A Deep Learning Framework for Heart Disease Prediction with Explainable Artificial Intelligence

Guardado en:
Bibliografiske detaljer
Udgivet i:Computers, Materials, & Continua vol. 86, no. 1 (2026), p. 1-21
Hovedforfatter: Muhammad Adil
Andre forfattere: Javaid, Nadeem, Ahmed, Imran, Ahmed, Abrar, Alrajeh, Nabil
Udgivet:
Tech Science Press
Fag:
Online adgang:Citation/Abstract
Full Text - PDF
Tags: Tilføj Tag
Ingen Tags, Vær først til at tagge denne postø!

MARC

LEADER 00000nab a2200000uu 4500
001 3280657485
003 UK-CbPIL
022 |a 1546-2218 
022 |a 1546-2226 
024 7 |a 10.32604/cmc.2025.071215  |2 doi 
035 |a 3280657485 
045 2 |b d20260101  |b d20261231 
100 1 |a Muhammad Adil  |u International Graduate School of AI, National Yunlin University of Science and Technology, Douliu, 64002, Taiwan 
245 1 |a A Deep Learning Framework for Heart Disease Prediction with Explainable Artificial Intelligence 
260 |b Tech Science Press  |c 2026 
513 |a Journal Article 
520 3 |a Heart disease remains a leading cause of mortality worldwide, emphasizing the urgent need for reliable and interpretable predictive models to support early diagnosis and timely intervention. However, existing Deep Learning (DL) approaches often face several limitations, including inefficient feature extraction, class imbalance, suboptimal classification performance, and limited interpretability, which collectively hinder their deployment in clinical settings. To address these challenges, we propose a novel DL framework for heart disease prediction that integrates a comprehensive preprocessing pipeline with an advanced classification architecture. The preprocessing stage involves label encoding and feature scaling. To address the issue of class imbalance inherent in the personal key indicators of the heart disease dataset, the localized random affine shadowsampling technique is employed, which enhances minority class representation while minimizing overfitting. At the core of the framework lies the Deep Residual Network (DeepResNet), which employs hierarchical residual transformations to facilitate efficient feature extraction and capture complex, non-linear relationships in the data. Experimental results demonstrate that the proposed model significantly outperforms existing techniques, achieving improvements of 3.26% in accuracy, 3.16% in area under the receiver operating characteristics, 1.09% in recall, and 1.07% in F1-score. Furthermore, robustness is validated using 10-fold cross-validation, confirming the model’s generalizability across diverse data distributions. Moreover, model interpretability is ensured through the integration of Shapley additive explanations and local interpretable model-agnostic explanations, offering valuable insights into the contribution of individual features to model predictions. Overall, the proposed DL framework presents a robust, interpretable, and clinically applicable solution for heart disease prediction. 
653 |a Cardiovascular disease 
653 |a Feature extraction 
653 |a Preprocessing 
653 |a Deep learning 
653 |a Classification 
653 |a Heart 
653 |a Machine learning 
653 |a Prediction models 
653 |a Explainable artificial intelligence 
653 |a Heart diseases 
700 1 |a Javaid, Nadeem  |u International Graduate School of AI, National Yunlin University of Science and Technology, Douliu, 64002, Taiwan 
700 1 |a Ahmed, Imran  |u School of Computing and Information Science, Anglia Ruskin University, Cambridge, CB11PT, UK 
700 1 |a Ahmed, Abrar  |u Department of Electrical and Computer Engineering, COMSATS University Islamabad, Islamabad, 44000, Pakistan 
700 1 |a Alrajeh, Nabil  |u Department of Biomedical Technology, College of Applied Medical Sciences, King Saud University, Riyadh, 11633, Saudi Arabia 
773 0 |t Computers, Materials, & Continua  |g vol. 86, no. 1 (2026), p. 1-21 
786 0 |d ProQuest  |t Publicly Available Content Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3280657485/abstract/embedded/BH75TPHOCCPB476R?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3280657485/fulltextPDF/embedded/BH75TPHOCCPB476R?source=fedsrch