Biomarker-Based Pretraining for Chagas Disease Screening in Electrocardiograms

TL;DR

This paper introduces a biomarker-based pretraining method for ECG-based Chagas disease screening, leveraging blood biomarker prediction to improve detection accuracy on noisy datasets.

Contribution

It presents a novel pretraining approach using biomarker prediction to enhance ECG-based disease detection, achieving competitive results in a challenge setting.

Findings

Achieved a challenge score of 0.269, ranking 5th in the competition.

Pretraining on biomarker prediction improved Chagas detection performance.

Shared code and models publicly on GitHub for reproducibility.

Abstract

Chagas disease screening via ECGs is limited by scarce and noisy labels in existing datasets. We propose a biomarker-based pretraining approach, where an ECG feature extractor is first trained to predict percentile-binned blood biomarkers from the MIMIC-IV-ECG dataset. The pretrained model is then fine-tuned on Brazilian datasets for Chagas detection. Our 5-model ensemble, developed by the Ahus AIM team, achieved a challenge score of 0.269 on the hidden test set, ranking 5th in Detection of Chagas Disease from the ECG: The George B. Moody PhysioNet Challenge 2025. Source code and the model are shared on GitHub: github.com/Ahus-AIM/physionet-challenge-2025