Call For Paper - Upcoming Conferences
Research Article | Open Access | Download PDF
Volume 13 | Issue 5 | Year 2026 | Article Id. IJECE-V13I5P101 | DOI : https://doi.org/10.14445/23488549/IJECE-V13I5P101

A Hybrid Deep Learning Framework for Predicting Heart Disease: Combining CNN, LSTM, and Attention Mechanisms

Rasitha Banu Gul Mohamed, Sasikala, Maha Yousif Rizgalla sulieman, Hanan Abdullah Almaimani, Wafa Hetany, Faiza Abdalla Saeed Khiery

Received Revised Accepted Published
04 Feb 2026 03 Mar 2026 02 Apr 2026 27 May 2026

Citation :

Rasitha Banu Gul Mohamed, Sasikala, Maha Yousif Rizgalla sulieman, Hanan Abdullah Almaimani, Wafa Hetany, Faiza Abdalla Saeed Khiery, "A Hybrid Deep Learning Framework for Predicting Heart Disease: Combining CNN, LSTM, and Attention Mechanisms," International Journal of Electronics and Communication Engineering, vol. 13, no. 5, pp. 1-12, 2026. Crossref, https://doi.org/10.14445/23488549/IJECE-V13I5P101

Abstract

Heart Disease (HD) continues to be among the top causes of death globally, and there is a need for precise and timely prediction models to aid clinical decision-making. This research suggests a new hybrid deep learning model by combining Convolutional Neural Networks (CNN) with Long Short-Term Memory (LSTM) networks to enhance the predictive accuracy of heart disease diagnosis. The model utilizes CNNs to extract spatial features from structured and time-varying clinical information, while LSTM and Bi-directional LSTM (Bi-LSTM) layers extract temporal dependencies and sequential patterns. Three configurations of architectures were tested: (i) CNN with 4 convolutional layers and a 2-layer LSTM with 64 units, (ii) CNN with 3 convolutional layers (32 filters) and a Bi-LSTM (64 units), and (iii) CNN with 5 convolutional layers (64 filters) and a single LSTM layer with 128 units. The performances were evaluated with regard to typical metrics accuracy, precision, recall, F1-score, and ROC-AUC score. Results showed that the Bi-LSTM-based setup obtained the best performance with an ROC-AUC value of 0.94 and high values for all the other measures. The results indicate that an equally balanced model structure with moderate complexity and bidirectional temporal learning yields the best predictive performance. The hybrid model holds the promise to be incorporated into clinical decision support systems to detect heart disease more accurately and in a timely fashion. This strategy is involved in the creation of intelligent diagnosis tools that can assist physicians in the identification of risky patients and in mitigating the burden of cardiovascular disease worldwide.

Keywords

Heart Disease Prediction, Hybrid Model, Convolutional Neural Networks, Long Short Term Memory, Attention Mechanisms.

