Mount Sinai researchers show that deep learning applied to ECGs can detect COPD early and accurately across diverse populations.
Key Details
- 1Study analyzed over 208,000 ECGs from more than 18,000 COPD cases and 49,000 matched controls spanning 2006-2023.
- 2A convolutional neural network achieved AUC 0.80 (internal), 0.82 (external validation), and 0.75 (UK Biobank).
- 3Model explainability linked predictions to clinically relevant ECG features (notably P-wave changes).
- 4Validation included distinct hospitals in New York City and patients from the UK Biobank.
- 5ECG-based AI tool uses standard 10-second, 12-lead data, enabling scalability and low cost for broad COPD screening.
Why It Matters
This work demonstrates that AI-driven ECG interpretation can provide scalable, non-invasive early detection for COPD, a major global health burden. Such AI models could expand access to screening in resource-limited settings, improving patient outcomes through earlier intervention.
Source
EurekAlert
Related News
•EurekAlert
AI Model Accurately Predicts Recurrence After Barrett’s Esophagus Therapy
Researchers created an AI tool that predicts recurrence of Barrett’s esophagus following endoscopic eradication therapies with greater than 90% accuracy.
•EurekAlert
Hybrid AI Model Enhances Early Lung Cancer Detection on CT Scans
Researchers developed a hybrid AI model that significantly improves early lung cancer detection from CT scans.
•EurekAlert
NIH Invests Additional $12.6M in USC-Led Imaging AI for Alzheimer's
NIH has renewed and expanded its support for a USC-led consortium developing AI to decode and treat Alzheimer's using imaging and genomic data.