Detection of Chagas disease from the ECG: the George B. Moody PhysioNet Challenge 2025
9 affiliations
- 1Emory University
- 2Johns Hopkins University
- 3University of the Basque Country EHU
- 4Universidade Federal de Minas Gerais
- 5Instituto de Medicina Tropical da Faculdade de Medicina da Universidade de São Paulo
- 6Science for Life Laboratory (SciLifeLab)
- 7Telehealth Center and Cardiology Service, Hospital das Clínicas, Universidade Federal de Minas Gerais
- 8Uppsala University
- 9Department of Biomedical Engineering, Georgia Institute of Technology and Emory University
Abstract
Objective. Chagas disease is a parasitic infection that is endemic to Latin America and primarily transmitted by insects. When untreated, Chagas disease can cause cardiomyopathy. Serological testing capacities for Chagas disease are limited, but Chagas cardiomyopathy often manifests in electrocardiograms (ECGs), providing an opportunity to use ECG-based screening to prioritize patients for testing and treatment. Approach. The George B. Moody PhysioNet Challenge 2025 invited teams to develop algorithmic approaches for identifying potential cases of Chagas disease from ECGs. The Challenge metric, denoted by TPR@5%, measured the true positive rate of the top 5% of patients determined by an algorithm to be the most likely to have Chagas disease, reflecting the Brazilian serological testing capacity. The data included more than 360 000 ECGs from five Brazilian databases. We also developed an ensemble algorithm for the best-performing entries. Main results. This Challenge provided multiple innovations. First, we leveraged several datasets with labels from either patient reports or serological testing, providing a large dataset with weak labels and smaller datasets with strong labels. Second, we augmented the data to support model robustness and generalizability to unseen data sources. Third, we applied an evaluation metric, TPR@5%, that captured the local serological testing capacity for Chagas disease to frame the Challenge as a triage task. Fourth, we developed an ensemble model that combined the individual Challenge models to improve performance. These innovations provided reliable sensitivity at clinically relevant operating points. The performance of the top-performing Challenge model (Biomed-Cardio) varied performed well across datasets (TPR@5% of 0.468 on REDS-II and TPR@5% of 0.125 on ELSA-Brasil), and our ensemble-based approach demonstrated consistent performance across datasets (TPR@5% of 0.389 on REDS-II and TPR@5% of 0.146 on ELSA-Brasil). Significance. Over 630 participants from 111 teams submitted over 1300 entries during the Challenge, representing diverse approaches from academia and industry worldwide.
Related
- The Utility of Microbial Cell-Free DNA in the Rapid Diagnosis of Chagas Disease: Chagas Disease Case Series
- Ecology, Evolution and Control of Chagas Disease: A Century of Neglected Modelling and a Promising Future
- A cellular automaton model for the transmission of Chagas disease in heterogeneous landscape and host community
- Invasion speeds of Triatoma dimidiata, vector of Chagas disease: An application of orthogonal polynomials method
- Small molecule biomarkers predictive of Chagas disease progression
BibTeX
@article{reyna2026detection,
title = {{Detection of Chagas disease from the ECG: the George B. Moody PhysioNet Challenge 2025}},
author = {Matthew A. Reyna and Soheil Saghafi and Zuzana Koscova and Audrey T Weigle and Ján Pavluš and Andoni Elola and Salman S. Seyedi and Kiersten S. Campbell and Qiao Li and Sandhi Barreto and Ester Cerdeiro Sabino and Antonio Luiz P. Ribeiro and Antonio Luiz Pinho Ribeiro and Reza Sameni and Gari D. Clifford},
journal = {Physiological Measurement},
year = {2026},
month = sep,
doi = {10.1088/1361-6579/aead44},
url = {https://doi.org/10.1088/1361-6579/aead44},
note = {CC BY},
}
RIS
TY - JOUR
TI - Detection of Chagas disease from the ECG: the George B. Moody PhysioNet Challenge 2025
AU - Matthew A. Reyna
AU - Soheil Saghafi
AU - Zuzana Koscova
AU - Audrey T Weigle
AU - Ján Pavluš
AU - Andoni Elola
AU - Salman S. Seyedi
AU - Kiersten S. Campbell
AU - Qiao Li
AU - Sandhi Barreto
AU - Ester Cerdeiro Sabino
AU - Antonio Luiz P. Ribeiro
AU - Antonio Luiz Pinho Ribeiro
AU - Reza Sameni
AU - Gari D. Clifford
PY - 2026
DA - 2026/09/28
JO - Physiological Measurement
DO - 10.1088/1361-6579/aead44
UR - https://doi.org/10.1088/1361-6579/aead44
AB - Objective. Chagas disease is a parasitic infection that is endemic to Latin America and primarily transmitted by insects. When untreated, Chagas disease can cause cardiomyopathy. Serological testing capacities for Chagas disease are limited, but Chagas cardiomyopathy often manifests in electrocardiograms (ECGs), providing an opportunity to use ECG-based screening to prioritize patients for testing and treatment. Approach. The George B. Moody PhysioNet Challenge 2025 invited teams to develop algorithmic approaches for identifying potential cases of Chagas disease from ECGs. The Challenge metric, denoted by TPR@5%, measured the true positive rate of the top 5% of patients determined by an algorithm to be the most likely to have Chagas disease, reflecting the Brazilian serological testing capacity. The data included more than 360 000 ECGs from five Brazilian databases. We also developed an ensemble algorithm for the best-performing entries. Main results. This Challenge provided multiple innovations. First, we leveraged several datasets with labels from either patient reports or serological testing, providing a large dataset with weak labels and smaller datasets with strong labels. Second, we augmented the data to support model robustness and generalizability to unseen data sources. Third, we applied an evaluation metric, TPR@5%, that captured the local serological testing capacity for Chagas disease to frame the Challenge as a triage task. Fourth, we developed an ensemble model that combined the individual Challenge models to improve performance. These innovations provided reliable sensitivity at clinically relevant operating points. The performance of the top-performing Challenge model (Biomed-Cardio) varied performed well across datasets (TPR@5% of 0.468 on REDS-II and TPR@5% of 0.125 on ELSA-Brasil), and our ensemble-based approach demonstrated consistent performance across datasets (TPR@5% of 0.389 on REDS-II and TPR@5% of 0.146 on ELSA-Brasil). Significance. Over 630 participants from 111 teams submitted over 1300 entries during the Challenge, representing diverse approaches from academia and industry worldwide.
SN - 0967-3334
SN - 1361-6579
ER -