Explainable CNN–LSTM Framework for Heart Disease Risk Prediction
Keywords:
CNN–LSTM, Deep learning, Explainable AI, Heart disease prediction, LIME, SHAPAbstract
Heart disease remains one of the top causes of mortality worldwide, making early and accurate risk prediction vital for modern healthcare systems. Although deep learning techniques have demonstrated strong predictive capability, many existing approaches lack interpretability, limiting their practical adoption in clinical environments. This work proposes an explainable hybrid CNN–LSTM framework for heart disease risk prediction that balances predictive performance with model transparency. The CNN component automatically extracts meaningful feature representations from clinical data, while the LSTM layer captures sequential dependencies and hidden relationships among patient attributes. To improve interpretability, SHAP and LIME were integrated to explain the model’s logic, giving doctors both a big-picture view of how it thinks and a case- by-case breakdown for individual patients. The proposed framework is evaluated using the UCI Heart Disease dataset and a large-scale cardiovascular dataset containing approximately 70,000 patient records. Experimental results demonstrate that the proposed framework achieves improved predictive performance compared to conventional machine learning approaches while maintaining strong interpretability. Statistical significance testing and cross-validation further confirm the reliability and consistency of the obtained results. In addition, external validation experiments demonstrate improved generalization capability across datasets with varying characteristics. The proposed framework not only predicts heart disease risk effectively but also highlights important contributing clinical factors, thereby improving transparency, clinical trust, and suitability for real-world healthcare decision support systems.
References
R. Kumar, S. Garg, R. Kaur, M. G. Johar, S. Singh, S. V. Menon, P. Kumar, A. M. Hadi, S. A. Hasson, and J. Lozanović, “A comprehensive review of machine learning for heart disease prediction: Challenges, trends, ethical considerations, and future directions,” Frontiers in Artificial Intelligence, vol. 8, Art. no. 1583459, May 2025.
V. V. Karna, V. R. Karna, V. Janamala, V. K. Devana, V. R. Ch, and A. B. Tummala, “A comprehensive review on heart disease risk prediction using machine learning and deep learning algorithms,” Archives of Computational Methods in Engineering, vol. 32, no. 3, pp. 1763–1795, Apr. 2025.
U. K. Lilhore, S. Simaiya, M. Khan, R. Alroobaea, A. M. Baqasah, M. Alsafyani, and A. Alhazmi, “A deep learning approach for heart disease detection using a modified multiclass attention mechanism with BiLSTM,” Scientific Reports, vol. 15, no. 1, Art. no. 25273, Jul. 2025.
H. El-Sofany, B. Bouallegue, and Y. M. El-Latif, “A proposed technique for predicting heart disease using machine learning algorithms and an explainable AI method,” Scientific Reports, vol. 14, no. 1, Art. no. 23277, Oct. 2024.
G. Keerthiga, V. Pavan, M. J. Venu, and J. S. Jeyanathan, “A robust heart disease prediction system using hybrid deep neural networks,” in Sustainable Materials and Technologies in VLSI and Information Processing. Boca Raton, FL, USA: CRC Press, 2025, pp. 276–281.
A. Darolia, R. S. Chhillar, M. Alhussein, S. Dalal, K. Aurangzeb, and U. K. Lilhore, “Enhanced cardiovascular disease prediction through self-improved Aquila optimized feature selection in quantum neural network & LSTM model,” Frontiers in Medicine, vol. 11, Art. no. 1414637, Jun. 2024.
A. Almulihi, H. Saleh, A. M. Hussien, S. Mostafa, S. El-Sappagh, K. Alnowaiser, A. A. Ali, and M. R. Hassan, “Ensemble learning based on hybrid deep learning model for heart disease early prediction,” Diagnostics, vol. 12, no. 12, Art. no. 3215, Dec. 2022.
S. M. Ganie, P. K. Pramanik, and Z. Zhao, “Ensemble learning with explainable AI for improved heart disease prediction based on multiple datasets,” Scientific Reports, vol. 15, no. 1, Art. no. 13912, Apr. 2025.
M. Alsarori and M. H. Sulaiman, “Integrated deep learning for cardiovascular risk assessment and diagnosis: An evolutionary mating algorithm-enhanced CNN-LSTM,” MethodsX, vol. 15, Art. no. 103466, Dec. 2025.
P. Shah, M. Shukla, N. H. Dholakia, and H. Gupta, “Predicting cardiovascular risk with hybrid ensemble learning and explainable AI,” Scientific Reports, vol. 15, no. 1, Art. no. 17927, May 2025.
A. Awasthi and N. Goel, “Phishing website prediction: A comparison of machine learning techniques,” in Data Intelligence and Cognitive Informatics: Proceedings of ICDICI 2020. Singapore: Springer, 2021, pp. 637–650.
D. R. Hussein, A. S. Alhumaima, H. Alkattan, and M. Abotaleb, “Performance evaluation of logistic regression, random forest, and SVM models in heart disease prediction,” Journal of Transactions in Systems Engineering, vol. 4, no. 1, pp. 522–537, 2026.
M. M. Hossain, M. S. Ali, M. M. Ahmed, M. R. Rakib, M. A. Kona, S. Afrin, M. K. Islam, M. M. Ahsan, R. S. M. Raj, and M. H. Rahman, “Cardiovascular disease identification using a hybrid CNN-LSTM model with explainable AI,” Informatics in Medicine Unlocked, vol. 42, Art. no. 101370, 2023.
S. Al Gharib, J. Charafeddine, F. Dornaika, and S. Haddad, “Hybrid learning framework for explainable cardiovascular disease detection,” IEEE Access, early access, Jul. 2025.
S. Das, M. Sultana, S. Bhattacharya, D. Sengupta, and D. De, “XAI–reduct: Accuracy preservation despite dimensionality reduction for heart disease classification using explainable AI,” The Journal of Supercomputing, vol. 79, no. 16, pp. 18167–18197, Nov. 2023.
G. Sunilkumar and P. Kumaresan, “Deep learning and transfer learning in cardiology: A review of cardiovascular disease prediction models,” IEEE Access, vol. 12, pp. 193365–193386, Dec. 2024.
M. A. Talukder, A. S. Talaat, and M. Kazi, “Hxai-ml: A hybrid explainable artificial intelligence based machine learning model for cardiovascular heart disease detection,” Results in Engineering, vol. 25, Art. no. 104370, Mar. 2025.
A. M. Salih, I. B. Galazzo, P. Gkontra, K. Lekadir, G. Slabaugh, and J. Martinez-Miranda, “A review of evaluation approaches for explainable AI with applications in cardiology,” Artificial Intelligence Review, vol. 57, Art. no. 240, 2024.
S. Lipsa, R. K. Dash, S. Debdas, K. Cengiz, P. Kumar, and N. Pal, “Enhancing cardiac disease prediction with explainable bidirectional LSTM,” Scientific Reports, vol. 15, no. 1, Art. no. 41241, Nov. 2025.
S. Dhandapani, H. Somasundaram, and T. Angamuthu, “Hybrid deep learning framework for heart disease prediction using ECG signal images,” Scientific Reports, vol. 15, no. 1, Art. no. 33922, Sep. 2025.