References

  1. Saleh Mahdi Muhammed, Ghassan Abdul-Majeed, and Mahmoud Shuker Mahmoud, “Early Prediction of Chronic Heart Disease based on Electronic Triage Dataset by using Machine Learning,” 2023 Al-Sadiq International Conference on Communication and Information Technology (AICCIT), Al-Muthana, Iraq, pp. 131-136, 2023.
    [    CrossRef] [Google Scholar] [Publisher Link]
  2. Elham Nasarian et al., “AI Framework for Early Diagnosis of Coronary Artery Disease: An Integration of Borderline SMOTE, Autoencoders and Convolutional Neural Networks Approach,” arXiv preprint, pp. 1-6, 2023.
    [    CrossRef] [Google Scholar] [Publisher Link]
  3. Muhammad Raheel Khan et al., “Comprehensive Analysis of Cardiovascular Diseases: Symptoms, Diagnosis, and AI Innovations,” Bioengineering, vol. 11, no. 12, pp. 1-26, 2024.
    [    CrossRef] [Google Scholar] [Publisher Link]
  4. Benjamin A. Satterfield, Ozan Dikilitas, and Iftikhar J. Kullo, “Leveraging the Electronic Health Record to Address the COVID-19 Pandemic,” Mayo Clinic Proceedings, vol. 96, no. 6, pp. 1592-1608. 2021.
    [    CrossRef] [Google Scholar] [Publisher Link]
  5. Serdar Bozyel et al., “Artificial Intelligence-Based Clinical Decision Support Systems in Cardiovascular Diseases,” Anatolian Journal of Cardiology, 28, no. 2, pp. 74-86, 2024.
    [    CrossRef] [Google Scholar] [Publisher Link]
  6. Rohit Bharti et al., “Prediction of Heart Disease using a Combination of Machine Learning and Deep Learning,” Computational Intelligence and Neuroscience, vol. 2021, no. 1, pp. 1-11, 2021.
    [    CrossRef] [Google Scholar] [Publisher Link]
  7. Mohammad Farah, and Saad Al-Ahmadi, “WT-CNN: A Hybrid Machine Learning Model for Heart Disease Prediction,” Mathematics, vol. 11, no. 22, pp. 1-15, 2023.
    [    CrossRef] [Google Scholar] [Publisher Link]
  8. Zakaria K. D. Alkayyali, Syahril Anuar Bin Idris, and Samy S. Abu-Naser, “A Systematic Literature Review of Deep and Machine Learning Algorithms in Cardiovascular Diseases Diagnosis,” Journal of Theoretical and Applied Information Technology, 101, no. 4, pp. 1353-1365, 2023.
    [    Google Scholar] [Publisher Link]
  9. Tawsifur Rahman et al., “Deep Learning Technique for Congenital Heart Disease Detection using Stacking-based CNN-LSTM Models from Fetal Echocardiogram: A Pilot Study,” IEEE Access, vol. 11, pp. 110375-110390, 2023.
    [    CrossRef] [Google Scholar] [Publisher Link]
  10. R. Archana, and P.S. Eliahim Jeevaraj, “Deep Learning Models for Digital Image Processing: A Review,” Artificial Intelligence Review, vol. 57, pp. 1-33, 2024.
    [    CrossRef] [Google Scholar] [Publisher Link]
  11. V.K. Sudha, and D. Kumar, “Hybrid CNN and LSTM Network for Heart Disease Prediction,” SN Computer Science, vol. 4, 2023.
    [    CrossRef] [Google Scholar] [Publisher Link]
  12. Muthu Ganesh Veerabaku et al., “Intelligent Bi-LSTM with Architecture Optimization for Heart Disease Prediction in WBAN through Optimal Channel Selection and Feature Selection,” Biomedicines, vol. 14, no. 11, pp. 1-26, 2023.
    [    CrossRef] [Google Scholar] [Publisher Link]
  13. Md Maruf Hossain et al., “Cardiovascular Disease Identification using a Hybrid CNN-LSTM Model with Explainable AI,” Informatics in Medicine Unlocked, vol. 42, pp. 1-15, 2023.
    [    CrossRef] [Google Scholar] [Publisher Link]
  14. Abdulwahab Ali Almazroi, “A Clinical Decision Support System for Heart Disease Prediction using Deep Learning,” IEEE Access, vol. 11, pp. 61646-61659, 2023.
    [    CrossRef] [Google Scholar] [Publisher Link]
  15. Girish S. Bhavekar, and Agam Das Goswami, “A Hybrid Model for Heart Disease Prediction using Recurrent Neural Network and Long Short Term Memory,” International Journal of Information Technology, vol. 14, pp. 1781-1789, 2022.
    [    CrossRef] [Google Scholar] [Publisher Link]
  16. Umesh Kumar Lilhore et al., “An Attention‐Driven Hybrid Deep Neural Network for Enhanced Heart Disease Classification,” Expert Systems, vol. 42, no. 2, 2025.
    [    CrossRef] [Google Scholar] [Publisher Link]
  17. Xin Shi et al., “Congestive Heart Failure Detection based on Attention Mechanism-Enabled Bi-Directional Long Short-Term Memory Model in the Internet of Medical Things,” Journal of Industrial Information Integration, vol. 30, 2022.
    [    CrossRef] [Google Scholar] [Publisher Link]
  18. Mubarak Albathan, “Hybrid LSTM and Deep Belief Networks with Attention Mechanism for Accurate Heart Attack Data Analytics,” International Journal of Computer Science & Network Security, vol. 24, no. 10, pp. 1-16, 2024.
    [    Google Scholar] [Publisher Link]
  19. Ran Hao et al., “A Hybrid CNN-Transformer Model for Heart Disease Prediction Using Life History Data,” 2025 8th International Symposium on Big Data and Applied Statistics (ISBDAS), Guangzhou, China, pp. 833-837, 2025.
    [    CrossRef] [Google Scholar] [Publisher Link]
  20. Prashant Kumar Shrivastava et al., “HCBiLSTM: A Hybrid Model for Predicting Heart Disease using CNN and BiLSTM Algorithms,” Measurement: Sensors, vol. 25, pp. 1-7, 2023.
    [    CrossRef] [Google Scholar] [Publisher Link]
  21. Atta Ur Rahman et al., “Enhancing Heart Disease Prediction using a Self-Attention-Based Transformer Model,” Scientific Reports, vol. 14, pp. 1-13, 2024.
    [    CrossRef] [Google Scholar] [Publisher Link]
  22. Yakub Kayode Saheed et al., “Modified Bi-Directional Long Short-Term Memory and Hyperparameter Tuning of Supervised Machine Learning Models for Cardiovascular Heart Disease Prediction in Mobile Cloud Environment,” Biomedical Signal Processing and Control, vol. 94, 2024.
    [    CrossRef] [Google Scholar] [Publisher Link]
  23. B. Ramesh, and Kuruva Lakshmanna, “A Novel Early Detection and Prevention of Coronary Heart Disease Framework Using Hybrid Deep Learning Model and Neural Fuzzy Inference System,” IEEE Access, vol. 12, pp. 26683-26695, 2024.
    [    CrossRef] [Google Scholar] [Publisher Link]
  24. Dhadkan Shrestha, “Advanced Machine Learning Techniques for Predicting Heart Disease: A Comparative Analysis Using the Cleveland Heart Disease Dataset,” Applied Medical Informatics, vol. 46, no. 3, pp. 91-102, 2024.
    [    Google Scholar] [Publisher Link]
  25. Padmakumari Pitchal, Shanthi Ponnusamy, and Vidivelli Soundararajan, “Heart Disease Prediction: Improved Quantum Convolutional Neural Network and Enhanced Features,” Expert Systems with Applications, vol. 249, 2024.
    [    CrossRef] [Google Scholar] [Publisher Link]
  26. D. Cenitta et al., “Ischemic Heart Disease Prognosis: A Hybrid Residual Attention-Enhanced LSTM Model,” IEEE Access, vol. 13, pp. 4281-4289, 2025.
    [    CrossRef] [Google Scholar] [Publisher Link]
  27. Li Li, Xi Chen, and Sanjun Hu, “Application of an End-to-End Model with Self-Attention Mechanism in Cardiac Disease Prediction,” Frontiers in Physiology, vol. 14, pp. 1-24, 2024.
    [    CrossRef] [Google Scholar] [Publisher Link]