Smartwatch-Based Blood Pressure Measurement Demonstrates Insufficient Accuracy

Abstract

BackgroundNovel smartwatch-based cuffless blood pressure (BP) measuring devices are coming to market and receive FDA and CE labels. These devices are often insufficiently validated for clinical use. This study aims to investigate a recently CE-cleared smartwatch using cuffless BP measurement in a population with normotensive and hypertensive individuals scheduled for 24-h BP measurement.MethodsPatients that were scheduled for 24-h ambulatory blood pressure monitoring (ABPM) were recruited and received an additional Samsung Galaxy Watch Active 2 smartwatch for simultaneous BP measurement on their opposite arm. After calibration, patients were asked to measure as much as possible in a 24-h period. Manual activation of the smartwatch is necessary to measure the BP. Accuracy was calculated using sensitivity, specificity, positive and negative predictive values and ROC curves. Bland-Altman method and Taffé methods were used for bias and precision assessment. BP variability was calculated using average real variability, standard deviation and coefficient of variation.ResultsForty patients were included. Bland-Altman and Taffé methods demonstrated a proportional bias, in which low systolic BPs are overestimated, and high BPs are underestimated. Diastolic BPs were all overestimated, with increasing bias toward lower BPs. Sensitivity and specificity for detecting systolic and/or diastolic hypertension were 83 and 41%, respectively. ROC curves demonstrate an area under the curve (AUC) of 0.78 for systolic hypertension and of 0.93 for diastolic hypertension. BP variability was systematically higher in the ABPM measurements compared to the smartwatch measurements.ConclusionThis study demonstrates that the BP measurements by the Samsung Galaxy Watch Active 2 show a systematic bias toward a calibration point, overestimating low BPs and underestimating high BPs, when investigated in both normotensive and hypertensive patients. Standards for traditional non-invasive sphygmomanometers are not met, but these standards are not fully applicable to cuffless devices, emphasizing the urgent need for new standards for cuffless devices. The smartwatch-based BP measurement is not yet ready for clinical usage. Future studies are needed to further validate wearable devices, and also to demonstrate new possibilities of non-invasive, high-frequency BP monitoring.

The Microsoft Research Aurora Project: Important Findings on Cuffless Blood Pressure Measurement

“…21 In a third study by Falter et al in 40 adults, the cuff-calibrated Samsung device showed a systematic bias toward the cuff BP at calibration and could not accurately measure SBP and DBP when compared with 24-hour ambulatory cuff BP monitoring (SBP/DBP errors of 15.6/12.6 mm Hg, which are computed here from the reported values to be comparable to errors in Figure 2). 22 On the other hand, the Aurora Project findings are in stark contrast to 2 other recent studies with manufacturer involvement. One of these studies reported that the cuff-calibrated Biobeat device could almost perfectly predict average daytime and average nighttime ambulatory cuff SBP and DBP in 28 adults (correlation coefficients of 0.97-0.99).…”

“…21 In a third study by Falter et al in 40 adults, the cuff-calibrated Samsung device showed a systematic bias toward the cuff BP at calibration and could not accurately measure SBP and DBP when compared with 24-hour ambulatory cuff BP monitoring (SBP/DBP errors of 15.6/12.6 mm Hg, which are computed here from the reported values to be comparable to errors in Figure 2). 22…”

The use of commercial wrist-worn technology to track physiological outcomes in behavioral interventions

“…The LiveOne Band, which uses pressure sensors and machine learning to measure BP, also met validation criteria standards and was highly correlated with criterion measurements [46]. In contrast, the Samsung Galaxy Watch Active 2, which uses PPG to estimate BP, was found to be inaccurate [47]. Although findings from limited existing studies suggest the potential utility of wrist-worn devices for tracking BP [44][45][46][47], more evidence is needed to support their accuracy and use in intervention research.…”

“…In contrast, the Samsung Galaxy Watch Active 2, which uses PPG to estimate BP, was found to be inaccurate [47]. Although findings from limited existing studies suggest the potential utility of wrist-worn devices for tracking BP [44][45][46][47], more evidence is needed to support their accuracy and use in intervention research.…”

European Society of Hypertension recommendations for the validation of cuffless blood pressure measuring devices: European Society of Hypertension Working Group on Blood Pressure Monitoring and Cardiovascular Variability

“…A pragmatic and clinically meaningful approach which has been used in several studies for testing the accuracy of automated wearable intermittent cuffless devices is the evaluation versus simultaneous 24-h ABPM using validated oscillometric upper arm cuff devices [22][23][24][25][26][27]. This approach is important especially for individual-user calibrated devices to assess whether they can track awake/asleep BP changes (which is a highly relevant test for clinical practice); are robust to different device and body positions; and are effective during different daily activities.…”