide high-quality hyper personalise healthcare** \
**3. Identify cures for diseases and sicknesses at the earliest stage.**

BitDoctor AI is maximizing on opportunities currently untapped within the healthcare industry, whereby there are unfilled capacities to improve and develop the lifestyle and overall health conditions of the global community at large. This includes providing key solutions to external issues that continue to pose as threats to society.


# Problem Statement

**Healthcare cost**

Estimates from the World Health Organization (WHO) and other sources, out-of-pocket (OOP) payments constitute a substantial portion of total healthcare spending in many countries, especially those with fragmented or underfunded healthcare systems. These expenses include payments made directly by individuals for medical consultations, diagnostic tests, medications, hospitalizations, and other healthcare services not covered by insurance or public health programs.

In many low- and middle-income countries, out-of-pocket payments can account for a significant share of total healthcare expenditures, often exceeding 50% or more. This reliance on out-of-pocket financing can pose financial barriers to accessing essential healthcare services, leading to inequities in healthcare access and potential financial hardship for individuals and families, particularly those with low incomes or limited access to social protection.

Recruiting participants for clinical trials is a significant component of the overall budget, often accounting for a substantial portion of total costs. On average, patient recruitment expenses can constitute up to 40% of a clinical trial's budget.

The cost to recruit a single patient varies depending on factors such as trial complexity, therapeutic area, and recruitment strategies employed. Estimates suggest that recruiting one patient can cost approximately $6,500. If a patient drops out and needs to be replaced, the cost can escalate to around $19,500 per patient.

These figures highlight the financial impact of patient recruitment and retention on clinical trial budgets.&#x20;

&#x20;

**Accessibility to healthcare**

Rural and underdeveloped regions, lack access to medical facilities and professionals, base on report from World Bank and WHO on 2017: Half the world lacks access to essential health services, 100 million still pushed into extreme poverty because of health expenses. The statistic has grown on an impeccable level recently due to many disadvantage factors happening globally.

**Healthcare Data Breaches**

In 2024, healthcare data breaches reached unprecedented levels, affecting over 168 million Individuals in the United States. Anonymity in medical records serves several important purposes, each contributing to the protection of patient privacy, confidentiality, overall healthcare quality and facilitating responsible data use for research and healthcare improvement initiatives. Patient privacy and confidentiality, healthcare organizations can uphold ethical standards, comply with regulatory requirements, and promote positive impact to society.

**Diagnosis accuracy and efficiency**

People are not going to do medical check! More sickness can be cured with early detection. Human diagnosis prone to error and varies in accuracy, based on experience not based on data.

&#x20;&#x20;

**Selfish Behaviour by Medical Facility in for greater good**

In the healthcare industry, instances of medical facilities acting selfishly can occur when their primary focus shifts away from patient care and community well-being towards profit maximisation or other self-serving objectives while collaborative effort for the better of mankind is often ignore from top down. BitDoctor is dedicated to delivering truthful health information and restoring the optimal health everyone deserves.&#x20;


# Market Insights

<figure><img src="/files/6pnw4o1zYhxX7cv1cmCY" alt=""><figcaption><p><a href="https://www.who.int/news/item/13-12-2017-world-bank-and-who-half-the-world-lacks-access-to-essential-health-services-100-million-still-pushed-into-extreme-poverty-because-of-health-expenses">https://www.who.int/news/item/13-12-2017-world-bank-and-who-half-the-world-lacks-access-to-essential-health-services-100-million-still-pushed-into-extreme-poverty-because-of-health-expenses</a></p></figcaption></figure>

**Advertising Gap in Healthcare**

Due to strict advertising restrictions, the healthcare industry faces limited channels for promotion. Despite this, the global healthcare advertising market is valued at USD 59.9 billion and is projected to grow at a CAGR of 5.3% from 2023 to 2032. Notably, advertising spending in healthcare represents only 0.27% of the total industry value. In contrast, the global healthcare services market is massive—currently valued at USD 22.57 trillion—and is expected to grow at a CAGR of 6.05% from 2024 to 2033. BitDoctor aims to tap into just 1% of this market, which translates to a target opportunity of USD 225.7 billion.
\
-<https://www.linkedin.com/pulse/healthcare-advertising-market-size-share-trends-report-denis-green-prasf>
\
-<https://www.precedenceresearch.com/hospital-services-market>

**Clinical Trial Patient Recruitment Market**

In 2024, the U.S. clinical trial patient recruitment services market was valued at approximately USD 428.8 million and is projected to reach USD 711.2 million by 2030, reflecting a compound annual growth rate (CAGR) of 7.5% from 2024 to 2030.

**Fitness App Market**

The global fitness app market size according to the researchers at Extrapolate, the global [mHealth Market](https://www.globenewswire.com/Tracker?data=QKgjcNvMFOWVrjYRFHZHUry-kLX33O3k7eYWnLjlzFxHsMCJhOtCFavE8NmftsNW46lP1FOgbz55-ds10C2f6OtanO4VEryr9SgElbzb6l1MTHGxHm85mscIajzbcsz_zGKaGBm_aKlt_CKmENlq4L3vlBLDsplMimki_zVmT5o=) size was valued at USD 35.2 billion in 2021 and is anticipated to expand to USD 293.2 billion in 2030.

**Health Check-Up Market Size**

Medical health check-up market size alone reach USD 51.36 billion in 2023.

**Out Of Pocket Healthcare Expenses**

The report shows that global spending on health continually rose between 2000 and 2018 and reached **US$ 8.3 trillion or 10% of global GDP**. The data also show that out-of-pocket spending has remained high in low and lower-middle income countries, representing greater than 40% of total health spending in 2018.

**Fitness Industry**

An evergrowing global emphasis on health consciousness and the pursuit of an active lifestyle dictates that the fitness industry will continue to see stimulated growth and transformation over the coming years.

* Despite experiencing [steady growth](https://www.statista.com/statistics/275035/global-market-size-of-the-health-club-industry/) in the past decade, with a nearly **30% increase from 2009 to 2019**, the fitness industry has faced challenges due to the global pandemic.&#x20;

#### Deloitte report found that the total impact of the health and wellness market worldwide has [<mark style="color:red;">now reached $91.22 billion</mark>](https://www.healthclubmanagement.co.uk/health-club-management-features/Research-Deep-impact/35887)<mark style="color:red;">.</mark> Key Drivers Behind the Growth of the Fitness Industry?

<figure><img src="/files/o4grbr8WE2X2mFSL2pMJ" alt=""><figcaption></figcaption></figure>

#### One notable trend in the fitness industry is the **increasing** [integration of technology and digital innovations](https://www.perfectgym.com/en/blog/business/fitness-technology-transform-your-gym). Fitness apps, wearable devices, and online fitness platforms have revolutionised how people engage with fitness and wellness activities. The accessibility and convenience offered by digital solutions have [opened new avenues](https://www.ukactive.com/reports/digital-futures-2022/).


# Preventive Healthcare

Ultimately this technology will be the most commonly use preventive healthcare tool that can focuses on identifying and addressing health risks before they escalate into more severe conditions. It includes activities such as regular checkups, screenings, and lifestyle modifications to maintain optimal health and prevent chronic diseases.&#x20;

The importance of preventive healthcare cannot be overstated. By taking a proactive approach to health, individuals can avoid costly and debilitating medical conditions that negatively impact their quality of life. Furthermore, preventive healthcare can maximise on savings as there is significant potential to reduce healthcare costs associated with chronic disease management, hospitalisations and emergency services.&#x20;

Enforcing regular check-ups will provide for early detection, allowing for timely intervention and more effective-prone treatments, which can prevent complications and potentially save lives.

**This has been proven by a report, following a WHO statement that via rigorous prevention, we can save up to 16 million lives from experiencing non-communicable diseases (NCDs).**

**These are NCDs that account for 71% of global mortality rates, some of which include:**

**Cardiovascular diseases** \
**Cancer** \
**Respiratory Diseases** \
**Diabetic**\
**Mental Health**

In essence, preventive healthcare empowers individuals to take charge of their health and wellbeing more proactively, allowing them to lead a more fulfilling life.


# Unique Value Proposition

1\) BitDoctor is creating a smart health ecosystem from collecting health data to running clinical trials, offering medical advice, and delivering AI-powered diagnostics—it’s all streamlined to reduce user’s healthcare cost and providing Universal Health Coverage to who ever that owns a smartphone.

2\) With just a mobile phone, anyone can screen for early signs of disease anytime, anywhere—no more long hours at medical centers for a basic check. Early detection of NCDs can potentially save millions of lives annually.

3\) Over time, BitDoctor’s AI Doctor agent learns to spot patterns, assess health risks, and deliver personalized advice to help people live longer, healthier lives. Its algorithms aim to detect issues earlier and more accurately than traditional methods.

4\) To protect user privacy, all health data is secured using blockchain—fully anonymous, transparent, and accessed only with consent.

5\) BitDoctor also makes staying healthy fun through gamified rewards and challenges. Users are encouraged to take better care of themselves while earning real benefits.


# BitDoctor Blockchain Technology Stack

Decentralized Health Data Management System

<figure><img src="/files/HvJWREsYmy7lJhZXs7qw" alt=""><figcaption></figcaption></figure>

This document outlines the architecture for BitDoctor.AI, a decentralized system leveraging blockchain technology for managing health data, analysis, and rewarding contributors. The system incorporates **Decentralized Physical Infrastructure Networks (DePIN)** and **Decentralized Science (DeSCI)** principles to create a transparent, secure, and community-driven ecosystem. Additionally, it introduces a **Flywheel Effect** to drive network growth and a **Data Protocol Vision** that invites developers and researchers to build on top of anonymized health data.

Note

1\) The final choice of blockchain architecture is **TBD**. We are still evaluating whether to deploy on our own **native blockchain** or use an **L2 solution** (e.g., Base) or **Solana**.&#x20;

2\) The **LIV** points mentioned in this document are **in-game points** used to determine weightage for future airdrops; they are **not the final token.**

## 1. Core Components and Flow&#x20;

#### a) Data Sources&#x20;

**BitDoctor Smartphone AI Doctor:** \
\- Collect health metrics such as heart rate, blood pressure, heart attack risk, diabetes risk, etc. \
\- Forward the data to the system via the **BitDoctor Gateway.**&#x20;

**b) BitDoctor Gateway** \
\- **Entry Point:**\
Acts as the entry point for the collected data. \
\- **Processing and Forwarding:** \
**Blockchain (TBD):** For creating a decentralized identity (DID) and storing data hashes. \
**Centralized Databases or IPFS/Arweave**: For scalable storage of health data.&#x20;

**c) Blockchain (TBD)** \
\- **Data Integrity**: Ensures data integrity and security. \
\- **Decentralized Identity (DID)**: DID and data hashes are stored for transparency and validation. \
&#x20;\- **Reward System**: Handles the reward system via a Reward Contract (using LIV points for distribution weightage, until final token is determined).&#x20;

**d) Data Storage** \
\- **Filecoin/Arweave**: Decentralized storage solutions for health data. \
\- **Centralized Database**: Backup or complementary storage for certain data needs.&#x20;

**e) BitDoctor Aggregator** \
\- **Data Aggregation and Analysis**: Aggregates health data and analyzes it. \
\- **Outputs**: Medical reports. Propensity for diseases. \
\- **Sharing**: Shares data with medical providers and AI agents for further use.&#x20;

**f) Consumers** \
\- **Stakeholders**: Medical Institutions, End Users, and Health Agencies. \
\- **Access**: These stakeholders pay (in tokens or other agreed-upon means) to access medical reports and health data insights.

**g) AI Agents** \
\- **Enhanced Models**: Use the aggregated data to enhance AI-driven medical models for diagnostics or predictive analytics. \
\- **Tracking**: Contributors to these models are tracked using the Model Contributor Tracking system.&#x20;

h) **Reward System** \
**- Contributor Rewards**: Individuals providing BitDoctor application data are rewarded with LIV points (which may later translate to token allocations). \
\- **Management**: \
\&#xNAN;*Data Contributor Validator*: Validates data contributions. \
\&#xNAN;*Reward Contract:* Allocates points based on contributions.&#x20;

**i) Medical Providers** \
**Access**: Gain access to aggregated data and reports for diagnostics or treatment recommendations.

## 2. DePIN and DeSCI Integration&#x20;

### Decentralized Physical Infrastructure Networks (DePIN)&#x20;

**a) Distributed Data Collection** \
\- Leverages BitDoctor application as physical infrastructure to collect health data. \
\- Incentivizes device owners through LIV points to participate in a contributing their data.&#x20;

**b) Infrastructure for AI Training** \
\- Uses distributed computing and data storage networks (e.g., Filecoin, Arweave) to support massive AI model training workloads. \
\- Reduces dependency on centralized entities, democratizing access to AI capabilities.&#x20;

**c) Network Security and Integrity** \
\- Ensures data collected from physical infrastructure is securely stored and accessible only through permissioned blockchain-based mechanisms.

### Decentralized Science (DeSCI)&#x20;

**a) Open Data for Research** \
\- Health data aggregated through BitDoctor is anonymized and shared with the global scientific community for disease research and predictive model development.\
\- Researchers can access data via a pay mechanism (or token model), ensuring contributors are rewarded fairly for their participation.&#x20;

**b) Transparent Model Development** \
All AI models developed using contributor data are anonymized and governed on-chain, ensuring transparency and accountability.

**c) Collaborative Research Incentives** \
Encourages scientific collaborations by rewarding contributors whose data significantly enhances research outcomes, fostering innovation in healthcare.&#x20;

**d) DeSCI Tokenomics** \
A portion of institutional payments for medical data or AI models is reserved for funding decentralized scientific initiatives.

## 3. Reward and Tracking System&#x20;

#### a) Recognition and Rewards&#x20;

* Ensures contributors of data or models are recognized and rewarded.&#x20;
* DID and wallet information is used to ensure transparency in reward distribution (through LIV points).

