Topic
cardiology
Artificial Intelligence #explainable ai#machine learning
AI Model Predicts Five-Year Heart Failure Risk from 24-Hour ECG Data
Researchers at Technion and Leumit Health Services developed DeepHHF, a deep learning model that analyzes 24-hour single-lead ECG recordings to predict heart failure risk within five years. The model achieved an AUC of 0.80, outperforming shorter segments and clinical scores, and identified high-risk individuals with a twofold chance of hospitalization or death.
Jun 21, 2026 1 source
Artificial Intelligence #ai#active learning
AI Pace-Mapping System Uses Continual Learning to Cut Pacing Sites by 67% for Ventricular Tachycardia
Researchers introduced cAPM, a continuous AI-assisted pace-mapping system for ventricular tachycardia ablation. Using a surrogate neural network, active learning, and continual learning, cAPM reduced required pacing sites from 13.7 to 4.5 while improving localization probability from 38% to 81% within 5 mm accuracy, compared to the state-of-the-art active-learning method.
Jun 20, 2026 1 source