A TabNet-Based Multidimensional Deep Learning Model for Predicting Doxorubicin-Induced Cardiotoxicity in Breast Cancer Patients

Sep 30, 2026

Objective: Develop and validate an interpretable TabNet-based deep learning model to predict doxorubicin-induced cardiotoxicity (DIC) in breast cancer patients by integrating multidimensional clinical data. Methods: A retrospective cohort of 2034 patients receiving doxorubicin-based chemotherapy (2021–2023) used six algorithms, with discrimination, calibration, and clinical utility evaluated via AUC, C-index, calibration plots, and decision curve analysis. Interpretability used attention-based feature importance and SHAP. Results: TabNet showed best performance (AUC 0.86, C-index 0.80) and identified eight dominant cardiometabolic predictors. Conclusions: The model provides accurate, stable, interpretable individualized prediction to support early intervention and precision management during anthracycline therapy.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages21

Reading Time53 min

AccessFree to download

Simple Summary

Abstract

Keywords

1. Introduction

Article A TabNet-Based Multidimensional Deep Learning Model for Predicting Doxorubicin-Induced Cardiotoxicity in Breast Cancer Patients Juanwen Cao 1, Xiaojian Hong 1, Li Dong 1, Wei Jiang 2,* and Wei Yang 1, * Academic Editor: Ognjen Arandjelovi´c Received: 4 November 2025 Revised: 26 December 2025 Accepted: 29 December 2025 Published: 30 December 2025 Copyright: © 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license. 1 Department of Cardiology, The Fourth Affiliated Hospital of Harbin Medical University, Harbin 150001, China; [842617@hrbmu.edu.cn](842617@hrbmu.edu.cn) (J.C.); [101232@hrbmu.edu.cn](101232@hrbmu.edu.cn) (X.H.); [843203@hrbmu.edu.cn](843203@hrbmu.edu.cn) (L.D.) 2 Department of Medical Oncology, Cancer Hospital of Dalian University of Technology, Cancer Hospital of China Medical University, Liaoning Cancer Hospital & Institute, No. 44 Xiaoheyan Road, Dadong District, Shenyang 110042, China * Correspondence: [202101422@hrbmu.edu.cn](202101422@hrbmu.edu.cn) (W.J.); [112465@hrbmu.edu.cn](112465@hrbmu.edu.cn) (W.Y.) Simple Summary Doxorubicin is a widely used chemotherapy drug for breast cancer, but it can cause heart damage in some patients, which may limit treatment and affect long-term outcomes. Identifying patients at high risk of cardiotoxicity before or during treatment remains challenging. In this study, we developed an interpretable deep learning model based on the TabNet architecture using routinely collected clinical, laboratory, electrocardiographic, and echocardiographic data. The model accurately predicted doxorubicin-induced cardiotoxicity and identified key risk factors related to cardiac function, electrical activity, and metabolic status. This approach may help clinicians recognize high-risk patients earlier and support personalized monitoring and preventive strategies during chemotherapy. Abstract Objective: To develop and validate an interpretable deep learning model based on the TabNet architecture for predicting doxorubicin-induced cardiotoxicity (DIC) in patients with breast cancer through integration of multidimensional clinical data. Methods: This retrospective study included 2034 patients who received doxorubicin-based chemotherapy at The Fourth Affiliated Hospital of Harbin Medical University between January 2021 and December 2023 . Clinical, biochemical, electrocardiographic, and echocardiographic parameters were incorporated into six predictive algorithms: logistic regression, decision tree, random forest, gradient boosting machine, XGBoost, and TabNet. Model discrimination, calibration, and clinical utility were assessed using AUC, C-index, calibration plots, and decision curve analysis. Model interpretability was evaluated through attention-based feature importance and SHAP analysis. Results: TabNet achieved the best overall predictive performance, with an AUC of 0.86 and a C-index of 0.80 in the validation cohort, demonstrating superior discrimination, calibration, and generalization compared with all baseline models. Decision curve analysis confirmed its higher net clinical benefit across threshold probabilities. The model identified eight dominant predictors—cumulative anthracycline dose, LVEF, QTc interval, lactate dehydrogenase, creatinine, glucose, hypertension, and platelet count—that collectively reflected myocardial contractility, electrophysiological stability, and systemic metabolic stress. Correlation and clustering analyses revealed that high-risk patients exhibited concurrent QTc prolongation, metabolic disturbance, and LVEF decline, defining a distinct cardiometabolic injury phenotype. These findings highlight TabNet’s ability to uncover complex feature interactions while maintaining transparent and clinically interpretable outputs. Conclusions: The TabNet-based multidimensional model provides an accurat

FAQs

What clinical data are used to build the TabNet prediction model for DIC?

The model integrates routinely collected multidimensional inputs including clinical, biochemical, electrocardiographic, and echocardiographic parameters.

How does TabNet compare with baseline models in predicting doxorubicin-induced cardiotoxicity?

TabNet achieves the best overall predictive performance in validation, with higher discrimination, calibration, and generalization than logistic regression, decision tree, random forest, gradient boosting machine, and XGBoost.

Which factors are identified as the dominant predictors of DIC?

Eight dominant predictors are highlighted: cumulative anthracycline dose, LVEF, QTc interval, lactate dehydrogenase, creatinine, glucose, hypertension, and platelet count.

Sep 30, 2026

Uploaded by Olivia Brown