**b) Profit Distribution Contributors** \
to the AI models generating profits are identified, and LIV-based rewards are allocated accordingly.

## 4. Reward Distribution in LIV (Points)&#x20;

### Reward Calculation&#x20;

**a) DID Creation** \
\- When a contributor logs in via the mobile app, a unique Decentralized Identifier (DID) is created (e.g., did:bitdoc:12345abc). \
\- The DID tracks the contributor’s data contributions, which are stored along with metadata about the data (e.g., type, volume, timestamp, relevance). \
\- The DID does not equate to a wallet but acts as a bridge between the contributor’s data and the reward (points) allocation process.

**b) Wallet Linking** \
\- Contributors link their DID to a wallet address through the app. Mapping between the DID and the wallet is securely stored: {

"DID": "did:bitdoc:12345abc",

"Wallet": "0x12345abcdef67890"

} \
\- If a wallet is not linked, the allocated points remain tied to the DID until claimed or converted (upon token launch).

### Data Collection&#x20;

**Contributor Participation** \
Contributor A uploads health data (e.g., heart rate, blood pressure) via their BitDoctor application.&#x20;

The system assigns this data to their DID (did:bitdoc:12345abc) and logs it with metadata:&#x20;

{

"DID": "did:bitdoc:12345abc", "Data": { "Type": "Heart Rate, Blood Pressure", "Volume": "1,000 records", "Timestamp": "2025-01-01T10:00:00Z",

"Relevance": "High"

}

}

### AI Model Training&#x20;

**Massive Data Pool** \
The Stroke Prediction Model is trained using data from 50,000 contributors. \
The system logs each DID whose data was used for training: {

"Model": "Stroke Prediction Model", "Contributors": \[ { "DID": "did:bitdoc:12345abc", "Volume": 1000, "Relevance": "High" },

{ "DID": "did:bitdoc:67890xyz", "Volume": 500, "Relevance": "Medium" }

]

}

### Payment and LIV Allocation&#x20;

**a) Institution Payment** \
\- Suppose a hospital pays a certain amount (e.g., 100,000 tokens or a stablecoin equivalent) for access to the Stroke Prediction Model / data. \
\- A portion of that payment (e.g., 50%) is allocated to the reward pool for contributors.&#x20;

**b) Reward Pool Allocation** \
\- **LIV** points are allocated based on: Volume of data contributed. Relevance of the data (e.g., stroke-specific metrics may carry more weight). \
\- **Example Allocation**:&#x20;

* Contributor A’s data volume: 1,000 records.&#x20;
* Total data volume: 50,000,000 records (all contributors combined).&#x20;
* Contributor A’s share: \
  \- Adjustments for relevance: High relevance multiplier (e.g., ×2): Contributor A earns 2 LIV points.

**c) Reward Storage**

Allocated points are stored on the blockchain (or sidechain) under the contributor’s DID until they are claimed:&#x20;

{

"DID":&#x20;

"did:bitdoc:12345abc",&#x20;

"Allocated Points": 2&#x20;

}

### DID-to-Wallet Mapping Example&#x20;

**a) Contributor Logs In** \
Contributor A logs into the system app and links their DID (did:bitdoc:12345abc) to their wallet (0x12345abcdef67890).&#x20;

**b) Mapping on Blockchain**

The system records:&#x20;

{

"DID": "did:bitdoc:12345abc",

"Wallet": "0x12345abcdef67890"

}

**c) Claiming Process** \
\- Contributor A logs into the app and view the LIV points. Claimable tokens are determined based on the LIV points of the contributor. \
\- Contributor A clicks on the claim button and the system validates their wallet and processes the transaction, transferring tokens from the reward pool to their wallet.

**d) Audit Log**

Blockchain transaction log: \
{

"Transaction ID": "tx123456",&#x20;

"DID":&#x20;

"did:bitdoc:12345abc",&#x20;

"Wallet":&#x20;

"0x12345abcdef67890", "Points&#x20;

Claimed": 2,&#x20;

"Timestamp": "2025-01-02T12:00:00Z"

}

## 5. Token and Gas Mechanism (TBD)&#x20;

As mentioned, the final choice of **blockchain architecture** is still under discussion (native chain vs. L2 solutions like Base vs. Solana). The LIV points described here are not the final token but an in-game metric for airdrop weightage. Below is a conceptual overview, which may evolve:

**Proposed Token Structure (Subject to Change)**&#x20;

**a) BitDoctor's Future Token (TBD)** \
\- The primary token within the BitDoctor ecosystem will be determined after the chain choice (native vs. L2). \
\- This token could be used for: \
i) Payments for accessing medical reports. \
ii) Rewards to contributors.&#x20;

**b) Gas Fee Mechanism** \
\- If BitDoctor launches its own network, gas fees could be denominated in the BitDoctor token or in a well-adopted gas token (e.g., ETH on L2, SOL on Solana). \
\- Until then, LIV points will serve as an internal reward and accounting mechanism.

### Cross-Chain Compatibility (Possible Directions)&#x20;

**a) Bridge to Popular Blockchains** \
\- To enhance liquidity in the future, bridging mechanisms may be implemented, allowing the final token to be interoperable with popular chains (e.g., Ethereum, BSC, Solana). \
\- LIV points, as an internal measurement, would eventually convert or unlock the final token.&#x20;

**b) Seamless Conversion** \
A bridging or conversion contract could facilitate the movement of tokens between ecosystems, ensuring holders can leverage multiple blockchain networks.

### Benefits of a Dedicated Mechanism&#x20;

**a) Efficiency (If Native or L2)** \
**-** A streamlined chain or L2 could reduce transaction costs and congestion.&#x20;

**b) Flexibility** \
**-** Cross-chain bridges provide users with greater liquidity options.&#x20;

**c) Sustainability** \
\- A well-designed token model ensures long-term viability for data contributors and ecosystem partners.

## 6. Flywheel Effect and Ecosystem Growth&#x20;

### The Flywheel Dynamics&#x20;

**a) Incentivizing Data Submission** \
\- Contributors are rewarded (via LIV points) for submitting health data. \
\- This incentivizes individuals to upload data more frequently, improving the quantity and quality of the dataset.&#x20;

**b) Enhanced Data Value** \
\- As data volume and quality increase, the health dataset becomes **more valuable.** \
\- A larger and richer dataset attracts more medical institutions and researchers, who purchase access to the data and AI models.&#x20;

**c) Platform Revenue Growth** \
\- With more data and growing demand, BitDoctor’s revenue from data sales and AI model subscriptions increases. \
\- Part of these revenues is **channeled back** into the reward pool.&#x20;

**d) Increased Incentives for Members** \
\- As revenues grow, the system can offer **higher rewards** (via more LIV points which gives weightage for future token airdrops) to new and existing contributors.\
\- This further **encourages** more data submissions and participant growth.&#x20;

**e) Reinforcing the Cycle** \
The cycle repeats, creating a **positive feedback loop**: More data leads to more value, which leads to more revenue, which leads to more rewards, and thus encourages even more data contributions.

## 7. Data Protocol Vision and Developer Integration&#x20;

### Becoming a Data Protocol&#x20;

**a) Protocol Approach** \
\- Over time, BitDoctor aims to evolve into a **comprehensive data protocol**, aggregating vast amounts of anonymized health data. \
\- This protocol will serve as a **foundation laye**r upon which developers, researchers, and AI model creators can build.&#x20;

**b) Developer Ecosystem** \
\- By exposing APIs and smart contract interfaces, developers can create applications or tools that **leverage anonymized health data**. \
\- Examples include: \
i) Advanced AI-driven diagnostics tools. \
ii) Research platforms for epidemiological studies. \
iii) Customized health and wellness apps offering personalized recommendations.&#x20;

**c) Open Collaboration** \
\- **Researchers and AI model developers** are invited to build on top of the protocol. \
\- **DeSCI** principles ensure that data remains **open, anonymized,** and **securely permissioned,** fostering a global community of innovators in healthcare.

### Anonymized Data for Developers&#x20;

**a) Privacy by Design** \
All data made available to third-party developers will be anonymized and stripped of personally identifiable information (PII).&#x20;

**b) Enhanced Research Outcomes** \
The **richness** of the dataset, combined with its **anonymized** nature, fosters cutting-edge research and AI model development without compromising individual privacy.

## 8. Conclusion&#x20;

BitDoctor.AI aims to revolutionize healthcare data management by combining **decentralized technology, robust incentive mechanisms,** and **privacy-focused data sharing**. Through its **Flywheel Effect**, the platform drives continuous growth and increased value for all participants. By evolving into a **data protocol**, BitDoctor invites developers, researchers, and AI innovators to build transformative healthcare solutions on top of a vast pool of **anonymized health data**—ultimately improving global health outcomes while ensuring contributors are **fairly rewarded** via **LIV points** (and, in the future, a fully realized token).


# Our AI Technology

Combining neuroscience, psychology, physiology and Deep Learning to produce an Affective AI engine that ultimately become the key provider under the universal health coverage (UHC) principles.

In the intersection between Affective Computing and Artificial Intelligence.

BitDoctors AI starts by track key region of the subject using any conventional video camera including those found in a smartphone.

<figure><img src="/files/HNTPphWkJsGm7I7Wopm1" alt="" width="563"><figcaption></figcaption></figure>

<figure><img src="/files/MrS5DNV4s6HfdbuY3ZLZ" alt="" width="563"><figcaption><p>BitDoctor AI automatically detects and tracks and identifying key regions of interest (ROIs)</p></figcaption></figure>

**Blood Flow Data Extraction**

Human skin is translucent. Light and its respective wavelengths are reflected at different layers below the skin and can be used to reveal blood flow information in the human face. This information is captured by and contained in conventional video images. BitDoctor AI extracts this information and sends it securely up to the cloud to be processed by BitDoctor’s AI, our cloud-based Affective AI engine.

<figure><img src="/files/X0lbdcicln0DQEvz0Q3j" alt="" width="563"><figcaption><p><strong>No image or video is taken during the whole process.</strong></p></figcaption></figure>

**Signal Processing and Deep Learning**

Extracted facial blood flow data is sent up to the cloud where our AI Doctor engine applies advanced signal processing and Deep Learning AI models to predict physiological and psychological affects together with our medical partners.

<figure><img src="/files/5Pr5jQHTlNQqLkZkLq3s" alt=""><figcaption></figcaption></figure>

BitDoctor AI imaging technology is a recently developed variant of remote photoplethysmography for imaging blood flow patterns from video of the face. Video-based photoplethysmography capitalizes on the following facts.&#x20;

First, because of the translucent nature of facial epidermis, ambient light can penetrate the epidermis and reach the tissue below, with some of it reflected back out of the skin. Second, the digital optical sensors in smartphones are highly sensitive and thus can capture re-emitted light and its small attenuations. Third, the quantity of hemoglobin protein in the blood and melanin pigment in the skin determines the color of light that is reflected back out of the skin. Each has a different color signature, so it is possible to separate re-emitted light containing mostly hemoglobin information from light containing melanin information based on the differential absorbance characteristics of these 2 light-absorbing proteins.

<figure><img src="/files/JnixZpKT2PsZE2XEJPDv" alt=""><figcaption></figcaption></figure>

![A diagram of a light source&#x20;
Translucent nature of facial epidermis, ambient light can penetrate the epidermis and reach the tissue below, with some of it reflected back out of the skin. ](/files/t4g4ibhPkkZA8kSqP72z)

In BitDoctor AI imaging technology, light from the visible spectrum travels beneath the skin surface and is re-emitted before being captured by the camera sensor. BitDoctor AI imaging technology capitalizes on subtle changes in skin color from the difference in re-emitted light between hemoglobin and melanin chromophores to detect blood flow pulsation in the cardiovascular system.&#x20;

The process of BitDoctor AI imaging technology involves: \
(1) capturing video of the face using a conventional camera \
(2) extracting spatiotemporal images of hemoglobin concentration from the bitplanes of the red, green, and blue image channels using advanced machine learning \
(3) processing the hemoglobin signal from 17 different regions of interest\
(4) extracting features from these signals, and \
(5) using a blood pressure prediction model trained with advanced machine learning algorithms to indicate blood pressure from these signals.

### **Results**

Results processed by BitDoctor AI Imaging engine are then sent back to your device for display and further analysis.

<figure><img src="/files/ub5VcMFqdM5OWkfF0J32" alt="" width="563"><figcaption></figcaption></figure>

The accuracy measurements have been trained and validated. The computational models against already well-established scientific instruments found in labs and clinics. Accuracy and validity of the measurements have been tested at regulated medical body.\
\
An article by Google Research explain clearly how this is possible with just a smart phone\
<https://research.google/blog/a-step-towards-making-heart-health-screening-accessible-for-billions-with-ppg-signals/>

**Technology currently deployed on:** \
*Google Play Store* \
[https://play.google.com/store/apps/details?id=com.bitDoctor.ai.android\&hl=en  ](https://play.google.com/store/apps/details?id=com.bitDoctor.ai.android\&hl=en)\
*Apple App Store*\
<https://apps.apple.com/us/app/bitdoctor-ai/id6738619305>

Referral code is required. Request from existing community members on [Telegram](https://t.me/BitDocAI) or [Discord](https://discord.gg/r2wWZmwk8t).


# Training BitDoctor's AI

<figure><img src="/files/cRanqr45vw3njhbeHSHW" alt="" width="563"><figcaption></figcaption></figure>

In its relentless pursuit of advancing healthcare through state-of-the-art technology, BitDoctor meticulously crafts a comprehensive process to train its AI models. Embarking on this journey, BitDoctor initiates with the meticulous collection of vast and varied datasets, encompassing images that capture intricate facial vascular networks. These datasets are meticulously curated from an array of sources including esteemed medical databases, reputable research institutions, and valuable contributions from users. Each individual image undergoes an intricate process of annotation, meticulously delineating key regions of interest such as those containing melanin and hemoglobin. This meticulous annotation serves as indispensable ground truth data essential for the meticulous training of BitDoctor's AI models.

