A deep learning model trained to extract digital biomarkers from electrocardiograms has successfully validated across a large-scale U.S. healthcare system. All 10 ECG-AI biomarkers met non-inferiority criteria and showed consistent performance for identifying both acute cardiac emergencies and structural heart disease. Original paper: External validation of ECG artificial intelligence for emergency and cardiac assessment across a large-scale U.S. healthcare system. — NPJ digital medicine. 10.1038/s41746-026-00001 📄 Read the article