Screening for Chagas disease from the electrocardiogram using a deep neural network
PLOS Neglected Tropical Diseases · 2023
DOI: 10.1371/journal.pntd.0011118 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS Neglected Tropical Diseases, 2023. Verfasst von Carl Jidling und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information Technology, Uppsala University, Uppsala, Sweden. Hauptthemen laut MEDLINE: Chagas Cardiomyopathy, Chagas Disease. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIAID NIH HHS, Knut och Alice Wallenbergs Stiftelse, CNPq.
Abstract (Originalsprache)
Background
Worldwide, it is estimated that over 6 million people are infected with Chagas disease (ChD). It is a neglected disease that can lead to severe heart conditions in its chronic phase. While early treatment can avoid complications, the early-stage detection rate is low. We explore the use of deep neural networks to detect ChD from electrocardiograms (ECGs) to aid in the early detection of the disease.
Methods
We employ a convolutional neural network model that uses 12-lead ECG data to compute the probability of a ChD diagnosis. Our model is developed using two datasets which jointly comprise over two million entries from Brazilian patients: The SaMi-Trop study focusing on ChD patients, enriched with data from the CODE study from the general population. The model’s performance is evaluated on two external datasets: the REDS-II, a study focused on ChD with 631 patients, and the ELSA-Brasil study, with 13,739 civil servant patients.
Findings
Evaluating our model, we obtain an AUC-ROC of 0.80 (CI 95% 0.79-0.82) for the validation set (samples from CODE and SaMi-Trop), and in external validation datasets: 0.68 (CI 95% 0.63-0.71) for REDS-II and 0.59 (CI 95% 0.56-0.63) for ELSA-Brasil. In the latter, we report a sensitivity of 0.52 (CI 95% 0.47-0.57) and 0.36 (CI 95% 0.30-0.42) and a specificity of 0.77 (CI 95% 0.72-0.81) and 0.76 (CI 95% 0.75-0.77), respectively. Additionally, when considering only patients with Chagas cardiomyopathy as positive, the model achieved an AUC-ROC of 0.82 (CI 95% 0.77-0.86) for REDS-II and 0.77 (CI 95% 0.68-0.85) for ELSA-Brasil.
Interpretation
The neural network detects chronic Chagas cardiomyopathy (CCC) from ECG—with weaker performance for early-stage cases. Future work should focus on curating large higher-quality datasets. The CODE dataset, our largest development dataset includes self-reported and therefore less reliable labels, limiting performance for non-CCC patients. Our findings can improve ChD detection and treatment, particularly in high-prevalence areas.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Information Technology, Uppsala University, Uppsala, Sweden.
- Preventive Medicine, School of Medicine, Universidade Federal de São João del-Rei, Divinópolis, Brazil.
- Graduate Program in Health Sciences, Universidade Estadual de Montes Claros, Montes Claros, Brazil.
- Preventive Medicine, School of Medicine, Clinical Hospital/EBSERH, Universidade Federal de Minas Gerais, Belo Horizonte, Brazil.
- Instituto de Medicina Tropical da Faculdade de Medicina, Universidade de São Paulo, São Paulo, Brazil.
- Department of Internal Medicine, Faculdade de Medicina, Telehealth Center, Hospital das Clínicas, Universidade Federal de Minas Gerais, Belo Horizonte, Brazil.
ORCID-Profile: Carl Jidling, Daniel Gedon, Thomas B Schön, Claudia Di Lorenzo Oliveira, Clareci Silva Cardoso, Sandhi Maria Barreto, Ester C Sabino, Antonio L P Ribeiro, Antônio H Ribeiro
Förderung
- NIAID NIH HHS
- Knut och Alice Wallenbergs Stiftelse
- CNPq
- FAPEMIG
- Brazilian Ministries of Health and of Science and Technology
- National Institutes of Health
Zitieren
APA
Jidling, C., Gedon, D., Schön, T. B., Oliveira, C. D. L., Cardoso, C. S., Ferreira, A. M., Giatti, L., Barreto, S. M., Sabino, E. C., Ribeiro, A. L. P., & Ribeiro, A. H. (2023). Screening for Chagas disease from the electrocardiogram using a deep neural network. PLOS Neglected Tropical Diseases. https://doi.org/10.1371/journal.pntd.0011118
Vancouver
Jidling C, Gedon D, Schön TB, Oliveira CDL, Cardoso CS, Ferreira AM, et al. Screening for Chagas disease from the electrocardiogram using a deep neural network. PLOS Neglected Tropical Diseases. 2023. doi:10.1371/journal.pntd.0011118
BibTeX
@article{Jidling2023,
author = {Jidling, Carl and Gedon, Daniel and Schön, Thomas B and Oliveira, Claudia Di Lorenzo and Cardoso, Clareci Silva and Ferreira, Ariela Mota and Giatti, Luana and Barreto, Sandhi Maria and Sabino, Ester C and Ribeiro, Antonio L P and Ribeiro, Antônio H},
title = {Screening for Chagas disease from the electrocardiogram using a deep neural network},
journal = {PLOS Neglected Tropical Diseases},
year = {2023},
doi = {10.1371/journal.pntd.0011118}
}
EUVIMED