As the journey progresses, BitDoctor employs rigorous preprocessing techniques to ensure the uniformity and consistency of the dataset. This involves meticulous standardization of image sizes, enhancement of image quality, and the meticulous elimination of any artifacts or noise. Leveraging cutting-edge machine learning algorithms, particularly the proficiency of convolutional neural networks (CNNs), BitDoctor meticulously selects models known for their adeptness in feature extraction and pattern recognition from input data.

The pivotal stage of model training ensues, utilizing renowned machine learning techniques such as deep learning. Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Transformer models emerge as commonly employed architectures in the realm of medical AI. Throughout this rigorous training process, the AI model evolves, discerning and differentiating between various features within facial vascular networks with precision. BitDoctor meticulously hones the model's capability to identify melanin-rich and hemoglobin-rich regions, ensuring accuracy and generalization while diligently guarding against overfitting.

As the AI model progresses through continuous validation against separate datasets, BitDoctor adeptly refines its parameters. This iterative refinement process is pivotal in ensuring the model's efficacy in analyzing facial vascular networks and providing reliable health analyses to users. Through extensive testing on independent datasets, BitDoctor meticulously evaluates the model's performance metrics, encompassing precision, recall, and overall accuracy. By fervently embracing an iterative process and perpetually updating the AI model with fresh data, BitDoctor steadfastly maintains its position at the forefront of healthcare innovation. Committed to delivering cutting-edge solutions, BitDoctor empowers individuals to effectively manage their health, epitomizing a paradigm shift in healthcare delivery. Furthermore, BitDoctor diligently validates and evaluates trained models, ensuring adherence to rigorous regulatory standards and clinical requirements, thereby cementing its reputation as a beacon of excellence in the realm of healthcare innovation.


# Hardware And Imaging Requirement

<figure><img src="/files/2hKr5KTCwLXUXJqyfFBC" alt=""><figcaption><p>Smartphone Optical Sensor</p></figcaption></figure>

**Optical Sensors**: Smart phone front camera turning into optical sensors are the core hardware components used in the AI Imaging system. Built in AI sensors typically utilize techniques such as near-infrared (NIR) spectroscopy or diffuse optical imaging to capture light absorption and scattering properties of tissues beneath the skin. AI sensors implemented may include photodiodes, photodetectors, or other light-sensitive elements to convert a common smart phone camera in to this technology.

**Light Sources adjustment with AI**: BitDoctoc.ai systems require basic light sources to illuminate the skin's surface and enable optical measurements. Converting any light source at the surrounding to become NIR spectrum are used as light sources for BitDoctor AI’s applications. These sources provide the necessary wavelengths for deeper tissue penetration and accurate measurements of hemoglobin concentration and oxygenation levels.

**Imaging System**: BitDoctor AI’s setups incorporate imaging systems to capture and process optical signals from through a smart phone front camera. Imaging techniques such as spatial frequency domain imaging (SFDI) or time-resolved imaging is used to enhance the spatial and temporal resolution of the measurements. Imaging systems include cameras, lenses, filters and image processing algorithms to reconstruct tissue parameters from raw optical data.


# Clinical Measurement Reports

Clinical trials are conducted to validate the accuracy of each parameter. The measurement details and results are presented under each subpage.

{% hint style="info" %}
Moment-to-moment fluctuations in the user's physiology mean that risk estimates could vary to some degree from one measurement to the next. The best estimate of a user's overall risk can therefore be obtained by averaging several measurements throughout the day and across several days to adequately account for this physiological variation.
{% endhint %}

**Each measurement is conducted with the following minimum information requirement, data collection setup, and data collection procedure (additional details are provided if any):**

## Information Required&#x20;

• Blood flow information extracted from video of the user’s face (BitDoctor Technology)&#x20;

• Demographic information (From the user profile)

## Data Collection Setup&#x20;

The participant’s face was illuminated with LED lights. Blood flow information was captured from conventional video of the face using BitDoctor Application for iOS (research version).&#x20;

## Data Collection Procedure&#x20;

BitDoctor Application was activated to record a 30-second video of the subject using the front facing camera of the iPhone. At the end of each recording, subjects were asked to fill out a questionnaire to collect their demographic information.


# Heart Rate

## Description&#x20;

Heart rate (HR) is the number of times the user’s heart beats, expressed as a rate per minute. A bpm of 60-100 is considered healthy/normal.

## Participants&#x20;

Subjects were recruited from Affiliated Hospitals. There were no exclusion criteria when recruiting participants, although most participants were healthy adults above 18 years of age. Table 1 summarizes participant characteristics.

| Participants              | Composition          |
| ------------------------- | -------------------- |
| Average Age               | 41.2 years           |
| Standard deviation of age | 15.2 years           |
| Gender distribution       | 48% Male; 52% Female |

*Table 1: Characteristics of participants for HR and MSI*

## Additional Data Collection Setup

Reference heartbeat information was collected with a 3-lead electrocardiograph (ECG). The data collection setup is depicted in Figure 1.

<figure><img src="/files/wMCQ1LqALxEPtlzOt6qg" alt="" width="375"><figcaption></figcaption></figure>

*Figure 1: HR, Mental Stress Index & Irregular Heartbeat data collection setup*

## Analysis of Accuracy & Reliability&#x20;

Heartbeats were then identified in both ECG signal (reference signal) and BitDoctor signal (test signal).&#x20;

ECG captures heartbeats as characteristic fluctuations in the heart’s electrical signal that occur with each beat (Figure 2). The major peak in this fluctuation (R-wave) was used to identify each heartbeat on the ECG trace. The heart rate is calculated by counting the number of heartbeats on a given trace (Figure 3) and expressing this number as a per minute rate.

<figure><img src="/files/JSWYbvAgFHykWSM2PYFg" alt="" width="353"><figcaption><p><em>Figure 2: Labeled ECG wave.</em></p></figcaption></figure>

<figure><img src="/files/YOxBkKA0YV8POL5vV6of" alt=""><figcaption><p><em>Figure 3: ECG recording used for heart rate computation.</em></p></figcaption></figure>

This signal robustly tracks the activity of the heart in terms of number of beats and inter-beat timing (Figure 4). Like ECG, BitDoctor heart rate was calculated from each participant’s blood flow information.

<figure><img src="/files/oRB2OLr3hu0PihbWTR1a" alt=""><figcaption></figcaption></figure>

*Figure 4. Comparison between ECG heart rate and BitDoctor HR. BitDoctor signal trace (red) is overlaid on an ECG trace (blue) from a healthy adult.*

The accuracy of BitDoctor-based measurements relative to ECG-based measurements was then calculated, considering only measurements with a positive signal-to-noise ratio.

<figure><img src="/files/mkgLyVX8oF079GUnI8ij" alt=""><figcaption><p>Equation 1: Calculation of BitDoctor heart rate accuracy.</p></figcaption></figure>

HR accuracy was calculated as: (1 − 1 𝑁 ∑ | *BITDOCTOR* 𝐻𝑅 − 𝐸𝐶𝐺 𝐻𝑅 𝐸𝐶𝐺 𝐻𝑅 |) × 100%

### Results&#x20;

The accuracy and reliability of BitDoctor-based HR is presented in Table 2. Reliability refers to the test-retest reliability of each item.

| Physiological Measure | Accuracy (%) | Reliability (%) |
| :-------------------: | :----------: | :-------------: |
|           HR          |      99      |       100       |

*Table 2: Accuracy and reliability of BitDoctor HR*

## HR Accuracy Details&#x20;

Table 3 presents additional accuracy metrics pertaining to HR.

|                             | HR Accuracy (bpm) |
| :-------------------------: | :---------------: |
|         Mean ECG HR         |        74.4       |
|      Mean BitDoctor HR      |        75.1       |
|          Mean Error         |        0.63       |
| Standard Deviation of Error |        1.21       |
|    Mean of Absolute Error   |        0.79       |

*Table 3: Additional BitDoctor heart rate accuracy metrics*

Additional analysis was conducted to determine BitDoctor-based HR accuracy with shorter (30-second) measurements. Once again, BitDoctor-based HR tracked reference (ECG) HR very well (Figure 5). The Pearson correlation between ECG and BitDoctor measurements under these conditions was essentially perfect (r=1.0).

<figure><img src="/files/G4ya1IROeuy2I7Koj0Q5" alt="" width="331"><figcaption></figcaption></figure>

*Figure 5: Scatter plot of 30-second HR measurements taken by ECG and BitDoctor Technology.*


# Breathing Rate

## Description&#x20;

Breathing rate (BR) corresponds to the number of times the user inhales and exhales, expressed as a rate per minute (Range: up to 50 breaths/minute). 12-25 breaths/minute is considered healthy/normal.

## Method&#x20;

BR measured by BitDoctor was assessed against BR as measured with a respiration belt. All tests were conducted by researchers with experience in data collection, signal processing, and machine learning.&#x20;

## Participants&#x20;

The subjects were recruited from Affiliated Hospitals. There were no exclusion criteria when recruiting participants, although most participants were healthy adults above 18 years of age. Table 9 displays a summary of participant characteristics.

| Participants              | Composition          |
| ------------------------- | -------------------- |
| Average Age               | 41.2                 |
| Standard deviation of age | 15.2                 |
| Gender distribution       | 48% Male; 52% Female |

&#x20;                                                *Table 9: Characteristics of participants for breathing*

## Additional Data Collection Setup&#x20;

A mechanical respiration belt was attached around the thoracic region of each participant and then connected to a BIOPAC recording device. Figure 12 depicts the data collection setup.

<figure><img src="/files/su4vOajzyj6GQXKlcP0i" alt="" width="347"><figcaption><p>      <em>Figure 12: BR test setup</em></p></figcaption></figure>

## Additional Data Collection Procedure

Oscillations in the tension of the respiration belt (capturing inspiration and expiration) and video recordings of the participant’s face were captured in a 2-minute recording.

## Analysis of Accuracy & Reliability&#x20;

Reference BR was calculated by counting the number of breathing cycles (inspiration + expiration) captured by the respiration belt, and then expressing this value as a per-minute rate.&#x20;

BitDoctor-based BR was calculated by using the breathing detection algorithm to predict the number of breaths based on facial blood flow information, and then expressing this value as a per-minute rate.&#x20;

Breathing rate accuracy was then expressed as a Pearson correlation between participants’ reference breathing rate (as determined by respiration belt/BIOPAC) and breathing rate estimated by BitDoctor.

## Results&#x20;

The accuracy and reliability of BitDoctor BR is summarized in Table 10.

| Physiological Measure | Accuracy (%) | Reliability (%) |
| :-------------------: | :----------: | :-------------: |
|       Breathing       |      >90     |        99       |

&#x20;                                                 *Table 10: Accuracy and reliability of BitDoctor BR.*

The Pearson correlation between participants’ reference BR (as determined via respiration belt/BIOPAC) and BR estimated by BitDoctor was r=0.9. Figure 13 depicts the relation between reference BR (ground truth) and BitDoctor BR (predicted value)

<figure><img src="/files/QHuOWvwAqU2agFFeOUhr" alt="" width="563"><figcaption></figcaption></figure>

*Figure 13: Scatter plot depicting the relation between reference (ground truth) BR measured with a respiration belt and BR estimated from BitDoctor. The equation characterizes the line of best fit.*


# Irregular Heartbeat

## Description&#x20;

Irregular heartbeats (IHB) are those that occur outside the user’s normal heart rhythm (e.g., a premature ventricular contraction). BitDoctor Technology can be used to detect and count the number of IHB the user experiences within a given measurement period.  A bpm of 60-100 is considered healthy/normal.

## Method&#x20;

The ability to detect at least one irregular heartbeat via BitDoctor Technology was assessed against the presence of irregular heartbeats as determined by electrocardiograms (ECG) annotated by experienced cardiology nurses.&#x20;

## Participants&#x20;

Subjects were recruited from several cardiology clinics. These patients had been referred for ECGs and a large proportion had irregular heartbeats.&#x20;

## Additional Data Collection Setup

Same as the [setup as HR](/clinical-measurement-reports/heart-rate#additional-data-collection-setup).

## Additional Data Collection&#x20;

Each 30-minute recording was then sub-divided into 1-minute samples, resulting in 12,000 1- minute samples. Some of these were excluded due to movement or poor signal quality, leaving 24 10,997 samples for analysis. The electrocardiograph for each sample was then annotated by a cardiology nurse to identify segments with IHB.&#x20;

## Performance of IHB detection algorithm&#x20;

BitDoctor signal was extracted from each video and the IHB detection algorithm was employed to identify IHB within the signal. This algorithm employs machine-learning to identify IHB.&#x20;

The performance of this algorithm was assessed by recall, precision and f1 score. Recall is the percentage of cases where the BitDoctor-based algorithm detected an IHB when there was indeed an IHB (according to ECG). It was calculated as True Positives / (True Positives + False Negatives). Precision is the percentage of cases where an IHB actually occurred, out of all cases where the BitDoctor-based algorithm claimed an IHB had occurred. It was calculated as True Positives / (True Positives + False Positives). F1 score is the ‘harmonized mean’ of these measures, calculated as 2 \* (precision \* recall) / (precision + recall).&#x20;

## Results&#x20;

Recall was 96%, precision was 82% and the F1 score was 89% in terms of detecting at least one IHB.


# Heart Rate Variability

## Description&#x20;

Heart Rate Variability (HRV) is an important measure of the variation in time between successive heartbeats and reflects the dynamic balance between sympathetic and parasympathetic nervous system activity. HRV assessment is widely used as a tool for assessing cardiovascular function and overall health.&#x20;

HRV is influenced by various physiological factors that impact heart rate and variability between heartbeats, including breathing patterns, blood pressure regulation, and natural daily rhythms such as sleep-wake cycles, physical activity, and food intake. Together, these factors work to regulate the cardiovascular system, including heart rate and HRV.

