An AI tool accurately detected structural heart disease from smartwatch single-lead ECGs in a 600-person prospective trial.
Key Details
- 1AI model was trained using 266,000 12-lead ECGs from 110,000 patients and validated on large external cohorts.
- 2Prospective real-world testing was performed with 600 adults using smartwatch-recorded single-lead ECGs.
- 3Algorithm achieved 88% accuracy (AUC) in smartwatch data; sensitivity was 86% and negative predictive value 99%.
- 4Diseases detected included weakened pumping, valve damage, or thickened heart muscle—most commonly found with cardiac ultrasound (echo).
- 5Preliminary results were presented at AHA Scientific Sessions 2025 and have not yet been peer-reviewed.
Why It Matters
Wearable devices leveraging AI may democratize early detection of serious heart conditions, traditionally requiring advanced imaging. This signals a potential paradigm shift in accessible screening workflows, informing radiology and cardiology practice.
Source
EurekAlert
Related News
•EurekAlert
NYU AI Model Improves 5-Year Breast Cancer Risk Prediction via 3D Mammograms
NYU researchers developed an AI model using longitudinal 3D mammograms that outperforms single-scan and 2D-based tools in predicting 5-year breast cancer risk.
•EurekAlert
AI Framework Accelerates Aortic Aneurysm Risk Prediction from Imaging
Researchers developed BioPINN-LM, combining physics-informed neural networks and multimodal large language models to deliver fast, interpretable risk assessments for ascending thoracic aortic aneurysms.
•EurekAlert
Study Finds Patient Voices Missing in Generative AI Design for Oncology
A Flinders University-led review found patients and carers are rarely involved in shaping generative AI tools used in oncology.