Background: Cuff-based blood pressure measurement lacks comfort and convenience. Here, we examined whether blood pressure can be determined in a contactless manner using a novel smartphone-based technology called transdermal optical imaging. This technology processes imperceptible facial blood flow changes from videos captured with a smartphone camera and uses advanced machine learning to determine blood pressure from the captured signal. Methods: We enrolled 1328 normotensive adults in our study. We used an advanced machine learning algorithm to create computational models that predict reference systolic, diastolic, and pulse pressure from facial blood flow data. We used 70% of our data set to train these models and 15% of our data set to test them. The remaining 15% of the sample was used to validate model performance. Results: We found that our models predicted blood pressure with a measurement bias±SD of 0.39±7.30 mm Hg for systolic pressure, −0.20±6.00 mm Hg for diastolic pressure, and 0.52±6.42 mm Hg for pulse pressure, respectively. Conclusions: Our results in normotensive adults fall within 5±8 mm Hg of reference measurements. Future work will determine whether these models meet the clinically accepted accuracy threshold of 5±8 mm Hg when tested on a full range of blood pressures according to international accuracy standards.

Objective A new smartphone app called Anura can measure blood pressure (BP) any time and any place without cuffs or special equipment from video of the face. This study assessed its accuracy in close conformity with the American National Standards Institute/Association for the Advancement of Medical Instrumentation/International Organization for Standardization (ANSI/AAMI/ISO) 81060-2:2013 standard for BP measurement devices. Methods We validated Anura in reference to auscultation using a mercury sphygmomanometer and then assessed accuracy against the two accuracy criteria described in the guideline (n = 85 subjects; three measurement pairs per subject). Results The mean difference between the Anura measurement and its paired auscultatory reference measurement across all 255 measurement pairs was –0.4 ± 6.7 mmHg for systolic blood pressure (SBP) and 1.2 ± 7.0 mmHg for diastolic blood pressure (DBP). Both are within the acceptable limit of 5 ± 8 mmHg and thus satisfy accuracy criterion 1. When mean differences are averaged for each subject, the mean across all 85 subjects is –0.4 ± 5.8 mmHg for SBP and 1.2 ± 6.7 mmHg for DBP. Both are within acceptable limits (based on the mean difference) and thus satisfy accuracy criterion 2. Conclusions Anura meets ANSI/AAMI/ISO 81060-2:2013 standard with respect to BP measurement accuracy. As the ANSI/AAMI/ISO 81060-2:2013 standard has not been developed for cuffless devices, further research assessing additional accuracy issues specific to such devices is needed.

Abstract BACKGROUND The 2017 American College of Cardiology (ACC)/American Heart Association (AHA) (US) Guideline for the Prevention, Detection, Evaluation and Management of High Blood Pressure in Adults expanded the definition of hypertension and now considers atherosclerotic cardiovascular disease (ASCVD) risk in determining treatment for people with hypertension. US guidelines are influential around the world and it is therefore justified to study their impact in other settings. Our study determined the impact of adopting the 2017 ACC/AHA guideline in China. METHODS We analyzed the population impact of the 2017 ACC/AHA guideline using the 2011–2012 year of the China Health and Retirement Longitudinal Study (CHARLS), a nationally representative sample of Chinese adults 45–74 years of age (n = 11,822). Our analysis was unique because for the first time it used a population-appropriate equation to calculate ASCVD risk instead of the US Pooled Cohort Equation (the latter misrepresents risk in non-US populations). RESULTS Adopting the 2017 ACC/AHA guideline in China would increase the prevalence of hypertension from 44.1% to 56.4% (12.3 percentage points) and increase the number of adults recommended for antihypertensive medication from 41.6% to 49.1% (7.5 percentage points) in the 45–74-year age range. According to Chinese (but not US) risk calculations, the 2017 ACC/AHA guideline more selectively assigns antihypertensive medication to patients at higher risk for ASCVD. CONCLUSIONS The 2017 ACC/AHA guideline brings potential for risk reduction in China and selectively recommends medication for those who would benefit most. Realizing such benefits would ultimately depend on the acceptance, adherence, and feasibility of adopting this guideline.