The autonomic nervous system (ANS) plays a key role in regulating HRV by controlling heart rate and the balance between sympathetic and parasympathetic nervous system activity. The sympathetic nervous system is responsible for the "fight or flight" response to stress, which leads to an increase in heart rate and a decrease in HRV, while the parasympathetic nervous system is responsible for the "rest and digest" response, which leads to a decrease in heart rate and an increase in HRV.&#x20;

HRV can be measured using techniques such as electrocardiography (ECG) and photoplethysmography (PPG). Factors like stress, physical activity, sleep, and medication use can all influence HRV, and the interplay between these factors is complex. Understanding the impact of these factors on HRV can provide insights into the health and function of the cardiovascular system and help guide interventions to improve overall health.&#x20;

{% hint style="info" %}
BitDoctor Technology is designed to provide quick HRV measurements in just 30 seconds, but it's important to recognize that HRV analysis is typically performed over much longer periods of time to obtain accurate results. In general, electrocardiograms of at least 240-300 seconds are needed to reliably measure HRV. While short-term HRV measurements such as SDNN and RMSSD can be a useful approximation of longer-term HRV, there are some limitations. RMSSD is generally considered to be a more reliable measure than SDNN and averaging multiple 10- second ECG recordings can help to improve accuracy. However, it's important to use caution when interpreting the results of BitDoctor Technology, as it is subject to limitations similar to other short-term HRV analysis methods.
{% endhint %}

A value of 35.5 millisecond is considered healthy/normal.

## Analysis of Accuracy & Reliability&#x20;

The precise timing between heartbeats was calculated by measuring the time intervals between R-waves of successive beats (termed the R-R interval, Figure 6). The statistical variability in the length of successive intervals is termed heart rate variability (HRV). Certain HRV measures are closely associated with mental stress, and such measures were used to calculate the Mental Stress Index.

<figure><img src="/files/Iib551v3SfSUYCdAQOoz" alt=""><figcaption><p><em>Figure 6: The R-R Interval</em></p></figcaption></figure>

Heartbeats were then identified in blood flow signal extracted using BitDoctor technology. Rather than capturing electrical activity of the heart, blood flow signal characterizes arterial pressure pulses that propagate from the heart to the face with each beat of the heart. Advanced signal processing techniques are used to derive a robust blood flow signal. Such techniques include signal de-trending, de-noising and estimation of peaks and valleys (Figure 7).

<figure><img src="/files/OqAkNxspOqUUY0VFe6hU" alt=""><figcaption><p><em>Figure 7: RRI estimation algorithm in BitDoctor signals</em></p></figcaption></figure>

This signal robustly tracks the activity of the heart in terms of number of beats and inter-beat timing. Similar to ECG, R-R intervals (Figure 8 - Left) were calculated from each participant’s blood flow information. Intervals between beats were measured from trough to trough of the fitted waves (Figure 8 – Right).

<figure><img src="/files/KSYeyKPaLo8HK6nfsgSn" alt=""><figcaption><p><em>Figure 8: (Left) R-R interval in BitDoctor signals. (Right) The R-R Interval Signal extracted from ECG.</em></p></figcaption></figure>

The accuracy of BitDoctor-based measurements relative to ECG-based measurements was then calculated. Only measurements with a positive signal-to-noise ratio were included.

Once the R-R intervals are determined, there are different methods to analyze heart rate variability (HRV). Here are three common ways:

### 1. Time-domain analysis:&#x20;

A widely used method in heart rate variability (HRV) research, focusing on the examination of time intervals between successive heartbeats, known as interbeat intervals or R-R intervals, which are measured in milliseconds. This analysis provides valuable insights into the overall variability of the heart rate and the balance between sympathetic and parasympathetic nervous system activity. Additionally, a specific type of interbeat interval called the NN interval is of particular interest. The NN interval represents the interval between consecutive normal heartbeats, excluding any abnormal or ectopic beats. The analysis of NN intervals provides valuable insights into the variability of a normal heart rhythm. Table 4 presents some commonly used time-domain measures in HRV research, available through BitDoctor Technology along with their minimum required duration.

<table><thead><tr><th width="141">Signal Point </th><th width="73">Unit</th><th width="349">Feature Description </th><th align="center">Available after (sec)</th></tr></thead><tbody><tr><td>Mean HR</td><td>bpm</td><td>Average heart rate, expressed in beats per minute</td><td align="center">30</td></tr><tr><td>Mean RRI</td><td>ms</td><td>Average RR interval, expressed in milliseconds</td><td align="center">30</td></tr><tr><td>SDNN</td><td>ms</td><td>Standard deviation of NN intervals, expressed in milliseconds</td><td align="center">30</td></tr><tr><td>NN50</td><td></td><td>Number of adjacent NN intervals that differ from each other by more than 50 ms</td><td align="center">60</td></tr><tr><td>pNN50</td><td>%</td><td>Percentage of adjacent NN intervals that differ from each other by more than 50 ms</td><td align="center">60</td></tr><tr><td>RMSSD</td><td>ms</td><td>s Root mean square of successive RR interval differences, expressed in milliseconds</td><td align="center">30</td></tr></tbody></table>

*Table 4: Commonly used time-domain measures in heart rate variability (HRV) research.*

### 2. Frequency-domain analysis:&#x20;

Frequency-domain analysis is another method of HRV analysis that involves transforming the time-domain signal into its frequency components using mathematical techniques such as Fourier or wavelet transform. This method allows the identification and quantification of the variability in the different frequency bands of the HRV signal, which is related to the underlying physiological mechanisms involved in the regulation of the autonomic nervous system. Table 5 presents the most commonly used frequency-domain measures of HRV, available through BitDoctor Technology along with their minimum required duration.

<table><thead><tr><th width="140">Signal Point</th><th width="72">Unit</th><th width="342">Feature Description </th><th align="center">Available after (sec)</th></tr></thead><tbody><tr><td>VLF power</td><td>ms2</td><td>Power measured in the very-low-frequency band (0.003-0.04 Hz), expressed in sum of power</td><td align="center">120</td></tr><tr><td>LF power</td><td>ms2</td><td>Power measured in low-frequency band (0.04-0.15 Hz), expressed in sum of power</td><td align="center">120</td></tr><tr><td>HF power</td><td>ms2</td><td>Power measured in high-frequency band (0.15-0.40 Hz), expressed in sum of power</td><td align="center">120</td></tr><tr><td>Total Power</td><td>ms2</td><td>Summation of power measures in all frequency bands, expressed in sum of power</td><td align="center"></td></tr><tr><td>LF peak</td><td>Hz</td><td>Highest amplitude frequency in the low-frequency band (0.04-0.15 Hz) using Welch’s power spectral density estimate</td><td align="center">120</td></tr><tr><td>HF peak</td><td>Hz</td><td>Highest amplitude frequency in the high-frequency band (0.15- 0.40 Hz) using Welch’s power spectral density estimate</td><td align="center">120</td></tr><tr><td>LF power</td><td>nu</td><td>Proportion of power in the low-frequency band (0.04-0.15 Hz) to the summation of powers in low- and high-frequency bands, expressed in normal units (nu)</td><td align="center">120</td></tr><tr><td>HF power</td><td>nu</td><td>Proportion of power in the high-frequency band (0.15-0.40 Hz) to summation of powers in low- and high-frequency bands, expressed in normal units (nu)</td><td align="center">120</td></tr><tr><td>LF/HF</td><td></td><td>Ratio of power in low-frequency band (0.04-0.15 Hz) to power in high-frequency band (0.15-0.40 Hz)</td><td align="center">120</td></tr><tr><td>LF_AR peak</td><td>Hz</td><td>Highest amplitude frequency in the very-low-frequency band (0.003-0.04 Hz) using Autoregressive power spectral density estimate — Burg’s method</td><td align="center">120</td></tr><tr><td>HF_AR peak</td><td>Hz</td><td>Highest amplitude frequency in the high-frequency band (0.15- 0.40 Hz) using Autoregressive power spectral density estimate — Burg’s method</td><td align="center">120</td></tr></tbody></table>

*Table 5: Commonly used frequency-domain measures of heart rate variability (HRV) obtained through mathematical techniques such as Fourier or wavelet transform.*

### 3. Non-Linear Analysis:

Nonlinear HRV analysis is a sophisticated method of analyzing heart rate variability that utilizes complex mathematical algorithms to examine interactions among various components of the heart's autonomic control system. This approach involves the use of measures such as SD1, SD2, SD1/SD2, α, α1, and α2, which can be obtained from techniques such as Poincaré Plot and Detrended Fluctuation Analysis. Nonlinear HRV analysis can detect subtle changes in HRV and capture nonlinear relationships among different HRV parameters that may not be detected by traditional linear HRV analysis. By providing a more detailed and comprehensive view of HRV, nonlinear HRV analysis can aid in identifying early signs of cardiovascular disease, evaluating the effectiveness of interventions, and gaining insights into the underlying physiological mechanisms of HRV. A list of some of the measures used in nonlinear HRV analysis, available through BitDoctor Technology along with their minimum required duration can be found in Table 6.

<table><thead><tr><th width="136" align="center">Signal Point </th><th width="62">Unit</th><th width="359">Feature Description</th><th align="center">Available after (sec)</th></tr></thead><tbody><tr><td align="center">SD1</td><td>ms</td><td>Standard deviation of points perpendicular to the line of identity on the Poincaré Plot, expressed in milliseconds</td><td align="center">120</td></tr><tr><td align="center">SD2</td><td>ms</td><td>Standard deviation of points along the line of identity on the Poincaré Plot, expressed in milliseconds.</td><td align="center">120</td></tr><tr><td align="center">SD1/SD2</td><td></td><td>Ratio of SD1 to SD2 (both obtained from Poincaré Plot)</td><td align="center">120</td></tr><tr><td align="center">α</td><td></td><td>Scaling exponent of RR intervals over different time series based on Detrended Fluctuation Analysis</td><td align="center">120</td></tr><tr><td align="center">α1</td><td></td><td>Short-term fluctuations from Detrended Fluctuation Analysis</td><td align="center">120</td></tr><tr><td align="center">α2</td><td></td><td>Long-term fluctuations from Detrended Fluctuation Analysis</td><td align="center">120</td></tr></tbody></table>

*Table 6: Features of Nonlinear HRV Analysis Based on Poincaré Plot and Detrended Fluctuation Analysis*


# Hypertension Risk

## Description&#x20;

Hypertension Risk is the percentage likelihood that the user has hypertension (as diagnosed by a physician).&#x20;

It corresponds to the percentage of people with the user’s risk profile who report that they have been diagnosed with hypertension (irrespective of their current blood pressure reading).

Individuals with elevated hypertension risk might consider having their blood pressure monitored by a medical professional to determine if they meet the diagnostic criteria for hypertension.&#x20;

## Participants&#x20;

Adults (18+ years of age) recruited from several hospital health clinics.&#x20;

## Additional Data Collection&#x20;

Subjects were also asked whether they have been diagnosed with hypertension.

## Modeling Approach&#x20;

Blood flow signal was extracted and processed from facial video, and then blood flow features were extracted from blood flow signal.&#x20;

Feature selection was carried out on blood flow and demographic features to identify features predictive of hypertension status. A machine-learning based classifier was then created to predict an individual’s hypertension status based on those features.&#x20;

The model was created/trained using 80% of the subjects. The distribution of sex and hypertension status in this group is summarized in Table 1.

| Subjects in videos        | Composition                |
| ------------------------- | -------------------------- |
| Sex distribution          | 49.6 % Male; 50.4 % Female |
| Hypertension distribution | 20 % Hypertensive          |

&#x20;                                                  *Table 1: Hypertension distribution of training set*

## Model Performance&#x20;

The Hypertension Risk model was then validated for accuracy on an independent portion of the dataset (n=2,012) that was not used in training - validation set. Then the final accuracy was obtained on an independent portion of the dataset (n=2,012) that was not used in training - test set. The distribution of sex and hypertension status in these groups is summarized in Table 2.

| Subjects in videos        | Composition in Validation | Composition in Test      |
| ------------------------- | ------------------------- | ------------------------ |
| Sex distribution          | 49.8% Male; 50.2 % Female | 48.5 Male; 51.5 % Female |
| Hypertension distribution | 20 % Hypertensive         | 20 % Hypertensive        |

&#x20;                                      *Table 2: Hypertension distribution of validation and test sets*

The accuracy on the test set calculated as area under the curve was 88.9% as shown in Figure 2.

<figure><img src="/files/YHZ8gZTQavE5ohEAoTWu" alt="" width="563"><figcaption></figcaption></figure>

&#x20;                                                        *Figure 2: AUC of hypertension risk prediction*

Predictions are displayed to the user as a percentage likelihood of having hypertension. A percentage of 45% or more suggests a risk of hypertension, while 55% or more suggests high risk of hypertension.


# Type 2 Diabetes Risk

## Description&#x20;

**Type 2 diabetes risk** is the likelihood that the user has type 2 diabetes (impaired processing of blood sugar) and corresponds to the percentage of people with the user’s risk profile who have been diagnosed with type 2 diabetes (irrespective of their current blood sugar reading).&#x20;

Type 2 diabetes diagnosis considers blood sugar readings taken under specific conditions, and so individual measurements that are abnormally high (e.g., after meals) do not necessarily mean the user has diabetes. BitDoctor determines the user’s diabetes risk based on blood flow patterns and demographic information.&#x20;

A user with an elevated **type 2 diabetes risk** might consider having their blood sugar tested by a medical professional to determine if they meet the diagnostic criteria for diabetes.

## Participants&#x20;

Adults (18+ years of age) recruited from several hospital health clinics.&#x20;

## Additional Data Collection

Subjects were also asked whether they have been diagnosed with diabetes.

