Key result
Reliability-aware hierarchical learning for ECG Chagas screening achieves a ~0.16 PhysioNet Challenge Score.
Why the study?
Chagas disease remains underdiagnosed in resource-limited regions, and ECG-based algorithm development is challenged by label noise, data scarcity, and the latent nature of infection.
Does a reliability-aware hierarchical learning strategy using a foundation model improve Chagas disease screening from 12-lead ECGs compared to a CNN trained from scratch?
Does a reliability-aware hierarchical learning strategy using a foundation model improve Chagas disease screening from 12-lead ECGs compared to a CNN trained from scratch?
A reliability-aware hierarchical learning strategy using transfer learning from an ECG foundation model provides a robust framework for Chagas disease screening in resource-constrained settings.
Answers are grounded in this paper and cite their sources.
May aid automated Chagas screening in endemic regions; leaves open prospective clinical validation before adoption.
Objective. Chagas disease, a neglected tropical disease (NTD) with significant cardiovascular impact, remains underdiagnosed in resource-limited regions. Electrocardiogram (ECG) screening offers a low-cost tool for detecting cardiac involvement, yet algorithm development is challenged by label noise, data scarcity, and the latent nature of infection. This study proposes a robust ECG-based screening framework that explicitly addresses these constraints. Approach. We introduce a Reliability-Aware Hierarchical Learning strategy that calibrates supervision according to data provenance, prioritizing serology-confirmed labels over noisy self-reports. To mitigate data scarcity, we compare a specialized convolutional neural network (CNN) trained from scratch with a transfer learning approach based on a Spatio-Temporal ECG foundation Model (FM). Performance is evaluated across varying data scales, and the representation structure is analyzed to interpret model behavior. Main results. On the official hidden test set of the George B. Moody PhysioNet/Computing in Cardiology Challenge 2025, our approach achieved a Challenge Score of 0.163. We observe that while the specialized CNN performs competitively in data-rich regimes, the FM exhibits superior robustness in extreme low-resource settings. Furthermore, performance reaches a plateau imposed by underlying disease physiology. Bimodal score distributions suggest that models distinguish established cardiomyopathy from indeterminate infection, which remains electrophysiologically indistinguishable from healthy controls. Significance. These findings clarify both the potential and intrinsic limits of ECG-based AI screening for NTD-associated cardiac involvement. Reliability-aware supervision and data-efficient transfer learning provide a practical framework toward scalable and clinically meaningful ECG screening systems in resource-constrained environments.
No takes yet. Share an insight, caveat, or question.
Wen et al. (2026) studied Chagas disease. Reliability-Aware Hierarchical Learning strategy vs. Specialized convolutional neural network (CNN) trained from scratch was evaluated on Challenge Score on the official hidden test set of the George B. Moody PhysioNet/Computing in Cardiology Challenge 2025. A reliability-aware hierarchical learning strategy for ECG-based Chagas disease screening achieved a Challenge Score of 0.163 on the PhysioNet/Computing in Cardiology Challenge 2025 hidden test set.
Synapse has enriched 10 related papers. Consider them for comparative context: