University of Oldenburg (AI4Health) (Strodthoff, Lopez Alcaraz, Haverkamp)
Model weights not public. Contact creators for more information.
Unified deep-learning model for 12-lead ECG analysis that predicts a broad range of cardiac and non-cardiac discharge diagnoses coded under the ICD-10 classification system, evaluated as a unified screening tool for emergency departments where a single ECG could flag many potential conditions at once rather than one disease at a time. Introduces the MIMIC-IV-ECG-ICD-ED benchmark dataset (derived from MIMIC-IV and MIMIC-IV-ECG) and reports AUROC scores across diverse diagnostic scenarios (all discharge diagnoses vs. emergency-department-only diagnoses, cardiac vs. non-cardiac ICD-10 chapters), suggesting integration into emergency-department clinical decision-support systems.
Architecture
Other
S4 (Structured State-Space Sequence) model applied to raw 12-lead ECG signal for multi-label ICD-10 discharge-diagnosis prediction
Framework
PyTorch
Added to catalog
2026-08-10
800,035 12-lead ECG-report pairs from 161,352 subjects at Beth Israel Deaconess Medical Center.
Benchmark dataset derived from MIMIC-IV and MIMIC-IV-ECG that links each 12-lead ECG to ICD-10-coded discharge diagnoses (cardiac and non-cardiac) for the source hospital admission, with both emergency-department-only and all-encounter benchmarking scenarios.
Multi-label ICD-10 discharge-diagnosis prediction (cardiac and non-cardiac) from 12-lead ECG in the emergency-department setting