Scalable Approach to Consumer Wearable Postmarket Surveillance: Development and Validation Study

• Published in: JMIR medical informatics 2024-04, Vol.12, p.e51171-e51171
• Main Authors: Yoo, Richard M, Viggiano, Ben T, Pundi, Krishna N, Fries, Jason A, Zahedivash, Aydin, Podchiyska, Tanya, Din, Natasha, Shah, Nigam H
• Format: Article
• Language: English
• Subjects: Adoption and Change Management of eHealth Systems; Cardiac arrhythmia; Datasets; Decision Support for Health Professionals; Deep learning; eHealth Infrastructures; Electrocardiography; Electronic Health Records; Heart rate; Heuristic; Labeling; mHealth for Data Collection and Research; Natural language processing; New Technologies; Original Paper; Patients; Performance evaluation; Quality Improvement; Surveillance; Wearable computers; Wearable Devices and Sensors
• ISSN: 2291-9694; 2291-9694
• DOI: 10.2196/51171

With the capability to render prediagnoses, consumer wearables have the potential to affect subsequent diagnoses and the level of care in the health care delivery setting. Despite this, postmarket surveillance of consumer wearables has been hindered by the lack of codified terms in electronic health records (EHRs) to capture wearable use. We sought to develop a weak supervision-based approach to demonstrate the feasibility and efficacy of EHR-based postmarket surveillance on consumer wearables that render atrial fibrillation (AF) prediagnoses. We applied data programming, where labeling heuristics are expressed as code-based labeling functions, to detect incidents of AF prediagnoses. A labeler model was then derived from the predictions of the labeling functions using the Snorkel framework. The labeler model was applied to clinical notes to probabilistically label them, and the labeled notes were then used as a training set to fine-tune a classifier called Clinical-Longformer. The resulting classifier identified patients with an AF prediagnosis. A retrospective cohort study was conducted, where the baseline characteristics and subsequent care patterns of patients identified by the classifier were compared against those who did not receive a prediagnosis. The labeler model derived from the labeling functions showed high accuracy (0.92; F1-score=0.77) on the training set. The classifier trained on the probabilistically labeled notes accurately identified patients with an AF prediagnosis (0.95; F1-score=0.83). The cohort study conducted using the constructed system carried enough statistical power to verify the key findings of the Apple Heart Study, which enrolled a much larger number of participants, where patients who received a prediagnosis tended to be older, male, and White with higher CHA2DS2-VASc (congestive heart failure, hypertension, age ≥75 years, diabetes, stroke, vascular disease, age 65-74 years, sex category) scores (P