Vision Transformer Detects Heart Condition from ECGs with High Accuracy

Researchers have developed a vision transformer model capable of detecting reduced left ventricular ejection fraction (LVEF) from standard electrocardiograms (ECGs). The model, trained on over 10,000 patients across multiple sites, achieved an AUROC of 0.88 in an external validation cohort. Attention maps from the model highlight focus on the QRS complex, offering interpretability and suggesting routine ECGs could serve as a scalable screening tool for identifying patients needing further echocardiography. AI

IMPACT Potential to enhance early detection of heart conditions using widely available ECG data, improving patient triage and outcomes.

RANK_REASON Academic paper detailing a novel application of a vision transformer for medical diagnosis. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• arXiv
• AUROC
• echocardiography
• Left Ventricular Systolic Dysfunction
• QRS complex
• US
• vision transformer

• paper
• model release
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →