Machine learning for classification of advanced rheumatic heart disease using electrocardiogram in cardiology ward - research open access

Sep 29, 2026

Uploaded by jay

Rheumatic heart disease (RHD) develops from untreated streptococcal throat infections, causing progressive, often irreversible cardiac valve damage. Echocardiography is the standard, yet it is constrained in low-income settings by limited resources and specialist availability. The study evaluates electrocardiogram (ECG)-based detection in cardiology wards, aiming to determine whether ECG can function as a cost-effective diagnostic tool in endemic, resource-constrained regions.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages15

Reading Time38 min

AccessFree to download

Abstract

Background

Methods

Results

Conclusion

Chuma etal. BMC Cardiovascular Disorders (2026) 26:6 BMC Cardiovascular Disorders [https://doi.org/10.1186/s12872-025-05315-1](https://doi.org/10.1186/s12872-025-05315-1) RESEARCH Open Access Machine learning for classification of advanced rheumatic heart disease using electrocardiogram in cardiology ward Amsalu Tomas Chuma 1,3*, Melkamu Hunegnaw Asmare 1,4, Carolina Varon2, Desalew Mekonnen Kassie5, Chunzhuo Wang 1 and Bart Vanrumste 1 Abstract Background Rheumatic heart disease (RHD) arises from untreated streptococcal throat infections caused by betahemolytic group A streptococci, leading to progressive damage to cardiac valves. While echocardiography is the gold standard for RHD diagnosis, its use in low-income countries is limited due to scarce resources and a lack of trained professionals. Automated RHD detection via echocardiography and phonocardiography data has shown promising, but the effectiveness of electrocardiogram (ECG) for detecting RHD in endemic regions at cardiac wards with limited resource remains uncertain. This study explores the viability of ECG as a cost-effective tool for RHD detection in cardiac wards. Methods The study utilizes a dataset comprising single-lead ECG recordings from 124 confirmed RHD patients and 46 healthy controls collected at a major referral hospital in Ethiopia. Additionally, an extended-RHDECG dataset, which consists of age-matched ECGs from the Physikalisch-Technische Bundesanstalt (PTB-XL) dataset and RHD ECGs, was utilized. A single lead ECG segment of 10-second duration per patient was resampled at 250 Hz. Temporal and relative wavelet energy (RWE) features combined with Convolutional Neural Network (CNN) model features were employed for classification of prevalent cardiovascular diseases in the context of the Global South. Results A 5-folds cross-validation on RHDECG dataset using CNN model showed an average accuracy (mean ± std) of 88.6 ± 0. 2% in detecting RHD from healthy controls. This result was improved with combined features of CNN, temporal and RWE to an average accuracy of 94.6 ± 0. 1% . Similar evaluation on extended-RHDECG yielded an accuracy of 54.3 ± 0. 3%, which reached to 71.2 ± 0. 3% considering the top-2 predictions of the six classes. The RWE concentrations at higher frequency bands were significantly greater in the RHD group than in the healthy control group. Conclusion The findings suggest that single-lead ECG in combination with machine learning could serve as a potential tool for automatically classifying patients with advanced RHD. ECG time‒frequency features effectively capture abnormalities associated with RHD, enhancing the performance of deep CNN models. This approach offers *Correspondence: Amsalu Tomas Chuma [amsaluthomas.chuma@kuleuven.be](amsaluthomas.chuma@kuleuven.be) Full list of author information is available at the end of the article © The Author(s) 2025. Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit [http://creati](http://creati)[vecommons.org/l](vecommons.org/l)icenses/by-nc-nd/4.0/. Chuma et al. BMC C

FAQs

Why is electrocardiogram (ECG) being considered for detecting advanced rheumatic heart disease (RHD)?

Echocardiography is the gold standard but is limited in low-income countries due to scarce resources and lack of trained professionals. The study investigates whether ECG can provide a cost-effective alternative for RHD detection in cardiology wards.

What data and preprocessing are used to train and evaluate the classification model?

The study uses single-lead ECG recordings from 124 confirmed RHD patients and 46 healthy controls collected in Ethiopia. It also uses an extended-RHD ECG dataset with age-matched ECGs from PTB-XL plus RHD ECGs, resampling 10-second segments at 250 Hz.

How well does the model perform and what improves accuracy?

Using 5-fold cross-validation on the RHDECG dataset with a CNN model yields an average accuracy of 88.6%. Combining CNN features with temporal features and relative wavelet energy (RWE) increases accuracy to 94.6%, while extended-RHDECG reaches 71.2% using top-2 predictions across six classes.

Sep 29, 2026

Uploaded by jay