Contactless Blood Oxygen Saturation Estimation from Facial Videos Using Deep Learning.

Blood oxygen saturation (SpO2) is an essential physiological parameter for evaluating a person's health. While conventional SpO2 measurement devices like pulse oximeters require skin contact, advanced computer vision technology can enable remote SpO2 monitoring through a regular camera without skin contact. In this paper, we propose novel deep learning models to measure SpO2 remotely from facial videos and evaluate them using a public benchmark database, VIPL-HR. We utilize a spatial-temporal representation to encode SpO2 information recorded by conventional RGB cameras and directly pass it into selected convolutional neural networks to predict SpO2. The best deep learning model achieves 1.274% in mean absolute error and 1.71% in root mean squared error, which exceed the international standard of 4% for an approved pulse oximeter. Our results significantly outperform the conventional analytical Ratio of Ratios model for contactless SpO2 measurement. Results of sensitivity analyses of the influence of spatial-temporal representation color spaces, subject scenarios, acquisition devices, and SpO2 ranges on the model performance are reported with explainability analyses to provide more insights for this emerging research field.

Robust Heart Rate Variability Measurement from Facial Videos.

Remote Photoplethysmography (rPPG) is a contactless method that enables the detection of various physiological signals from facial videos. rPPG utilizes a digital camera to detect subtle changes in skin color to measure vital signs such as heart rate variability (HRV), an important biomarker related to the autonomous nervous system. This paper presents a novel contactless HRV extraction algorithm, WaveHRV, based on the Wavelet Scattering Transform technique, followed by adaptive bandpass filtering and inter-beat-interval (IBI) analysis. Furthermore, a novel method is introduced to preprocess noisy contact-based PPG signals. WaveHRV is bench-marked against existing algorithms and public datasets. Our results show that WaveHRV is promising and achieves the lowest mean absolute error (MAE) of 10.5 ms and 6.15 ms for RMSSD and SDNN on the UBFCrPPG dataset.

Predicting Subjective Discomfort Associated With Lens Distortion in VR Headsets During Vestibulo-Ocular Response to VR Scenes.

With advances in Virtual Reality (VR) technology, user expectation for a near-perfect experience is also increasing. The push for a wider field-of-view can increase the challenges of correcting lens distortion. Past studies on imperfect VR experiences have focused on motion sickness provoked by vection-inducing VR stimuli and discomfort due to mismatches in accommodation and binocular convergence. Disorientation and discomfort due to unintended optical flow induced by lens distortion, referred to as dynamic distortion (DD), has, to date, received little attention. This study examines and models the effects of DD during head rotations with various fixed gazes stabilized by vestibulo-ocular reflex (VOR). Increases in DD levels comparable to lens parameters from poorly designed commercial VR lenses significantly increase discomfort scores of viewers in relation to disorientation, dizziness, and eye strain. Cross-validated results indicate that the model is able to predict significant differences in subjective scores resulting from different commercial VR lenses and these predictions correlated with empirical data. The present work provides new insights to understand symptoms of discomfort in VR during user interactions with static world-locked / space-stabilized scenes and contributes to the design of discomfort-free VR headset lenses.

Blood Pressure Measurement: From Cuff-Based to Contactless Monitoring.

Blood pressure (BP) determines whether a person has hypertension and offers implications as to whether he or she could be affected by cardiovascular disease. Cuff-based sphygmomanometers have traditionally provided both accuracy and reliability, but they require bulky equipment and relevant skills to obtain precise measurements. BP measurement from photoplethysmography (PPG) signals has become a promising alternative for convenient and unobtrusive BP monitoring. Moreover, the recent developments in remote photoplethysmography (rPPG) algorithms have enabled new innovations for contactless BP measurement. This paper illustrates the evolution of BP measurement techniques from the biophysical theory, through the development of contact-based BP measurement from PPG signals, and to the modern innovations of contactless BP measurement from rPPG signals. We consolidate knowledge from a diverse background of academic research to highlight the importance of multi-feature analysis for improving measurement accuracy. We conclude with the ongoing challenges, opportunities, and possible future directions in this emerging field of research.

Deep Learning Methods for Remote Heart Rate Measurement: A Review and Future Research Agenda.

Heart rate (HR) is one of the essential vital signs used to indicate the physiological health of the human body. While traditional HR monitors usually require contact with skin, remote photoplethysmography (rPPG) enables contactless HR monitoring by capturing subtle light changes of skin through a video camera. Given the vast potential of this technology in the future of digital healthcare, remote monitoring of physiological signals has gained significant traction in the research community. In recent years, the success of deep learning (DL) methods for image and video analysis has inspired researchers to apply such techniques to various parts of the remote physiological signal extraction pipeline. In this paper, we discuss several recent advances of DL-based methods specifically for remote HR measurement, categorizing them based on model architecture and application. We further detail relevant real-world applications of remote physiological monitoring and summarize various common resources used to accelerate related research progress. Lastly, we analyze the implications of research findings and discuss research gaps to guide future explorations.

