Opportunistically Detecting Signs of Hypertension on a Consumer Smartwatch

Hypertension is a silent killer, with over half of affected adults unaware of their condition1,2. This lack of awareness is a major concern, as early intervention is critical for preventing major adverse cardiovascular events3,4. While cuffless wearable blood pressure (BP) monitors offer comfort and convenience, their reliance on periodic calibration and inconsistent accuracy have limited their clinical adoption5,6. Here we show that applying artificial intelligence (AI) pre-trained on almost 500,000 hours of data to multimodal waveforms (photoplethysmography and accelerometry) recorded using a widely available consumer smartwatch (AI-PPG-ACC-HTN), without any cuff calibration, can detect hypertension with accuracy levels comparable to traditional cuffed BP devices in the existing clinical framework, including both initial and confirmatory screening. We validated AI-PPG-ACC-HTN in a prospective, multicenter study of 196 diverse participants free from known cardiovascular disease and antihypertensive medication against gold-standard 24-hour ambulatory BP monitoring. Over seven days of real-world monitoring, AI-PPG-ACC-HTN detected hypertension with a sensitivity of 65.8% (95% CI, 54.0%-76.3%), specificity of 90.0% (83.2-94.7), and positive predictive value (PPV) of 80.6% (68.6-89.6). In comparison, initial office BP screening achieved a sensitivity of 55.3% (43.4-66.7), specificity of 90.0% (83.2-94.7) and PPV of 77.8% (64.4-88.0). For confirmatory testing of participants with elevated BP identified by initial office BP screening (N=48), AI-PPG-ACC-HTN detected hypertension with a sensitivity of 78.4% (61.8-90.2), specificity of 90.9% (58.7-99.8) and PPV of 96.7% (82.8-99.9). Comparatively, repeat office BP achieved a sensitivity of 67.6% (50.2-82.0), specificity of 63.6% (30.8-89.1) and PPV of 86.2% (68.3-96.1); multiday home BP monitoring achieved a sensitivity of 89.2% (74.6-97.0), specificity of 81.8% (48.2-97.7) and PPV of 94.3% (80.8-99.3). These results highlight an opportunity for consumer smartwatches to facilitate population-level opportunistic hypertension screening, offering an accessible tool to address this major public health challenge.