Ahus AIM Chagas ECG model

Akershus University Hospital / University of Oslo (Stenhede, Ranjbar)

12-lead ECG

Filter catalog by Modality:
ECG

Chagas disease

Filter catalog by Disease / Trait:
Other Conditions

Binary classification

Filter catalog by Task Type:
Classification

CNN (1D)

Filter catalog by Architecture:
Convolutional (CNN)

PyTorch

Filter catalog by Framework:
PyTorch

code View code

Model weights not public. Contact creators for more information.

Screens 12-lead ECGs for Chagas cardiomyopathy by first pretraining a feature extractor to predict blood-biomarker levels from MIMIC-IV-ECG data, then fine-tuning on Brazilian CODE-15%, SaMi-Trop, and PTB-XL recordings; the final model is a 5-model ensemble. Submitted to the George B. Moody PhysioNet Challenge 2025 (Detection of Chagas Disease from the ECG), where it placed 5th on the official leaderboard. Developed by a team from Akershus University Hospital and the University of Oslo.

memory Specifications

description Publication

Biomarker-Based Pretraining for Chagas Disease Screening in Electrocardiograms open_in_new

2026 · original paper

database Training & evaluation data

CODE-15% open_in_new

train

Brazil

Publicly available 15% subset of the CODE (Clinical Outcomes in Digital Electrocardiology) dataset from the Telehealth Network of Minas Gerais; full CODE dataset (>2 million exams) is request-only.

SaMi-Trop open_in_new

train

public 1,631 subjects · Brazil

1,631 12-lead ECGs from serologically confirmed chronic Chagas disease patients in Brazil.

science Capabilities & performance