Machine learning detection of obstructive hypertrophic cardiomyopathy using a wearable biosensor

Abstract

Hypertrophic cardiomyopathy (HCM) is a heritable disease of heart muscle that increases the risk for heart failure, stroke, and sudden death, even in asymptomatic patients. With only 10-20% of affected people currently diagnosed, there is an unmet need for an effective screening tool outside of the clinical setting. Photoplethysmography uses a noninvasive optical sensor incorporated in commercial smart watches to detect blood volume changes at the skin surface. In this study, we obtained photoplethysmography recordings and echocardiograms from 19 HCM patients with left ventricular outflow tract obstruction (oHCM) and a control cohort of 64 healthy volunteers. Automated analysis showed a significant difference in oHCM patients for 38/42 morphometric pulse wave features, including measures of systolic ejection time, rate of rise during systole, and respiratory variation. We developed a machine learning classifier that achieved a C-statistic for oHCM detection of 0.99 (95% CI: 0.99-1.0). With further development, this approach could provide a noninvasive and widely available screening tool for obstructive HCM.

Keywords: Diagnostic markers; Translational research.

Fig. 1

Differences in photoplethysmography tracings between oHCM patients and healthy volunteers. a Single beats extracted from the PPG recordings and b 10 s continuous recordings illustrating differences in waveform morphology between two representative healthy subjects and two oHCM patients. Markers indicate separation between beats detected by an automated algorithm. Example morphometric features are shown as follows: (1) systolic ejection time, (2) slope of systolic rise, and (3) slope of diastolic decline. c Plot of the magnitude and statistical significance of the difference in feature values between healthy controls and oHCM patients for 42 analyzed pulse features. The 38 features with Bonferroni-corrected p < 0.05 are colored black and the remaining four are shown in red. d Receiver-operator curve with marker indicating the cutoff point used to derive the embedded confusion matrix