A Hybrid CNN-SVM Model with Attention Mechanisms for Chronic Kidney Disease Prediction

Ederi Felicia Azibanigha; May Stow; Samuel Apigi Ikirigo

doi:10.56201/ijcsmt.vol.12.no3.2026.pg55.73

📄 Download Paper

A Hybrid CNN-SVM Model with Attention Mechanisms for Chronic Kidney Disease Prediction

Ederi Felicia Azibanigha, May Stow, Samuel Apigi Ikirigo

Abstract

Chronic Kidney Disease represents a significant global health challenge, requiring early and accurate diagnosis to prevent progression to end-stage renal failure. This study addresses the limitations of traditional diagnostic methods and the "black-box" nature of standard deep learning by developing an explainable, attention-driven hybrid Convolutional Neural Network- Support Vector Machine (CNN-SVM) framework. The methodology integrates 1D-Convolutional layers with a custom attention mechanism, which serves as a dual-purpose tool for both automated feature extraction and Explainable AI . By quantifying the importance of specific clinical variables, the model moves beyond simple prediction to offer transparent, justifiable diagnostic insights. The architecture is completed by a Support Vector Machine that replaces the final Softmax layer to optimize decision boundaries through structural risk minimization, while SMOTE-based class balancing ensures robustness against dataset imbalances. The research findings demonstrate state-of-the-art performance, with the hybrid model achieving a benchmark accuracy, precision, recall, and F1-score of 100% (1.0000) on the test set, significantly outperforming a standalone CNN baseline of 93.33%. A core contribution of this work is the visualization of feature importance, which identified key clinical biomarkers— such as hemoglobin, specific gravity, and serum creatinine—as primary drivers for prediction, thereby bridging the gap between machine learning outputs and clinical intuition. These findings are significant because they provide a robust, transparent, and low-cost diagnostic utility— deployed via a Flask web interface—that offers clinicians a reliable and explainable "second opinion" for early CKD detection, particularly in resource-limited settings.

Keywords

Chronic Kidney DiseaseConvolutional Neural NetworkSupport Vector MachineAttention MechanismClinical Decision SupportPredictive Modeling

References

Aljarrah, I. A., et al. (2022). A hybrid deep learning model for predicting chronic kidney disease. Computers in Biology and Medicine, 149, 106024. Almasoud, M., & Ward, T. E. (2021). Detection of chronic kidney disease using machine learning algorithms with least number of predictors. International Journal of Environmental Research and Public Health, 18(23), 12342. Amrollahi, F., et al. (2023). Challenges in deploying clinical decision support systems: a review of usability and scalability. International Journal of Medical Informatics, 170, 104971. Chen, Y., et al. (2024). A CNN-SVM hybrid model with attention mechanism for enhanced chronic kidney disease prediction. Journal of Biomedical Informatics, 151, 104611. Esteva, A., et al. (2021). Deep learning-enabled medical computer vision. NPJ Digital Medicine, 4(1), 1-9. GBD Chronic Kidney Disease Collaboration. (2020). Global, regional, and national burden of chronic kidney disease, 1990–2017: a systematic analysis for the Global Burden of Disease Study 2017. The Lancet, 395(10225), 709-733. Hingwala, J., et al. (2023). Addressing racial and ethnic disparities in chronic kidney disease risk prediction models. Journal of the American Society of Nephrology, 34(4), 587-599. Inker, L. A., et al. (2021). New creatinine- and cystatin C–based equations to estimate GFR without race. New England Journal of Medicine, 385(19), 1737-1749. Kaze, A. D., et al. (2022). Burden of chronic kidney disease on the African continent: a systematic review and meta-analysis. BMC Nephrology, 23(1), 1-12. Kumar, A., et al. (2022). Web-based deep learning tools for non-invasive diagnostic support in dermatology and ophthalmology. NPJ Digital Medicine, 5(1), 1-10. Levin, A., et al. (2021). Executive summary of the KDIGO 2021 Clinical Practice Guideline for the Management of Blood Pressure in Chronic Kidney Disease. Kidney International, 99(3), 559-569. Liyanage, T., et al. (2022). The global burden of chronic kidney disease: estimates from the Global Burden of Disease Study 2019. The Lancet, 400(10345), 786-799. Norouzi, J., et al. (2021). A comprehensive review of machine learning techniques for chronic kidney disease diagnosis. Artificial Intelligence in Medicine, 118, 102123. Raj, A. S., & Sivasangari, A. (2024). A Flask-based web framework for deploying machine learning models in healthcare. Journal of Web Engineering, 23(2), 145-162. Salekin, A., & Stankovic, J. (2020). Detection of chronic kidney disease using selective feature ranking and ensemble classifiers. IEEE Journal of Biomedical and Health Informatics, 24(9), 2547-2554. Shilo, S., et al. (2023). A hybrid deep learning framework for predictive analytics in healthcare. Nature Communications, 14(1), 1-12. Stevens, P. E., & Levin, A. (2020). Evaluation and management of chronic kidney disease: synopsis of the KDIGO 2012 clinical practice guideline. Annals of Internal Medicine, 158(11), 825-830. Swapna, G., et al. (2021). A deep learning approach for chronic kidney disease prediction using clinical data. IEEE Access, 9, 165012-165022. United States Renal Data System. (2023). 2023 USRDS Annual Data Report: Epidemiology of Kidney Disease in the United States. National Institutes of Health, National Institute of Diabetes and Digestive and Kidney Diseases. Vaswani, A., et al. (2023). Attention is all you need: The persistent impact of transformer architectures. Advances in Neural Information Processing Systems, 36. Vollmer, S., et al. (2024). The role of explainable AI in clinical decision support: a systematic review. The Lancet Digital Health, 6(2), e123-e135. Wang, L., et al. (2022). Deep learning for precise prediction of chronic kidney disease progression. IEEE Transactions on Neural Networks and Learning Systems. Zebari, D. A., et al. (2023). A systematic review of support vector machines in healthcare analytics. Healthcare Analytics, 3, 100183.

A Hybrid CNN-SVM Model with Attention Mechanisms for Chronic Kidney Disease Prediction

Abstract

Keywords

References

More Articles from INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND MATHEMATICAL THEORY