## Modeling Approach&#x20;

Blood flow signal was extracted and processed from facial video, and then blood flow features were extracted from blood flow signal.&#x20;

Feature selection was carried out on blood flow and demographic features to identify features predictive of diabetes status. A machine-learning based classifier was then created to predict an individual’s diabetes status based on those features.&#x20;

The model was created/trained using 80% of the subjects. The distribution of sex and diabetes status in this group is summarized in Table 3.

| Subjects in videos    | Composition               |
| --------------------- | ------------------------- |
| Sex distribution      | 51.5 % Male; 48.5% Female |
| Diabetes distribution | 25% Diabetic              |

&#x20;                                                   *Table 3: Diabetes distribution of training set*

## Model performance&#x20;

The Diabetes Risk model was then validated for accuracy on an independent portion of the dataset (n=684) that was not used in training - validation set. Then the final accuracy was obtained on an independent portion of the dataset (n=684) that was not used in training - test set. The distribution of sex and diabetes status in these groups is summarized in Table 4.

| Subjects in videos    | Composition in Validation | Composition in Test        |
| --------------------- | ------------------------- | -------------------------- |
| Sex distribution      | 53.4% Male; 46.6 % Female | e 51.5% Male; 48.5% Female |
| Diabetes distribution | 25% Diabetic              | 25% Diabetic               |

&#x20;                                         *Table 4: Diabetes distribution of validation and test sets*

The accuracy on the test set calculated as area under the curve was 82.1% as shown in Figure 3.

<figure><img src="/files/Tv7zsLOWxMlpD6VShzqV" alt="" width="563"><figcaption></figcaption></figure>

&#x20;                                                   *Figure 3: AUC of diabetes type 2 risk prediction*

Predictions are displayed to the user as a percentage likelihood of having diabetes. A percentage of 45% or more suggests a risk of diabetes, while 55% or more suggests high risk of diabetes.


# Cardiovascular Diseases Risk (incl. Heart Attack & Stroke Risks)

Future health risks evaluate the user’s risk of developing a condition in the intervening time between the present day and some duration of time into the future.

## Description&#x20;

This risk prediction model estimates an individual’s likelihood (in percent) of developing cardiovascular disease (specifically their **first heart attack** or **stroke**) within the next 10 years. It does not apply to people who have already had a heart attack or stroke.

## Additional Information Required

• Body Mass Index (kg/m2 ) (calculated from height and weight)&#x20;

• Systolic Blood Pressure (mmHg)

Estimates are more accurate when the user also answers the following questions in their user profile:&#x20;

1. Are you taking medication for high blood pressure? (yes/no)&#x20;
2. Are you currently a smoker? (yes/no)&#x20;
3. Do you have diabetes? (yes/no)

## Participants&#x20;

Risk prediction models were derived from and tested on the same sample of Chinese adults (18+ years of age).

## Additional Data Collection&#x20;

Subjects were also asked whether they have previously had a heart attack, and whether they have previously had a stroke. The participant’s systolic blood pressure was also measured (taken as the average of 3 measurements). Only participants without prior heart attack or stroke were included in the study.

Data collection took place at baseline (Year 0) and cardiovascular disease status was assessed 10 years later.

## Modeling Approach&#x20;

**Cox regression** - the same methodological approach used in deriving risk prediction equations in the Framingham Heart Study. It derives prediction functions based on data from a prospective study that collected risk factor information and cardiovascular disease status at baseline and then tracked the occurrence of cardiovascular disease events for at least 10 years. Participants with a prior heart attack or stroke were removed from analysis.&#x20;

We derived mathematical risk prediction equations in a manner similar to the cardiovascular disease prediction equations derived in the Framingham Heart Study (<https://framinghamheartstudy.org/fhs-risk-functions/cardiovascular-disease-10-year-risk/>). Specifically, we used sex-specific cox proportional hazard regression to relate risk factors (predictors) to the incidence of a first cardiovascular disease event.&#x20;

We derived two versions of each equation: one using the minimal set of risk factors above and another using the full set.

## Model Performance&#x20;

### Internal validation&#x20;

The area under the curve (AUC) for the full model was 0.72 (n=4500).&#x20;

### External validation&#x20;

The China-PAR equation is the gold standard for predicting risk in the Chinese population, but it requires the user to know their cholesterol values and thus it is not practical for most people.&#x20;

The correlation between the current model’s predictions (without cholesterol) and the ChinaPAR model's predictions (with cholesterol) was examined using an alternative Chinese dataset.&#x20;

The relation between these two values overall, in males only and in females only is depicted in Figure 4. The respective Pearson correlations are r=0.68, r=0.61 and r=0.74.

<figure><img src="/files/jC4ctzupqrOG1KbKnXzG" alt=""><figcaption></figcaption></figure>

*Figure 4: Validation against China-PAR equation; Scatter plot and Pearson r for: (a) Males and females, (b) Males only, and (c) Females only*

## Secondary Models: Heart attack and stroke&#x20;

Heart attack and stroke-specific models were derived in a similar manner.

Predictions are displayed to the user as a percentage likelihood of having diabetes. A percentage of 7.25% or higher suggests a risk of cardiovascular diseases, 2.39% or higher indicates a risk of heart attack, and 4.79% or higher suggests a risk of stroke.


# Hypercholesterolemia

## Description&#x20;

Hypercholesterolemia risk is the likelihood that the user has abnormally high cholesterol levels (defined as a total cholesterol (TC)-to-high density lipoprotein (HDL) cholesterol (“good cholesterol”) ratio of 4.1 or higher) and corresponds to the percentage of people with the user’s risk profile that have an abnormally high TC/HDL ratio. BitDoctor.ai determines the user’s risk of hypercholesterolemia based on blood flow patterns and demographic information.

## Participants&#x20;

Adults (18+ years of age) recruited from several hospital health clinics.

## Additional Data Collection

Subjects also received a blood test at the same clinic visit where their cholesterol levels were measured.

## Modeling Approach

Blood flow signal was extracted and processed from facial video, and then blood flow features were extracted from blood flow signal.&#x20;

Feature selection was carried out on blood flow and demographic features to identify features predictive of hypercholesterolemia. A machine-learning based classifier was then created to predict whether an individual has hypercholesterolemia based on these features.&#x20;

The model was created/trained using 80% of the subjects. The distribution of sex and hypercholesterolemia status in this group is summarized in Table 17.

|         Subjects in videos        |        Composition        |
| :-------------------------------: | :-----------------------: |
|          Sex distribution         | 46.5 % Male; 53.5% Female |
| Hypercholesterolemia distribution |            30%            |

&#x20;                                       *Table 17: Hypercholesterolemia distribution of training set*

## Model Performance&#x20;

The Hypercholesterolemia Risk model was then validated for accuracy on an independent portion of the dataset (n=700) that was not used in training - validation set. Then the final accuracy was obtained on an independent portion of the dataset (n=700) that was not used in training - test set. The distribution of sex and hypercholesterolemia status in these groups is summarized in Table 18.

| Subjects in videos                | Composition in Validation | Composition in Test      |
| --------------------------------- | ------------------------- | ------------------------ |
| Sex distribution                  | 47.8% Male; 52.2% Female  | 46.6% Male; 53.4% Female |
| Hypercholesterolemia distribution | 30%                       | 30%                      |

&#x20;                             *Table 18: Hypercholesterolemia distribution of validation and test sets*

The accuracy on the test set calculated as area under the curve was 80.3% as shown in Figure 22.

<figure><img src="/files/WpfQK7j8xD2X4PHdtGos" alt="" width="563"><figcaption></figcaption></figure>

&#x20;                                           *Figure 22: AUC of Hypercholesterolemia risk prediction*

Predictions are displayed to the user as a percentage likelihood of having hypercholesterolemia. A percentage of 45% or more suggests a risk of diabetes, while 55% or more suggests high risk of diabetes.


# Hypertriglyceridemia

## Description&#x20;

Hypertriglyceridemia risk is the likelihood that the user has abnormally high triglyceride levels (defined as being above 1.7 mmol/L or 150 mg/dL) and corresponds to the percentage of people with the user’s risk profile who have abnormally high triglyceride levels. BitDoctor determines the user’s hypertriglyceridemia risk based on blood flow patterns and demographic information.

## Participants&#x20;

Adults (18+ years of age) recruited from several hospital health clinics.

## Additional Data Collection

Subjects also received a blood test at the same clinic visit where their triglyceride levels were measured.

## Modelling Approach&#x20;

Blood flow signal was extracted and processed from facial video, and then blood flow features were extracted from blood flow signal.&#x20;

Feature selection was carried out on blood flow and demographic features to identify features predictive of hypertriglyceridemia. A machine-learning based classifier was created to predict whether an individual has hypertriglyceridemia based on those features.&#x20;

The model was created/trained using 80% of the subjects. The distribution of sex and hypertriglyceridemia status in this group is summarized in Table 19.

| Subjects in videos                | Composition               |
| --------------------------------- | ------------------------- |
| Sex distribution                  | 48.7 % Male; 51.3% Female |
| Hypertriglyceridemia distribution | 35%                       |

&#x20;                                         *Table 19: Hypertriglyceridemia distribution of training set*

## Model Performance&#x20;

The Hypertriglyceridemia Risk model was then validated for accuracy on an independent portion of the dataset (n=641) that was not used in training - validation set. Then the final accuracy was obtained on an independent portion of the dataset (n=641) that was not used in training - test set. The distribution of sex and hypertriglyceridemia status in these groups is summarized in Table 20.

| Subjects in videos                | Composition in Validation | Composition in Test      |
| --------------------------------- | ------------------------- | ------------------------ |
| Sex distribution                  | 49.8% Male; 50.2% Female  | 47.3% Male; 52.7% Female |
| Hypertriglyceridemia distribution | 35%                       | 35%                      |

&#x20;                              *Table 20: Hypertriglyceridemia distribution of validation and test sets*

The accuracy on the test set calculated as area under the curve was 79.2% as sown in Figure 24.

<figure><img src="/files/mgBNSRZuYZV4a4td3n2W" alt="" width="563"><figcaption></figcaption></figure>

&#x20;                                           *Figure 24: AUC of Hypertriglyceridemia risk prediction*

Predictions are displayed to the user as a percentage likelihood of having hypertriglyceridemia. A percentage of 45% or more suggests a risk of hypertriglyceridemia, while 55% or more suggests high risk of hypertriglyceridemia.


# Fatty Liver Disease

## Description&#x20;

Fatty liver disease (FLD) is characterized by the accumulation of triglyceride lipids within the liver cells, leading to an abnormal increase in liver size. A normal liver typically contains about 5% lipid content, but with the progression of the disease, this can escalate to as much as 50% of the liver's mass.

The development of fatty liver disease involves multiple contributing factors. One significant factor is alcohol consumption. Excessive intake of alcohol disrupts the normal process of alcohol detoxification in the liver, resulting in the accumulation of alcohol metabolites and impairment of liver cell function. This, in turn, promotes the retention of fatty acids within the liver cells, contributing to the development of the disease. It is important to note that alcohol consumption thresholds of 20 g/day for women and 30 g/day for men are typically considered in relation to alcoholic fatty liver disease.&#x20;

Another contributing factor to fatty liver disease is metabolic syndrome, which encompasses multiple conditions including obesity, insulin resistance, type 2 diabetes, dyslipidemia, and hypertension. In individuals with metabolic syndrome, factors such as insulin resistance play a central role. Insulin resistance hampers the normal response of cells to insulin and increases the release of free fatty acids from adipose tissue. These fatty acids are then taken up by the liver, resulting in the accumulation of triglycerides within liver cells.&#x20;

Furthermore, dietary factors can contribute to the development of fatty liver disease. High consumption of fructose, often found in sweetened beverages or high fructose corn syrup, has been associated with a specific form of fatty liver disease known as non-alcoholic fatty liver disease (NAFLD). Excess fructose intake contributes to the storage of excessive fat in the liver cells.

## Participants&#x20;

Adults (18+ years of age) recruited from several hospital health clinics.

## Additional Data Collection Procedure

Subjects were also asked whether they have been diagnosed with FLD.

## Modeling Approach&#x20;

Blood flow signal was extracted and processed from facial video, and then blood flow features were extracted from blood flow signal.&#x20;

Feature selection was carried out on blood flow and demographic features to identify features predictive of FLD status. A machine-learning based classifier was then created to predict an individual’s FLD status based on those features.&#x20;

The model was created/trained using 80% of the subjects. The distribution of sex and FLD status in this group is summarized in Table 21.

| Subjects in videos | Composition               |
| ------------------ | ------------------------- |
| Sex distribution   | 51.7 % Male; 48.3% Female |
| FLD distribution   | 20%                       |

&#x20;                                                    *Table 21: FLD distribution of training set*

## Model Performance&#x20;

The fatty liver disease model was then validated for accuracy on an independent portion of the dataset (n=1082) that was not used in training - validation set. Then the final accuracy was obtained on an independent portion of the dataset (n=1082) that was not used in training - test set. The distribution of sex and FLD status in these groups is summarized in Table 22.

| Subjects in videos | Composition in Validation C | Composition in Test      |
| ------------------ | --------------------------- | ------------------------ |
| Sex distribution   | 49.1% Male; 50.9 % Female   | 54.1% Male; 45.9% Female |
| FLD distribution   | 20% FLD                     | 20% FLD                  |

&#x20;                                             *Table 22: FLD distribution of validation and test sets*

The accuracy on the test set calculated as area under the curve was 89.0% as shown in Figure 26.

<figure><img src="/files/tWLK9gU2xpClrcXHhM1D" alt="" width="563"><figcaption></figcaption></figure>

&#x20;                                                         *Figure 26: AUC of FLD risk prediction*

Predictions are displayed to the user as a percentage likelihood of having FLD. A percentage of 45% or more suggests a risk of FLD, while 55% or more suggests high risk of FLD.


# Morning Fasting Blood Glucose

## Description&#x20;

Blood glucose concentration is controlled to approximately 5 mmol/L in the fasting state before breakfast. The importance of maintaining the constant blood glucose concentration is because it is the only nutrient that can be used by the brain and retinal cells in sufficient quantities to supply them with the required energy levels.&#x20;

Fasting blood glucose risk corresponds to the percentage of people with the user's risk profile who had their blood glucose levels above 5.5 mmol/L when tested after 8-10 hours of fasting, indicating a high risk of prediabetes. Their risk profile is based on facial blood flow and demographics.