Clinical Correlates, Ethnic Differences, and Prognostic Implications of Perivascular Spaces in Transient Ischemic Attack and Ischemic Stroke.

BACKGROUND AND PURPOSE: Perivascular spaces (PVSs) are considered markers of small vessel disease. However, their long-term prognostic implications in transient ischemic attack/ischemic stroke patients are unknown. Ethnic differences in PVS prevalence are also unknown. METHODS: Two independent prospective studies were conducted, 1 comprising predominantly whites with transient ischemic attack/ischemic stroke (OXVASC [Oxford Vascular] study) and 1 comprising predominantly Chinese with ischemic stroke (University of Hong Kong). Clinical and imaging correlates, prognostic implications for stroke and death, and ethnic differences in basal ganglia (BG) and centrum semiovale (CS) PVSs were studied with adjustment for age, sex, vascular risk factors, and scanner strength. RESULTS: Whites with transient ischemic attack/ischemic stroke (n=1028) had a higher prevalence of both BG and CS-PVSs compared with Chinese (n=974; >20 BG-PVSs: 22.4% versus 7.1%; >20 CS-PVSs: 45.8% versus 10.4%; P<0.0001). More than 20 BG or CS-PVSs were both associated with increasing age and white matter hyperintensity, although associations with BG-PVSs were stronger (all P<0.0001). During 6924 patient-years of follow-up, BG-PVSs were also independently associated with an increased risk of recurrent ischemic stroke (adjusted hazard ratio compared with <11 PVSs, 11-20 PVSs: HR, 1.15; 95% confidence interval, 0.78-1.68; >20 PVSs: HR, 1.82; 1.18-2.80; P=0.011) but not intracerebral hemorrhage (P=0.10) or all-cause mortality (P=0.16). CS-PVSs were not associated with recurrent stroke (P=0.57) or mortality (P=0.072). Prognostic associations were similar in both cohorts. CONCLUSIONS: Over and above ethnic differences in frequency of PVSs in transient ischemic attack/ischemic stroke patients, BG and CS-PVSs had similar risk factors, but although >20 BG-PVSs were associated with an increased risk of recurrent ischemic stroke, CS-PVSs were not.

Association between high cumulative dose of benzodiazepine in Chinese patients and risk of dementia: a preliminary retrospective case-control study.

BACKGROUND: Evidence describing the association between high-dose benzodiazepine use and dementia has been conflicting. Most previous studies involved Caucasian populations, with only limited data on Chinese subjects. Possible differences exist between Chinese and Caucasian populations with regard to metabolism and prescription practice. This study aimed to assess the association between high-dose benzodiazepine use and dementia in a Chinese population. METHOD: A retrospective case-control study was carried out in all public hospitals under the Hong Kong Hospital Authority Hong Kong West Cluster between 2000 and 2015. The study recruited 273 Chinese adults (91 cases, 182 controls) aged 75 and over, with at least 6 years of follow-up data. Each dementia case was matched with two controls according to sex, age group, and duration of follow-up. The number of patients with benzodiazepine ever-use and the exposure density based on the prescribed daily doses were assessed. Prescribed daily doses were categorized as either <1096 or ≥1096. Odds ratios and 95% confidence intervals were computed by multivariate analysis. RESULTS: The difference in exposure density between the dementia and control groups was statistically significant between prescribed daily doses <1096 and ≥1096 (P = 0.02). There were two multivariate analyses models; one factored in depression (model 1), and the other (model 2) did not. Model 2 showed a statistically significant association (odds ratio = 1.71, 95% confidence intervals = 1.02-2.89, P = 0.04) between benzodiazepine exposure density and dementia. CONCLUSION: High-dose benzodiazepine use may be associated with dementia in the Chinese population. Prospective studies are required.

Systematic Review of Cholinesterase Inhibitors on Cognition and Behavioral Symptoms in Patients of Chinese Descent with Alzheimer's Disease, Vascular Dementia, or Mixed Dementia.

Cholinesterase inhibitors (ChEIs) are the primary pharmacologic treatment for dementia. Their efficacy in patients of Chinese descent is not well described. We reviewed how ChEIs could affect cognition and behavioral and psychological symptoms (BPSD) in Chinese patients with Alzheimer's disease (AD), vascular dementia (VaD), or mixed (AD with vascular component) dementia. MEDLINE, PsycINFO, EMBASE and CINAHL were systematically searched for controlled trials of ChEIs, including donepezil, galantamine, and rivastigmine, for Chinese patients with AD, VaD, or mixed dementia. Outcomes for cognition and BPSD were extracted for discussion. Fifty-four studies were identified. While one larger study found that dementia patients of Chinese descent treated with ChEIs had significantly higher mean Mini-Mental State Examination (MMSE) score, other studies showed no significant difference. Evidence on BPSD after use of ChEIs was also conflicting. ChEIs may be effective in improving cognition among patients of Chinese descent with dementia. Further studies are needed to examine the possible effects of ChEIs on BPSD in Chinese patients with dementia in view of the small number of studies and limitations in their methodologies.