Mental Stress Index
Last updated
Last updated
BitDoctor AI Imaging Reveal Basal Stress via Heart Rate Variability Analysis: A Novel Methodology Comparable to Electrocardiography
Humans encounter various stressful situations everyday at work, home, and school. Such stress when experienced at high degrees and/or for a long duration of time could lead to cardiovascular diseases, cognitive dysfunctions, and psychological disorders (Kofman et al., 2006; Pan and Li, 2007; Crowley et al., 2011). Currently, the assessment of stress relies on the analysis of psychometric (e.g., self-report questionnaires) and/or biometric (e.g., electrocardiography) data. While psychometric data can provide a glimpse into an individual’s psychological state and stress level, it is heavily dependent upon a subjective reflection of events and conditions. On the other hand, biometric data can provide an objective evaluation of physiological activity that has been demonstrated to correlate well with psychological stress (Sharpley and Gordon, 1999; Tavel, 2001). However, biometric data are often obtained using instruments which require the attachment of electrodes or sensors onto the body by trained individuals. This use of physiological measurement instruments can be inconvenient. Thus, to date, we still face diculties in monitoring stress levels both reliably and conveniently. The present research aimed to address these diculties directly.
Based on the evidences of cardiovascular changes in response to stress, we have specifically developed a new imaging technology to assess stress conveniently, contactlessly, and remotely. This technology uses video record participants’ faces from a distance, analyzing facial blood flow information to obtain participants’ heart rate and HRV. BitDoctor AI technology is built upon a century of research that has revealed cardiovascular activities to be obtainable via analyses of blood flow changes. It is well-established that light can travel beneath the skin and re-emit due to the translucent property of the skin (Brunsting and Sheard, 1929; Edwards and Duntley, 1939; Dawson et al., 1980). Furthermore, this re-emitted light can be captured by an optical sensor, from which blood flow information can be obtained (Anderson, 1991; Stamatas et al., 2004; Demirli et al., 2007). Information regarding blood flow changes reveal cardiovascular changes given that movement of blood from the heart to the rest of the body is part of the cardiovascular system. These discoveries have lead to the development of various methodologies (e.g., laser Doppler flowmetry, photoplethysmography) that measure cardiovascular activities optically. However, similar to the utilization of electrocardiography, these methodologies require the attachment of sensors to the body, which can be inconvenient. BitDoctor AI Imaging overcomes the limitations of current methodologies by utilizing a smart phone video camera to conveniently, contactlessly, and remotely capture video images of the face for extraction of cardiovascular changes. This is possible because re-emitted light from underneath the skin is aected by chromophores, primarily hemoglobin and melanin (Nishidate et al., 2004), which have dierent color signatures. Given the dierence in the color signatures, we can use machine learning to separate images of hemoglobin-rich regions from melaninrich regions, ultimately obtaining video images of hemoglobin changes under the. The face is ideal for analysis of blood flow changes because it is rich in vasculature and exposed, allowing us to obtain blood flow information conveniently, contactlessly, and remotely. In the present study, we examined the validity in measuring heart rate and HRV, which reflects individual stress. We measured participants’ cardiovascular activities while they were in a state of rest to assess their basal stress levels. We used the methodology to obtain facial blood flow data reflecting heart rate, HRV, and basal stress levels. At the same time, in order to validate our methodology, we compared the measurements obtained from AI Imaging with those collected concurrently from an ECG system. We hypothesized that if there is a high positive correlation between data obtained from BitDoctor AI Imaging and ECG, cardiovascular changes as assessed should correspond by ECG, which were previously proven to correlate with individual stress. Thus, we would provide evidence to suggest BitDoctor AI Imaging to be a valid methodology for assessing stress conveniently, contactlessly, and remotely.
RESULTS
To assess the accuracy of the technology, we compared measurements of heart rate and stress obtained with AI Imaging against those obtained with the BIOPAC ECG. Figure 5A shows that the average (SD) of heart rate as obtained from BitDoctor Technology was 70.59 (8.36) beats per minute (BPM), while that obtained from BIOPAC was 71.55 (7.97) BPM. Figure 5B shows that the average (SD) of SD1/SD2 (i.e., stress) as obtained from BitDoctor was 0.11 (0.03), while that obtained from BIOPAC was 0.11 (0.03). We calculated for the agreement between heart rate measurements obtained from AI Imaging and BIOPAC. The agreement limits are from 2.55 to 0.63, with a bias of 0.96 (see Figure 6A). Calculated for the agreement between stress measurements obtained from AI Imaging and BIOPAC. Data shown found that the agreement limits are from 0.03 to 0.03, with a bias of 0. Calculated for the correlation between heart rate measurements obtained from AI Imaging and BIOPAC. Proven that there was a positive correlation between the two instruments, r = 1.00. Demonstrates the points of heart rate (BPM) as obtained from AI Imaging and BIOPAC with a line of best fit drawn through the points to illustrate the positive correlation. This extremely strong, positive correlation between measurements of heart rate obtained from AI Imaging and those obtained from the BIOPAC ECG indicated that AI Imaging technology is able to measure heart rate as accurately as the BIOPAC ECG. We calculated for the correlation between stress measurements obtained from AI Imaging and BIOPAC. We found that there was a positive correlation between the measurements of stress obtained from AI Imaging and BIOPAC, r = 0.89. Figure 7B demonstrates the points of stress (SD1/SD2) as obtained from AI Imaging and BIOPAC with a line of best fit drawn through the points to illustrate the positive correlation. This strong, positive correlation between measurements of stress obtained from AI Imaging and BIOPAC indicated that AI Imaging technology is able to determine stress as accurately as the BIOPAC.