## Participants&#x20;

Adults (18+ years of age) recruited from several hospital health clinics.

## Additional Data Collection Procedure

Subjects were asked to provide their blood work report to determine their morning fasting blood glucose (mFBG) levels.

## Modeling Approach&#x20;

Blood flow signal was extracted and processed from facial video, and then blood flow features were extracted from blood flow signal.&#x20;

Feature selection was carried out on blood flow and demographic features to identify features predictive of mFBG levels above 5.5 mmol/L. A machine-learning based classifier was then created to predict an individual’s percentage likelihood of having mFBG above 5.5 mmol/L based on those features.&#x20;

The model was created/trained using 80% of the subjects. The distribution of sex and mFBG level above 5.5 mmol/L in this group is summarized in Table 23.

| Subjects in videos             | Composition           |
| ------------------------------ | --------------------- |
| Sex distribution               | 52 % Male; 48% Female |
| mFBG > 5.5 mmol/L distribution | 30%                   |

&#x20;                    *Table 23: Morning fasting blood glucose > 5.5 mmol/L distribution of training set*

## Model Performance&#x20;

The mFBG model was then validated for accuracy on an independent portion of the dataset (n=917) that was not used in training - validation set. Then the final accuracy was obtained on an independent portion of the dataset (n=917) that was not used in training - test set.&#x20;

The accuracy on the test set calculated as area under the curve was 80.4% as shown in Figure 28.

<figure><img src="/files/PLSqu84EDlK6KFtkN4jx" alt="" width="563"><figcaption></figcaption></figure>

&#x20;                 *Figure 28: AUC of prediction for morning fasting blood glucose value > 5.5 mmol/L*

Predictions are displayed to the user as a percentage likelihood of having prediabetes.  A percentage of 45% or more suggests a risk of prediabetes, while 55% or more suggests high risk of prediabetes.


# Hemoglobin A1C

<figure><img src="/files/ZBXLBHWFMkiUozq4BS9Y" alt="" width="563"><figcaption></figcaption></figure>

**Smartphone-based Identification of Critical Levels of Glycated Hemoglobin A1c**

*Abstract*

A current health concern is the constraints of blood glucose monitoring techniques in the face of the ever-expanding predominance of diabetes. Electronic medical devices can potentially overcome these limitations and prevent the development of diabetes-related complications. This study investigated whether advanced machine learning methods, a smartphone-based AI Imaging Technology that assesses health markers, can be a viable solution for diabetes management. To examine the validity and a novel machine algorithm for diabetes prediction, we compared the diabetes classification from AI Imaging obtained glycated haemoglobin A1c (HbA1c) concentrations against data obtained from FDA-approved blood immunoassays.&#x20;

The data set was obtained from participants recruited from several Health Management Centre of the Affiliated Hospitals. We used a kitchen sink random forest machine algorithm for diabetes prediction. To validate the model, pristine testing was done on 80% of the pristine participants pseudo-randomly selected during 20 trials of training and testing. The confusion matrix found BitDoctor AI imaging Technology to have a classification accuracy of 66%, and the Receiver operating characteristic (ROC) curve of the Random Forest (RF) classifier found AI Imaging to have a ROC Area Under the Curve (AUC) of .69. The present study provides evidence for the potential use of the technology for contactless, non-invasive, and inexpensive assessments of diabetes.

The BitDoctor AI imaging Technology system, the smartphone application, was used to collect participants’ facial blood flow information. BitDoctor AI imaging Technology to detect and track an individual’s facial regions of interest (ROIs), which provide the optical properties of the face to obtain blood flow information.

**Machine Learning Analysis.**

The dataset was divided into two parts: nondiabetes and diabetes. A novel kitchen sink random forest model to utilize the facial blood flow information obtained from AI imaging for diabetes classification. Since HbA1c accounts for 97% of total hemoglobin, a constructed a model to particularly extract HbA1c from AI Imaging obtained hemoglobin concentration (Kahn & Fonseca, 2008). Thus, the video of each participant's face was analyzed for facial blood flow information that reflects cardiovascular activities that correlate with HbA1c. In order to construct the Random Forest (RF) model, MATLAB model to build not balanced decision trees for ensemble diabetes prediction. Random samples of the training dataset were used to build the not-balanced trees. Each decision tree was built to make independent diabetes classification and ‘vote’ for the corresponding class (i.e., non-diabetes or diabetes) based upon HbA1c thresholds.&#x20;

In addition, MATLAB bagging and feature randomness methods to produce uncorrelated decision trees. Also applied the MATLAB feature selection and not-balanced RF classifier training with a threshold for non-diabetes and diabetes equal to clinically approved ones, 5.7% (Sherwani et al., 2016). The results from the laboratory HbA1c test were used as ground truth data in order to evaluate the accuracy of our diabetes classification model.

Validation of the Model. To validate the model, data were derived from pristine testing on 80% of the pristine participants pseudo-randomly selected during 20 trials of training and testing. To compare the data obtained from AI Imaging against those from the blood samples, the data computed the MATLAB confusion matrix and ROC curve of RF classifier to assess the level of agreement between AI Imaging and the blood samples’ diabetes prediction. The confusion matrix was used to assess the number of false positives, false negatives, true positives, and true negatives of BitDoctor AI Imaging. The ROC curve of RF classifier was used to assess the true positive rate and false positive rate of BitDoctor AI Imaging. The threshold for diabetes was incorporated in the MATLAB feature selection and not-balanced random forest classifier training at 5.7%

The ROC curve of the RF classifier is a graphical illustration of a model’s prediction of binary outcomes. It was used to assess the true positive rate and false positive rate of BitDoctor AI Imaging.

!\[A graph with a line going up

Description automatically generated]\(/files/bmicgIDZMjoRFsX5KtU5)

**The confusion matrix.** There are two axes: (1) the true class (y-axis; determined by blood samples), and (2) the predicted class (x-axis;). Non-diabetes is classified as ‘0’, and diabetes is classified as ‘1’. The equal error rate (EER) threshold values for the model’s false positive and false negative rate is set to {159 100 55 86 } 0.351. BitDoctor Technology has a classification accuracy of 66%.

![](/files/Se8u1yCnEh3M4G2YWc2A)


# Image-Based Age

## Description&#x20;

Image-based age estimates an individual’s age (in years) based on information obtained from video (or a single image) of their face.

There are several types of image-based age:

1. **Topographical Age** – an estimate of age based on features of the entire image, including face shape, wrinkles, and skin condition. This measure is currently displayed as “Facial Skin Age” in the BitDoctor app. It can be influenced by factors such as fatigue and the use of skincare and cosmetic products. Video images taken in poor lighting conditions (e.g., backlighting, overhead lighting) may distort this estimate.
2. **Physiological Age** – an estimate of age based on blood flow information acquired with BitDoctor Technology. It can be used as an indicator of the effects of aging on your facial vasculature.&#x20;
3. **Total Facial Age** is an estimate of age that combines information from 2 types of imagebased age (topographical and physiological).

## Participants&#x20;

**Topographical Age Model** – Dataset of images and demographic information of individuals. This is a multiracial dataset consisting mostly of North American participants.&#x20;

**Physiological Age Model** – Video of the face and demographic information of participants.

All participants were adults 18+ years of age.

## Additional Data Collectioon Procedure

A well-lit single image photograph of the face was taken for both models.

## Modeling Approach&#x20;

Deep learning models were trained to predict the subject’s actual age from various image types, depending on the model. The topographical age model was trained using single images of the face, with each image coming from a unique individual. The physiological age model was trained using blood flow features extracted from 30s of facial video and averaged over the duration of the video.

## Model Performance&#x20;

Image-based age models were validated on an independent dataset that was not used in training (data was collected in China akin to that used for physiological and Visage age models). The distribution of sex and age in this group is summarized in Table 27.

| Subjects in videos | Composition               |
| ------------------ | ------------------------- |
| Sex distribution   | 49.4% Male; 51.6 % Female |
| Age                | 53.87 ± 14.40             |

&#x20;                                              *Table 27: Age distribution of pristine validation set*

Model performance for the individual components of the model is summarized in Table 28. Combining information from all three models (Total Facial Age) results in the best performance.

| Model                                            | Pearson Correlation | Bias ± Error SD |
| ------------------------------------------------ | :-----------------: | :-------------: |
| Topographical Age Model                          |         0.77        |   -2.87 ± 6.04  |
| Physiological Age Model                          |         0.77        |   -3.96 ± 9.25  |
| Total Facial Age (Topographical + Physiological) |         0.94        |   -4.11 ± 4.77  |

&#x20;                                                      *Table 28: Facial skin age model performance*


# DePIN Shared Economy

A Mutually Beneficial Purpose

The concept of a DePIN (Decentralised Physical Infrastructure Network) shared economy revolves around the idea of individuals or businesses sharing resources, goods, or services with others for mutual benefit. It leverages technology and platforms to facilitate peer-to-peer transactions, enabling people to access and utilise underused or idle assets more efficiently.

In Web3, blockchain technology plays a central role, enabling peer-to-peer interactions, decentralised applications and ownership and management of digital assets through smart contracts.

As BitDoctor makes its exodus into Web3 to expedite an ecosystem that includes a shared economy protocol, we are powering a system that provides a more open, transparent and user-centric ecosystem.

A key focus of this shared economy is the distribution of profits back to the users who actively engage with BitDoctor's platform activities.

In the traditional sharing economy of Web2, profits are often concentrated among platform owners and a few key stakeholders. However, BitDoctor aims to disrupt this model by empowering users to play a more active role in the platform's success and share in the rewards.

**Here's how BitDoctor's DePIN shared economy works:**

**BitDoctor's Revenue Sharing Model**: Traditionally, consumers are the products in the marketing model, gaining no benefit. BitDoctor aims to disrupt this by redirecting marketing and medical research dollar revenues back to consumers. This model fosters consumer loyalty and engagement, while consumers improve their health and earn rewards. Sponsors gain access to a targeted audience, creating a win-win-win scenario for all involved parties.

**Data Contributors Reward Pool:** Incentivizing Ecosystem Participation A vibrant and active community is the backbone of any successful platform. Recognizing this, BitDoctor has allocated 24% of its token supply to reward contributors within its ecosystem. Over a period of 36 months, 24 million tokens will be distributed to those who contribute to the cultivation of AI Doctor (through scanning on the app), growing the platform’s social presence, volunteering, and providing medical expertise. Contributors are initially rewarded with $LiV, BitDoctor’s in-ecosystem currency. The more $LiV accumulated, the greater the allocation of future airdrops and special privileges within the BitDoctor ecosystem. This reward pool not only incentivizes participation but also fosters a sense of community, encouraging individuals to actively engage in the platform’s growth and success.

Users are encouraged to actively participate in various activities on the platform which consist of AI health scan, educational health quests and many more. This will include content created and shared by partnering brands, community contribution and users utilising services provided by vendor. Additionally, medical specialists contributing their expertise are appropriately rewarded, as are volunteers who help with the platform's growth.

**Token-Based Rewards:** BitDoctor issues native tokens, which users can earn as rewards for their participation. These tokens represent a stake in the platform and its ecosystem.

**Decentralized Governance:** BitDoctor's DePIN shared economy incorporates decentralized governance, allowing users to have a say in the platform's development and decision-making processes through BitDoctor's DAO. Users with a stake in the ecosystem can propose and vote on changes or improvements to the platform.

**Smart Contracts:** Through the use of smart contracts on the blockchain, BitDoctor automates the process of profit distribution. These self-executing contracts ensure that users are rewarded fairly based on their level of engagement and contribution to the platform.

**Token Value:** The native tokens hold inherent value within BitDoctor's ecosystem. Users can trade, hold, stake or utilize them to access additional services, benefits or discounts on the platform.

**Incentivizing Vendors:** Vendors on the platform are also incentivized to actively engage with users and provide high-quality services. Their success is tied to the level of user satisfaction and engagement, leading to a more symbiotic relationship between vendors and users.

***Overall, BitDoctor's DePIN shared economy creates a virtuous cycle, where active user participation drives the platform's growth and success, leading to more significant profits, which are then distributed back to the users.***

***This approach not only empowers users by giving them a stake in the platform's success but also fosters a stronger sense of community and collaboration, ultimately leading to a more sustainable and thriving ecosystem.***

<figure><img src="/files/WxX8St5ap3tHObC7M3sf" alt="" width="563"><figcaption></figcaption></figure>

**Revenue Stream**

**Big Data Sales:** As the app accumulates health data throughout its usage, this information holds immense potential for a variety of applications, while ensuring personal data protection. The collected data can provide valuable insights that can be utilised to enhance the offerings of brands, pharmaceutical companies, and other stakeholders in the healthcare industry.

**Content Sponsors:** Content sponsors on BitDoctor can benefit creators by providing them with $AIDR tokens as payment for creating sponsored content. Creators can then use these tokens to monetise or upgrade their dynamic NFTs (dNFTs), earn more tokens via the AI application platform, and participate in a variety of digital and physical level-up activities offered through BitDoctor's partnering Web2 and Web3 brands. This will create a gamified experience that is highly incentive for the creators to continue producing high-quality content in our ecosystem.

**Sponsors:** Sponsorships will primarily be facilitated through the acquisition of $AIDR tokens. Additionally, fiat payments are also accepted and will be subsequently converted into $AIDR tokens. This process will contribute to the appreciation of the $AIDR token's value.

**Royalty Fees:** Profile dynamic NFTs (dNFTs) will be available in the market, combined with a secondary marketplace for trading these assets. As NFTs are traded within this marketplace, the company will collect a royalty fee, which will serve as one of the revenue streams.

