ItemArticle

AI-Enabled Early Detection of Chemo-Induced Cardiotoxicity Patterns Using ECG Time Series Data

Title
AI-Enabled Early Detection of Chemo-Induced Cardiotoxicity Patterns Using ECG Time Series Data
Creator
Upreti, Kamal; George, Jossy P.; Malik, Khushboo; Radhakrishnan, G. V.; Ga-B?aszczykowska, Agnieszka
Description
Objectives: Chemotherapy-induced cardiotoxicity is still a major clinical problem, usually appearing subclinically before structural or symptomatic cardiac dysfunction appears. Standard surveillance methods use imaging and biomarkers, which are time-intensive and money-intensive and can only identify damage at more advanced levels. Electrocardiography (ECG) provides a low-cost, non-invasive method that can detect early electrophysiological changes but is not fully utilized in cardio-oncology. The present work was designed to build an explainable machine learning model for predicting chemo-like cardiotoxicity patterns at an early stage from single-lead ECG signals. Methods: A public ECG data set (n=4997 segments) underwent preprocessing and was converted to 18 temporal, morphologic, and spectral features. Two ensemble learning algorithmsRandom Forest and XGBoostwere trained and validated with stratified splits. Model performance was assessed with ROCAUC, PRAUC, and F1-score with 1000 bootstrap resampling. Feature interpretability was evaluated through permutation importance and SHAP analysis. Results: Both models scored near-perfect classification (ROCAUC and PRAUC>0.99, F1-score ? 0.986). Spectral entropy, band3 (high-energy frequency), QT surrogate, and peak count were the top features ranking alongside early cardiotoxicity indicators like repolarization instability and autonomic imbalance. Conclusions: The feature-driven, interpretable ML architecture suggested here shows that single-lead ECG has the potential to be an affordable and clinically relevant tool for the early detection of chemotherapy-induced cardiotoxicity. The method provides a feasible route toward implementation in precision cardio-oncology, particularly in resource-poor or ambulatory environments. 2025
Source
American Journal of Clinical Oncology: Cancer Clinical Trials;
Date
01-01-2025
Publisher
Lippincott Williams and Wilkins
Subject
cardio-oncology; cardiotoxicity; chemotherapy; ECG; precision medicine
Coverage
Upreti K., Department of Computer Science, Christ University, Delhi NCR, Uttar Pradesh, Ghaziabad, India; George J.P., Department of Computer Science, Christ University, Delhi NCR, Uttar Pradesh, Ghaziabad, India; Malik K., Department of Computer Science, Christ University, Delhi NCR, Uttar Pradesh, Ghaziabad, India; Radhakrishnan G.V., Department of Computer Science, KIIT School of Management (KSOM), Bhubaneswar, India; Ga-B?aszczykowska A., School of Law, War Studies University, Warsaw, Poland
Rights
Restricted Access; Hardcopy may be available in the library
Relation
ISSN: 2773732; CODEN: AJCOD
Format
online
Language
English
Type
Article

Citation

Upreti, Kamal; George, Jossy P.; Malik, Khushboo; Radhakrishnan, G. V.; Ga-B?aszczykowska, Agnieszka, “AI-Enabled Early Detection of Chemo-Induced Cardiotoxicity Patterns Using ECG Time Series Data,” CHRIST (Deemed To Be University) Institutional Repository, accessed June 18, 2026, https://archives.christuniversity.in/items/show/22830.

Output Formats