Deep Learning AI Reads ECGs in Under 2 Seconds, Predicts Kidney Disease and Diabetes
EricTopol · x · 2026-09-01
A new paper in The Lancet Digital Health from Eric Topol's team shows a deep learning model trained on millions of routine ECGs can extract information invisible to human experts, spotting heart failure and valve disease in under 2 seconds, while also predicting kidney disease, diabetes, and atrial fibrillation, and detecting hard-to-diagnose cardiac conditions.
Topol stresses it's not "superhuman" — just deep learning. Traditional ECGs cannot detect heart disease, which requires echocardiograms with months of waiting; the tool could fast-track high-risk patients. Results were presented at the ESC congress in Munich.
Related event: Deep Learning AI Detects Heart Disease from ECG in Under Two Seconds(3 posts)→
More from Research
- Elegant Sliding Window Aggregation Algorithm for Non-Invertible Operators Goes Viral — Paimaamu · 2026-10-16
- A $50 site of 50,000 fake stats got cited by ChatGPT for 7 months — metehan777 · 2026-10-16
- It's not gradient descent: burny_tech corrects the diagnosis to RLHF mode collapse — burny_tech · 2026-10-16
- A beginner-friendly introduction to causal inference kicks off, Part 1 — Nasereliver · 2026-10-16
- FBI method trains for Pass@K with one sample per update at 12.3% of the cost — EmtiyazKhan · 2026-10-16
- Berkeley researchers sample humanoid robot policies directly from weight space with diffusion — berkeley_ai · 2026-10-16