**Transaction Fees:** Considering that $LiV will determine the entitlement amount of $AIDR tokens allocation within our proprietary blockchain can be swapped to other major cryptocurrency such as Bitcoin, transaction fees will be required to facilitate these swaps. This fee structure not only helps maintain the network security and efficiency but also generates additional revenue for the platform. By charging transaction fees, the platform can reinvest these resources into improving the overall user experience, expanding its services, and ensuring the long-term sustainability of the ecosystem.

**In-App Ads and Health Article:** A large number of users on the app represent a significant consumer base. Leveraging our in-house AI technology, we can effectively target users with products tailored to their specific needs, aimed at improving their lives and potentially preventing future health issues. Ad purchases will generate revenue driven by brands featured on the platform, ensuring targeted and efficient marketing campaigns are optimised.

This approach will revolutionise performance marketing by moving away from conventional browsing history algorithms and focus on personalised recommendations based on individual health and wellness needs that have been determined by data gathered from our AI health scan. As a result, users will be presented with relevant and valuable offerings, whilst brands further benefit from increased engagement and higher conversion rates.

**Targeted Activation: D**ata partnerships with insurance companies, medical research firms, pharmaceutical companies, and health/lifestyle brands. On top of it, BitDoctor's data allows patient recruitment for clinical trial research companies. Sponsors and medical partners can benefit from being part of our ecosystem as they will have data on their campaign attendees, push marketing, impressions and brand awareness.&#x20;

***The BitDoctor team will organise campaigns with or without sponsored partners to benefit users.***<br>

Proceeds/profit/sponsorship/targeted ads from partners will be used to be shared among community members.


# Strategic Opportunities

Act as a decentralised data infrastructure that obtain mass health data that covers up to 30 different health metrics and also seven different disease risks. Data collected will be used to create a hyper-personalised AI Doctor agent that will serve every single of our premium user. The decentralised data infrastructure will also be used as a source for agencies, institutions or AI agents in medical industry, to be the champion of decentralised health data library globally.

BitDoctor enables quick identification of specific individuals based on cardiovascular activity, health level, and age, allowing for precise recruitment for clinical trials or campaigns within seconds. With BitDoctor easily recognizing such individuals, it reduces both clinical trial and medical research costs. Ultimately, the end consumer benefits from significantly reduced top-process costs, creating a win-win-win situation for all parties involved.

Additionally, our dataset tracks health data over weeks or months, identifying trends and patterns. Data can be filtered by groups such as sex, age, or high-risk disease categories. This enables targeted user engagement with actions like diet or lifestyle changes, while recording their progress. The structured data is valuable for further research and analysis in health institutions. With a simple ease of accessing such resources at a fraction of the cost compared to the usual practice. This will bring down the cost of medicine research from top down, ultimately benefiting end consumer with a more affordable healthcare ecosystem&#x20;

Available Medical Datasets From BitDoctor:

| <p><strong>Vitals</strong><br>Heart Rate</p><p>Irregular Heartbeat Count<br>Breathing Rate<br>Systolic Blood Pressure<br>Diastolic Blood Pressure </p><p></p><p><strong>Mental</strong><br>BitDoctor Mental Stress Index </p><p></p><p><strong>Physical</strong><br>Body Mass Index (BMI)<br>Facial Skin Age<br>Waist to Height Ratio<br>Body Shape Index<br>Estimated Height<br>Estimated Weight<br>Waist Circumference </p><p></p><p>P<strong>hysiological</strong><br>Heart Rate Variability<br>Cardiac Workload<br>Vascular Capacity </p> | <p><strong>General Risks</strong></p><p>Cardiovascular Disease Risk<br>Heart Attack Risk<br>Stroke Risk </p><p></p><p><strong>Metabolic Risks</strong><br>Hypertension Risk<br>Type 2 Diabetes Risk<br>Hypercholesterolemia Risk Hypertriglyceridemia Risk<br>Fatty Liver Disease Risk</p><p><br><strong>Overall Metabolic Health Risk</strong> </p><p>Blood Biomarkers<br>Hemoglobin A1C Risk<br>Fasting Blood Glucose Risk </p><p></p><p><strong>BitDoctor Scores</strong><br>BitDoctor Mental Score<br>BitDoctor Physical Score<br>BitDoctor Physiological Score<br>BitDoctor Risks Score<br>BitDoctor Vitals Score </p> |
| --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |


# Clinical Trial Agencies

<figure><img src="/files/czfJ5F9HzLFlQSuvnJht" alt=""><figcaption></figcaption></figure>

**Targeted Recruitment**: BitDoctor’s AI-driven health insights and decentralized data infrastructure enable clinical trial agencies to identify specific patient groups with precision. By leveraging data from diverse health metrics and disease risks, agencies can streamline patient recruitment, reducing the time and costs typically associated with finding suitable participants.

**Cost Efficiency**: Partnering with BitDoctor allows clinical trial agencies to minimize recruitment and data acquisition expenses. The platform's ability to analyze user health trends and filter participants by criteria such as age, sex, or risk category ensures trials are conducted more efficiently, saving significant operational costs.

**Enhanced Data Quality**: BitDoctor’s blockchain-based infrastructure ensures data integrity and transparency, addressing one of the critical challenges in clinical research. Agencies gain access to high-quality, validated health data, which can improve trial outcomes and reduce errors in research.

**Innovation in Trials**: Collaborating with BitDoctor allows clinical trial agencies to explore blockchain and AI technologies for advancing research methodologies. The platform’s robust health monitoring tools and decentralized structure present opportunities for more innovative trial designs, including remote and decentralized trials.

**Engaged Participants**: BitDoctor incentivizes users with rewards through its gamified DePIN model. This creates a motivated and engaged user base, which clinical trial agencies can tap into for trials, fostering better participant retention and compliance rates.


# Preventive Healthcare Brands

<figure><img src="/files/1yBZcG4tdUWXu8OxH1Ia" alt=""><figcaption></figcaption></figure>

Preventive healthcare brands can benefit from the BitDoctor platform in several ways:

**Marketing**: The BitDoctor platform provides a unique opportunity for preventive healthcare brands to market their products and services to a wider audience. By sponsoring various activities or creating their own NFTs, they can reach a new customer base and potentially increase their brand awareness.&#x20;

**Revenue Generation**: By partnering with the BitDoctor platform, preventive healthcare brands can generate additional revenue streams. They can offer their products or services as rewards for users who participate in various activities, creating a win-win situation for both the brand and the user.&#x20;

**Innovation**: Working with a blockchain-based platform like BitDoctor can provide opportunities for preventive healthcare brands to explore new technologies and potentially develop new products or services that are tailored to the needs of the platform's users. This could help these brands stay competitive in an increasingly digital world.&#x20;

**User Engagement**: The BitDoctor platform's focus on promoting a healthy lifestyle through gamification and rewards aligns with the goals of preventive healthcare brands. By working with the platform, these brands can engage with users who are already interested in health and wellness, potentially leading to increased customer loyalty and brand advocacy.


# Active Wear & Equipment

<figure><img src="/files/PByA1pe3I6KaXgXR4DRo" alt=""><figcaption></figcaption></figure>

Active wear and equipment companies could benefit from working with the BitDoctor platform in several ways:

**Marketing**: The BitDoctor platform provides a unique opportunity for active wear and equipment companies to market their products to a wider audience. By creating their own NFTs or sponsoring various activities on the platform, they can reach a new customer base and potentially increase their brand awareness.&#x20;

**Revenue Generation**: By partnering with the BitDoctor platform, active wear and equipment companies can generate additional revenue streams. They can offer their products as rewards for users who participate in various activities and earn tokens on the platform.&#x20;

**Innovation**: Working with a blockchain-based platform like BitDoctor can provide opportunities for active wear and equipment companies to explore new technologies and potentially develop new products or services that are tailored to the needs of the platform's users. This could help these companies stay competitive in an increasingly digital world.&#x20;

**User Engagement**: The BitDoctor platform's focus on promoting a healthy lifestyle through gamification and rewards aligns with the goals of active wear and equipment companies. By working with the platform, these companies can engage with users who are already interested in health and fitness, potentially leading to increased customer loyalty and brand advocacy.


# Insurance Company

<figure><img src="/files/YMhonMwGxTXcxQWJGYbR" alt=""><figcaption></figcaption></figure>

Insurance companies could potentially benefit from working with the BitDoctor platform in a few ways:

**Risk Reduction**: The BitDoctor platform is focused on promoting a healthy lifestyle through gamification and rewards. As users participate in various activities and earn tokens, they can use those tokens to upgrade their dynamic NFTs (dNFTs) and be rewarded for maintaining a healthy lifestyle. This could potentially lead to a reduction in risk for insurance companies as healthier individuals are less likely to make claims.&#x20;

**Marketing**: Insurance companies could leverage the BitDoctor platform to market their products and services to a wider audience. By sponsoring various activities or creating their own NFTs, insurance companies could reach a new customer base and potentially increase their brand awareness.&#x20;

**Innovation**: Working with a blockchain-based platform like BitDoctor could allow insurance companies to explore new technologies and potentially develop new products or services that are tailored to the needs of the platform's users. This could help insurance companies stay competitive in an increasingly digital world.


# Pharmaceutical Company

<figure><img src="/files/9jY2a0pRh8S764PzLqIQ" alt=""><figcaption></figcaption></figure>

Benefits from the BitDoctor platform and its users are as follows:

**Research**: The BitDoctor platform could potentially provide a large and diverse pool of users who are interested in health and wellness, making it an ideal population for conducting clinical trials or research studies. Pharmaceutical companies could partner with the platform to recruit study participants and gather valuable data for their research.&#x20;

**Marketing**: The BitDoctor platform provides a unique opportunity for pharmaceutical companies to market their products and services to a wider audience. By sponsoring various activities or creating their own NFTs, they can reach a new customer base and potentially increase their brand awareness.&#x20;

**Revenue Generation**: By partnering with the BitDoctor platform, pharmaceutical companies can generate additional revenue streams. They can offer their products or services as rewards for users who participate in various activities, creating a win-win situation for both the company and the user.&#x20;

**Innovation**: Working with a blockchain-based platform like BitDoctor can provide opportunities for pharmaceutical companies to explore new technologies and potentially develop new products or services that are tailored to the needs of the platform's users. This could help these companies stay competitive in an increasingly digital world.&#x20;

**User Engagement**: The BitDoctor platform's focus on promoting a healthy lifestyle through gamification and rewards aligns with the goals of pharmaceutical companies. By working with the platform, these companies can engage with users who are already interested in health and wellness, potentially leading to increased customer loyalty and brand advocacy.

Pharmaceutical providers will provide education and outreach to users ensuring that medications are used safely and effectively. Furthermore, the platform will offer an opportunity to improve access to medications and make them more affordable for patients. This can involve offering patient assistance programs, working with insurers to ensure coverage, and offering discounts or other incentives to help patients afford necessary treatments.


# Supplement Company

<figure><img src="/files/4cfisVI1xgsL3I6rNgsm" alt=""><figcaption></figcaption></figure>

This is an opportunity to promote a high variety of dietary supplements, which are products designed to supplement or enhance the nutritional content of a person's diet. Supplement companies can benefit from the BitDoctor platform in several ways:

**Marketing**: The BitDoctor platform provides a unique opportunity for supplement companies to market their products and services to a wider audience. By sponsoring various activities or creating their own NFTs, they can reach a new customer base and potentially increase their brand awareness.&#x20;

**Revenue Generation**: By partnering with the BitDoctor platform, supplement companies can generate additional revenue streams. They can offer their products as rewards for users who participate in various activities, creating a win-win situation for both the company and the user.&#x20;

**Innovation**: Working with a blockchain-based platform like BitDoctor can provide opportunities for supplement companies to explore new technologies and potentially develop new products or services that are tailored to the needs of the platform's users. This could help these companies stay competitive in an increasingly digital world.&#x20;

**User Engagement**: The BitDoctor platform's focus on promoting a healthy lifestyle through gamification and rewards aligns with the goals of supplement companies. By working with the platform, these companies can engage with users who are already interested in health and wellness, potentially leading to increased customer loyalty and brand advocacy.

In turn, the supplement company's products can benefit the BitDoctor community by providing users with a range of options to support their health and fitness goals. By offering quality supplements as rewards for participating in activities, the platform can incentivize healthy behavior while providing users with access to products that can help them achieve their goals.


# Crypto Firms

Increase Adoption of Services

<figure><img src="/files/nEk5Slp6ae5RjnNxII5P" alt=""><figcaption></figcaption></figure>

Crypto firms can create a mutually beneficial relationship whereby users can leverage on seamless processes that are quick, easy and effective. Crypto and Web3 companies can benefit from increased adoption of their services through collaboration with the BitDoctor platform in several ways:

**Exposure**: By partnering with BitDoctor , these companies can gain exposure to a wider audience of health and wellness enthusiasts who are interested in using blockchain technology to enhance their lifestyle. This exposure can lead to increased brand awareness and potentially more customers.

**Innovation**: Working with a blockchain-based platform like BitDoctor can provide opportunities for crypto and Web3 companies to explore new collaboration and potentially develop new products or services that are tailored to the needs of the platform's users. This could help these companies stay competitive in an increasingly competitive Web3 space.

**Revenue**: By integrating their services with BitDoctor platform, crypto and Web3 companies can potentially generate additional revenue streams through transaction fees, advertising, and other monetization strategies.

In turn, by partnering with these companies, the BitDoctor platform's community can benefit from access to cutting-edge blockchain technology and innovative services provided by the crypto firm.


