Cardiac imaging helps improve ECG detection of Chagas disease
Leveraging Cardiac Imaging to Improve ECG-Based Detection of Chagas Disease in Resource-Constrained Settings
Machine LearningArtificial Intelligence
Summary
Chagas disease harms the heart and is hard to detect in poorer areas because the best imaging machines are rare. The authors used a large set of heart images and electrical recordings from healthy people to teach a computer to understand the heart’s structure. They then showed that this training helps the computer better spot signs of Chagas disease using only the electrical signals from a simple ECG test. Their method worked well even on different groups of patients, suggesting it could help detect Chagas where advanced imaging is not available.
Chagas diseasecardiomyopathycardiac magnetic resonance (CMR)electrocardiography (ECG)contrastive pre-trainingInfoNCE objectiveUK BiobankAUROCcross-validationSaMi-Trop dataset
Authors
Laura Alvarez-Florez, Daniel Uyterlinde, Samuel Ruipérez-Campillo, Lukas P. A. Arts, Folkert W. Asselbergs, Fleur V. Y. Tjong
Abstract
Chagas disease is a major cause of cardiomyopathy in Latin America. Cardiac magnetic resonance (CMR) imaging can characterize its structural abnormalities, but scanners and expert readers remain scarce in endemic regions. Electrocardiography (ECG) is inexpensive and widely available, yet structural disease must be inferred indirectly from electrical signals. We propose to transfer CMR-derived structural knowledge to ECG through contrastive pre-training. Using 63,193 paired ECG-CMR examinations from the UK Biobank, we align an ECG encoder with a clinically grounded CMR embedding space using an asymmetric InfoNCE objective. Despite seeing no Chagas cases during pre-training, the resulting representation improves ECG-based Chagas detection. Across CODE-15% and SaMi-Trop, a frozen linear probe achieves an AUROC of 0.851 and sensitivity at the top 5% of predicted risk (Top5%-TPR) of 0.427 in five-fold cross-validation, compared with 0.827 and 0.377 for an unaligned ECG-FM baseline. On the PhysioNet/CinC 2025 Challenge test set, our model obtains the highest AUROC on SaMi-Trop-3 and the best ELSA-Brasil challenge score among the three top-performing methods, indicating that imaging-supervised ECG representations can generalize to populations and settings beyond the pre-training distribution.