Clinically interpretable risk stratification in Chagas disease using novel derived variables and calibrated decision trees

• Henrique C. Parro USP
• Alexandra Hurtado Ortíz Hospital Internacional de Colombia
• Alan Demétrius Baria Valejo UFSCar
• Liliana Torcoroma García UDES
• Lina Garcés USP

DOI: https://doi.org/10.5753/eniac.2026.31034

Resumo

This work investigates machine learning for risk stratification in Chagas cardiomyopathy. We evaluate a novel set of 10 derived clinical variables and propose an interpretable decision-support framework based on calibrated decision trees, threshold optimization, and abstention mechanisms. Three clinical representations (4 established variables, 10 derived variables, and 97 clinical variables) are compared under binary and ternary prediction settings. Results show that the comprehensive dataset achieves the best predictive performance, while the derived variables provide a compact alternative, outperforming the 4-variable panel only in the ternary setting. Furthermore, the proposed framework improves the sensitivity–specificity trade-off while preserving coverage, supporting safer clinical triage.

Referências

Abreu, V. V. (2021). Artificial intelligence-based decision for the prediction of cardioembolism in patients with chagas disease and ischemic stroke. Journal of Stroke and Cerebrovascular Diseases, 30(10):106034.

Chapman, P. (2000). CRISP-DM 1.0: Step-by-step data mining guide. Technical report, CRISP-DM Consortium.

Davis, J. and Goadrich, M. (2006). The relationship between precision-recall and roc curves. In Proceedings of the 23rd International Conference on Machine Learning (ICML ’06), pages 233–240.

Domingues, P. (2020). Você sabe o que é CRISP-DM? CRISP-DM é a abreviação de Cross Industry Standard Process for Data Mining. Bexs.IO.

Ferreira, A. M. (2022). Two-year death prediction models among patients with chagas disease using machine learning-based methods. PLOS Neglected Tropical Diseases, 16(4):e0010356.

Ghilardi, J. (2024). Machine learning for predicting chagas disease infection in rural areas of brazil. PLOS Neglected Tropical Diseases, 18(9):e0012026.

Guo, C., Pleiss, G., Sun, Y., and Weinberger, K. Q. (2017). On calibration of modern neural networks. In Precup, D. and Teh, Y. W., editors, Proceedings of the 34th International Conference on Machine Learning (ICML), volume 70 of Proceedings of Machine Learning Research, pages 1321–1330. PMLR.

Jidling, C. (2023). Screening for chagas disease from the electrocardiogram using a deep neural network. PLOS Neglected Tropical Diseases, 17(7):e0011118.

Kelly, C. J., Karthikesalingam, A., Suleyman, M., Corrado, G., and King, D. (2019). Key challenges for delivering clinical impact with artificial intelligence. BMC Medicine, 17(195).

Kompa, B., Snoek, J., and Beam, A. L. (2021). Second opinion needed: Communicating uncertainty in medical machine learning. NPJ Digital Medicine, 4(4).

Kuhn, M. and Johnson, K. (2013). Applied Predictive Modeling. Springer.

Niculescu-Mizil, A. and Caruana, R. (2005). Predicting good probabilities with supervised learning. In Proceedings of the 22nd International Conference on Machine Learning (ICML ’05), pages 625–632, New York, NY, USA. ACM.

Oliveira, B. (2021). Left ventricular systolic dysfunction predicted by artificial intelligence using the electrocardiogram in chagas disease patients – the sami-trop cohort. PLOS Neglected Tropical Diseases, 15(7):e0009974.

Parro, H., Ortiz, A., Valejo, A., García, L., and Garcés, L. (2026). Chagas decision tree: Data and code repository. [link]. GitHub repository, accessed February 25, 2026.

Provost, F. and Fawcett, T. (2013). Data Science for Business: What You Need to Know about Data Mining and Data-Analytic Thinking. O’Reilly Media.

Rassi, A., Rassi, A., and Marin-Neto, J. A. (2010). Chagas disease. The Lancet, 375(9723):1388–1402.

Weber de Santana Teles, S. (2021). Machine learning and automatic selection of attributes for the identification of chagas disease from clinical and sociodemographic data. Research, Society and Development, 10(4):e19310413879.

World Health Organization (2025). Chagas disease (also known as american trypanosomiasis). [link]. WHO Fact Sheet, updated 2 April 2025.