# Tokenomics

<figure><img src="/files/zVqJ2Q8N7AO4tdp3XzH3" alt=""><figcaption></figcaption></figure>

## **Token Distribution**

<table><thead><tr><th width="172">Rounds</th><th width="122">Token Amount</th><th width="75">%</th><th width="118">% On TGE</th><th width="105">Cliff</th><th width="147">Linear Release</th></tr></thead><tbody><tr><td>Alpha Raise</td><td>80 million</td><td>8%</td><td>15%</td><td>-</td><td>6 months</td></tr><tr><td>Liquidity Pool</td><td>60 million</td><td>6%</td><td>100% locked and burned in liquidity pool</td><td>-</td><td>-</td></tr><tr><td>Private Investors</td><td>30 million</td><td>3%</td><td>25%</td><td>-</td><td>6 months</td></tr><tr><td>Team</td><td>50 million</td><td>5%</td><td>  -</td><td>12 months</td><td>24 months</td></tr><tr><td>Marketing</td><td>90 million</td><td>9%</td><td>10%</td><td>-</td><td>12 months</td></tr><tr><td>Further Protocol Development</td><td>90 million</td><td>9%</td><td>10%</td><td>-</td><td>18 months</td></tr><tr><td>Contributor Mining Rewards</td><td>600 million</td><td>60%</td><td>  -</td><td>1 month</td><td>100 months</td></tr><tr><td><strong>Total</strong> </td><td><strong>1 Billion</strong></td><td><strong>100%</strong></td><td></td><td></td><td></td></tr></tbody></table>

\*The tokenomics is provisional and subject to adjustments.


# Token Utility

<figure><img src="/files/7YpbOaL5tlBSFA2MxJCD" alt="" width="375"><figcaption></figcaption></figure>

1. **Ensuring Data Protection**&#x20;

BitDoctor prioritize data privacy by using decentralized computing instead of centralized servers, preventing data leaks. Staked tokens support a secure and private decentralized layer.

2. **Access**&#x20;

Token holders benefit from discounted access to BitDoctor’s premium products and services. Stakers also earn a share of BitDoctor revenue, generated from data partnerships with insurance companies, medical research firms, pharmaceutical companies, and health/lifestyle brands.

3. **Stakeholding and Governance**&#x20;

Token holders can actively shape the ecosystem through BitDoctor’s Decentralized Autonomous Organization (DAO), promoting loyalty and transparent community engagement.

4. **Contributor Rewards**&#x20;

Tokens are used to reward contributors to the BitDoctor ecosystem, including medical specialists for their expertise, data contributors for providing health data to enhance the AI Doctor agent, and promoters, volunteers, and social workers who help expand BitDoctor’s reach.

5. **Privileges**&#x20;

Token holders gain privileged access to specialist consultations, healthcare products, and services from panel hospitals.

6. **Ecosystem Currency**&#x20;

Bio-research partners will use BitDoctor token as a currency to access BitDoctor’s vast health data assets, supporting advancements in healthcare research.

Learn more about our token value and functionality: <https://medium.com/@ad.bitdoctorai/exploring-the-token-utility-of-bitdoctor-the-value-and-functionality-2ef76e0bc832>


# Community

At BitDoctor, community engagement is at the core of our mission to democratize healthcare access and drive positive social impact. Through our innovative governance model and commitment to rewarding contributions, we aim to cultivate a dynamic and inclusive community of individuals dedicated to advancing healthcare solutions worldwide. As part of our efforts, we are establishing a Decentralized Autonomous Organization (DAO) that will serve as a platform for recognizing and rewarding not only data contributors, but also current volunteers, nurses, and social workers, healthcare helpers as esteemed contributors to our ecosystem. This initiative, slated for execution post Token Generation Event (TGE), exemplifies BitDoctor's dedication to noble endeavors and empowering those who champion healthcare accessibility on the ground.

In alignment with our vision, BitDoctor extends an open invitation to charity societies and organizations sharing our mission to collaborate and amplify our collective impact. By fostering strategic partnerships and leveraging collective resources, we can expand our reach and extend support to underserved communities in need of healthcare assistance.&#x20;

Furthermore, BitDoctor recognizes the importance of cultivating a health-conscious community that prioritizes well-being and proactive healthcare management. This community not only benefits from the services and insights offered by BitDoctor but also represents a cohesive network that actively promotes health awareness. Web2 pharmaceutical brands, such as Blackmores, Himalaya are inclined to support this society in pursuing its activities aimed at promoting the importance of health awareness.\
\
BitDoctor's AI technology plays a pivotal role in enhancing medical access for individuals in underdeveloped areas, enabling volunteers and healthcare professionals to bring these transformative solutions directly to the communities they serve.&#x20;

We encourage and empower these individuals to be ambassadors for BitDoctor, facilitating referrals and introducing our platform to those in need. In recognition of their invaluable efforts, BitDoctor goes beyond traditional reward mechanisms by allocating a portion of the monthly "contributors" allocation to support these volunteers financially. This holistic approach to community engagement ensures that BitDoctor not only incentivizes data contributors but also supports those who selflessly dedicate their time and expertise to advancing healthcare accessibility worldwide.

Through collaborative initiatives, strategic partnerships, and community empowerment, BitDoctor aims to create a global network of change-makers committed to revolutionizing healthcare delivery and improving lives. Join us in our mission to make healthcare accessible to all, one community at a time.

<br>


# About $LiV Points

$LiV is the Ecosystem Points of BitDoctor, designed to accumulate infinitely throughout your lifetime. It plays a crucial role in determining governance token allocation, rewards, airdrops, and exclusive benefits within the BitDoctor ecosystem. Additionally, $LiV will unlock advanced AI features in the future, granting you greater access to BitDoctor's cutting-edge healthcare technology.

{% hint style="info" %}
In summary, the more $LiV you accumulate, the more you stand to gain, making it an essential element for maximizing your experience and benefits on the BitDoctor platform.
{% endhint %}

## **How to Earn $LiV**

Earning $LiV happens in multiple ways, such as Basic Health Scans (BHS), referrals, royalties, tasks, and many more opportunities to earn $LiV in the future.

The following are explanations of some methods to earn $LiV.

### A. Basic Health Scan

Earn $LiV by using Basic Health Scan (BHS) and tracking your health over time

### B. Referrals

<figure><img src="/files/PiCct4q46FjwmcCDS6QC" alt=""><figcaption></figcaption></figure>

**Direct Referrals:** After downloading and successfully registering on the BitDoctor app, you'll receive 1 referral code (refreshed daily) to invite others. For each successful registration through your referral code, you'll earn 200 $LiV per referral and a 10% royalty on your referred user's rewards indefinitely.

{% hint style="info" %}
**OG Position Benefits:** If you hold an OG position, you'll receive 2 referral codes (refreshed daily) to invite others. For each successful registration through your referral code, you'll earn double the rewards — 400 $LiV per referral and 20% of your referred user's rewards indefinitely.
{% endhint %}

### C. Tasks

Earn $LiV by completing tasks such as connecting your X/Twitter account, posting tweets, participating in AMAs or events, and more.


# Roadmap

<figure><img src="/files/Tyk6sCBQ8ZKtUiQtCeIY" alt=""><figcaption></figcaption></figure>


# Links

Twitter X      - <https://twitter.com/bitdoctorai>

LinkedIn       - <https://www.linkedin.com/company/bitdoctor-ai/>

Telegram     - <https://t.me/BitDocAI> (Group)\
&#x20;                     \- <https://t.me/BitDoctorAiMain> (Channel)

Medium       - <https://medium.com/@ad.bitdoctorai>

Instagram   - <https://www.instagram.com/bitdoctor.ai/>


# Appendix

{% embed url="<https://www.marketsandmarkets.com/Market-Reports/artificial-intelligence-healthcare-market-54679303.html?gad_source=1&gclid=CjwKCAjwte-vBhBFEiwAQSv_xVc82ChPgSHBTp-jpCJnyiBLYntTEHuyB03rJmiX5ti0S2suuzZhMRoCEwEQAvD_BwE>" %}
AI in Healthcare
{% endembed %}

{% embed url="<https://www.who.int/news/item/13-12-2017-world-bank-and-who-half-the-world-lacks-access-to-essential-health-services-100-million-still-pushed-into-extreme-poverty-because-of-health-expenses>" %}
More than a billion people lack of basic healthcare access&#x20;
{% endembed %}

{% embed url="<https://www.who.int/news-room/fact-sheets/detail/ageing-and-health>" %}
100 yo is the new 80yo. People are living longer&#x20;
{% endembed %}

{% embed url="<https://health.gov/healthypeople/objectives-and-data/browse-objectives/preventive-care>" %}
Preventive Health care market size to grow as people are getting helathier&#x20;
{% endembed %}

{% embed url="<https://www.who.int/news-room/fact-sheets/detail/noncommunicable-diseases>" %}
NCD is a big killer&#x20;
{% endembed %}

{% embed url="<https://www.who.int/news/item/13-12-2017-world-bank-and-who-half-the-world-lacks-access-to-essential-health-services-100-million-still-pushed-into-extreme-poverty-because-of-health-expenses>" %}

{% embed url="<https://binariks.com/blog/ai-machine-learning-for-early-disease-detection/>" %}
AI in healthcare for early disease diagnosis &#x20;
{% endembed %}

{% embed url="<https://www.ncbi.nlm.nih.gov/books/NBK499956/>" %}
Medical Error Reduction and Prevention
{% endembed %}

{% embed url="<https://bmcmededuc.biomedcentral.com/articles/10.1186/s12909-023-04698-z>" %}
Importance of AI in Healthcare
{% endembed %}

{% embed url="<https://www.who.int/data/gho/indicator-metadata-registry/imr-details/4965>" %}
Out Of Pocket Medical Expenses&#x20;
{% endembed %}

{% embed url="<https://www.who.int/data/gho/indicator-metadata-registry/imr-details/4989>" %}
Households with out-of-pocket payments greater than 40% of capacity to pay for health care (food, housing and utilities approach - developed by WHO/Europe)
{% endembed %}

{% embed url="<https://www.globenewswire.com/en/news-release/2023/02/13/2606613/0/en/Mobile-Health-mHealth-Market-Size-and-Projections-2023-2030-Growing-at-a-CAGR-of-22-3-with-Country-Wise-Data-Technological-Innovations-Recent-Developments-Competitive-Landscape-Dyn.html>" %}
Mobile Health (mHealth) Market Size and Projections 2023-2030
{% endembed %}

{% embed url="<https://cris.unu.edu/access-medicines-through-global-health-diplomacy>" %}
Around 2 billion people globally have no access to essential medicines
{% endembed %}

{% embed url="<https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10158563/>" %}
Artificial intelligence (AI) enables remote patient monitoring (RPM) which reduces costs by triaging patients to optimize hospitalization and avoid complications.
{% endembed %}

{% embed url="<https://www.sciencedirect.com/science/article/pii/S1877050915001878>" %}
Face Region Of Interest(ROIs)&#x20;
{% endembed %}

{% embed url="<https://daglar-cizmeci.com/blockchain-encryption/>" %}
Blockchain Encryption&#x20;
{% endembed %}

{% embed url="<https://www.ahajournals.org/doi/10.1161/CIRCIMAGING.119.008857>" %}
Smart Phone Blood Pressure Measurement&#x20;
{% endembed %}

{% embed url="<https://www.researchgate.net/publication/321659246_Face_Liveness_Detection_Based_on_Skin_Blood_Flow_Analysis>" %}
Skin Blood Flow Analysis&#x20;
{% endembed %}

{% embed url="<https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6995958/>" %}
Spatial frequency domain imaging (SFDI)
{% endembed %}

{% embed url="<https://www.researchgate.net/publication/333913977_Spatial_frequency_domain_imaging_in_2019_principles_applications_and_perspectives>" %}
Smart Phone base Spatial frequency domain imaging (SFDI)
{% endembed %}

{% embed url="<https://www.imf.org/external/pubs/ft/fandd/1999/12/dillinge.htm>" %}
From Centralized to Decentralized Governance(DAO)
{% endembed %}


# Team Info

<figure><img src="/files/zi2sjBGuodtwjyDNLOYG" alt=""><figcaption></figcaption></figure>

**Asher Looi : Co-Founder & Project Lead** [*LinkedIN*](http://linkedin.com/in/asherlooi)\
*1st Crypto E-Pharmacy, Public Listed Healthtech, Multidisciplinary*

**Wilson Tay : Co-Founder & CTO** [*LinkedIN*](https://www.linkedin.com/in/wilsontay/)\
*Founder of Multiple Companies, Full-Stack Expertise*

**Joanne Odom: Medical & Science Liaison** [*LinkedIN*](https://www.linkedin.com/in/joanne-odom-pharmd-38123713/)\
*C-suite, Pharmacoeconomic*

**James Ang: Business Strategist** [*LinkedIN*](< https://www.linkedin.com/in/ban-joo-80386154/>)\
*Commercialisation Specialist*

**Annie Tay: Growth Strategist** [*LinkedIN*](<https://www.linkedin.com/in/anniejwhtay/ >)\
*C-suite, Insurance, Bank*

**Mari Juk: Head of Europe Partnership** [*LinkedIN*](<https://my.linkedin.com/in/alantjb >)\
*Expansion Expert*

**Nelson Nworie: Content Lead** [*LinkedIN*](<https://www.linkedin.com/in/nelson-ike-nworie/ >)\
*Season Web3 Writer*<br>


# Advisors

![](/files/te8kRcxPAl1iAud5w0fM)

**Rebecca Chow, PhD**\
*Head of Investment Research, ViaBTC Capital*

Graduating from Medical University of South Carolina to a crypto degen. Over 8 years of crypto experience, she has made contributions as an author, speaker, investor, and advisor. Former member of Venom Foundation, Cryptonite Capital

<div align="left"><figure><img src="/files/JK2SDcMWAoXLfVlqfQdu" alt=""><figcaption></figcaption></figure></div>

**Jeremy Fong**\
*Co-founder of Bitazza*

Jeremy has over 17 years of experience in finance, including roles at Fortune 500 companies like IBM and Hewlett Packard across Australia, Singapore, Malaysia, and Thailand. He now works as a trader and investor in foreign exchange currencies and digital assets for private clients. Jeremy is passionate about cryptocurrency, seeing it as an innovative, exciting way to achieve financial freedom and be the best version of oneself.