What question did this study set out to answer?

The aim is to develop an automated detection system for Chagas disease using ECG signals.

March 2, 2026Open Access

Automated detection of Chagas disease from ECG signals using wavelet scattering transform and RUSBoost classifier

Key Result

Automated ECG analysis using wavelet scattering transform and RUSBoost achieved 90.53% accuracy for early Chagas disease detection in PhysioNet Challenge 2025.

Key Points

The aim is to develop an automated detection system for Chagas disease using ECG signals.
Preprocessing ECG signals by standardizing sampling frequency and detecting QRS complexes.
Extracting features using wavelet scattering transform, statistical descriptors from heart rate variability, and patient metadata.
Utilizing the RUSBoost classifier for binary classification of Chagas versus non-Chagas cases.
Achieved an accuracy of 90.53% on the evaluation dataset.
Reported F1 score for Chagas cases is 10.73%.
Obtained AUROC of 63.67% and AUPRC of 11.96%.

Structured PICO

Does an automated machine learning system using wavelet scattering transform and RUSBoost classifier accurately detect Chagas disease from 12-lead ECG signals?

Population

ECG recordings from the PhysioNet/Computing in Cardiology (CinC) Challenge 2025 dataset

Intervention

Automated detection system using wavelet scattering transform (WST) coefficients, HRV statistical descriptors, statistical features, patient metadata, and RUSBoost classifier

Comparator

Non-Chagas cases

Outcome

Diagnostic performance (Accuracy, F1 Chagas, AUROC, AUPRC, Challenge Score)surrogate

An automated machine learning framework using ECG signals shows potential for scalable, non-invasive early detection of Chagas disease.

Main Result

Absolute Event Rate: 0% vs 0%

Abstract

Early diagnosis of Chagas disease plays a vital role in enabling timely treatment and reducing the likelihood of underlying severe cardiovascular complications. Electrocardiogram (ECG) signals contain vital information that reflects cardiac disease progression, motivating the use of advanced signal processing and machine intelligence for accurate diagnosis of Chagas disease. This work presents an automated system for Chagas disease detection using conventional 12-lead ECG recordings. Approach: The method begins with preprocessing by standardizing the ECG sampling frequency and detecting QRS complexes. Then, four categories of features are extracted: (a) wavelet scattering transform (WST) coefficients from limb lead II and chest leads V1 and V3; (b) statistical descriptors from heart rate variability (HRV); (c) statistical features across all leads; and (d) patient metadata. The computed diagnostic feature vector is used as an input to the RUSBoost classifier for its ability to handle class imbalance for binary classification between Chagas and non-Chagas cases. Main Results: The proposed framework was evaluated on the PhysioNet/Computing in Cardiology (CinC) Challenge 2025 dataset. Evaluation on the hidden test data set yielded an accuracy of 90.53 %,F1 Chagas = 10.73 %, AUROC=63.67 %, AUPRC=11.96 % and Challenge Score = 20.5% under the team name Medics. Significance: The findings of this work highlight the potential of signal processing and machine learning based analysis of ECG for scalable, non-invasive, and cost-effective early detection of Chagas disease, supporting improved clinical decision-making and preventive healthcare strategies. Keywords: Wavelet scattering transform, Heart rate variability, RUSBoost classifier, Chagas disease, PhysioNet Challenge 2025.