Lightweight Machine Learning Models For Large-Scale Heart Disease Prediction In Resource-Constrained Healthcare Environments

MR. Abhijit Sanjay Shinde; Dr. Shamkumar B Chavan

doi:10.29284/nfn3zk91

Authors

MR. Abhijit Sanjay Shinde PhD scholar, Shivaji University, Kolhapur, Maharashtra, India
Dr. Shamkumar B Chavan HoD, School of Engineering and Technology, Shivaji University Kolhapur, Maharashtra, India

DOI:

https://doi.org/10.29284/nfn3zk91

Keywords:

Heart Disease Prediction; Lightweight Machine Learning; Support Vector Machine (SVM); Resource-Constrained Healthcare; Large-Scale Data Analytics; Clinical Decision Support Systems.

Abstract

Cardiovascular disease (CVD) continues to be one of the leading causes of death globally, and especially in lower-resource regions with limited access to advanced diagnostic infrastructure. Though deep learning methods achieved strong predictive performance, their computational complexity limits their use in resource-sensitive healthcare settings. This study is focused on comparative evaluation of lightweight ML models for heart disease prediction in large sets, achieving efficiency, scalability and probable online applicable performance. This study constructs a dataset of 78,812 instances with sample level augmentation based on publicly available heart disease records. We implemented three classifiers — Logistic Regression, Decision Tree and Support Vector Machine on a low-complexity preprocessing pipeline combining feature selection and normalization. Model performance is assessed by accuracy, precision, recall, F1-score, confusion matrix analysis and receiver operating characteristic–area under the curve (ROC–AUC). The experimental results show that the Support Vector Machine model, with an accuracy of 90.3% and ROC–AUC score of 0.934, provides the best performance while computationally efficient. Logistic Regression and Decision Tree models also show comparably performance with lower complexity. Moreover, a graphical user interface is designed to validate the real-time prediction capability. These findings emphasize the potential of lightweight machine learning methods to serve as practical and scalable decision-support tools for predicting heart disease in low-resource healthcare environments.

References

[1] World Heart Federation, World Heart Report 2023, World Heart Federation, Geneva, Switzerland, 2023.

[2] D. Dua and C. Graff, “Heart Disease,” UCI Machine Learning Repository, University of California, Irvine, CA, USA, 1988. [Online]. Available: https://archive.ics.uci.edu/ml/datasets/Heart+Disease

[3] A. A. Ahmad, M. M. Hasan, and S. Rahman, “Prediction of heart disease based on machine learning algorithms,” Journal of Healthcare Engineering, vol. 2023, Article ID 6692048, 2023.

[4] K. Karthick, S. Srinivasan, and R. Manikandan, “Implementation of a heart disease risk prediction model using machine learning techniques,” Healthcare, vol. 10, no. 3, pp. 1–15, 2022.

[5] M. Ozcan, “A classification and regression tree algorithm for heart disease prediction and rule extraction,” Biomedical Signal Processing and Control, vol. 79, Article no. 104057, 2023.

[6] G. Ambrish, “Logistic regression technique for prediction of cardiac disease using UCI dataset,” Materials Today: Proceedings, vol. 62, pp. 6463–6467, 2022.

[7] S. M. Muthukumari, “The pivotal role of edge computing with machine learning and its impact on healthcare,” in Edge Computing and Machine Learning in Healthcare Applications, Hershey, PA, USA: IGI Global, 2022, pp. 1–18.

[8] N. Biswas, A. Roy, and S. Dutta, “Machine learning-based model to predict heart disease,” Computational Intelligence and Neuroscience, vol. 2023, Article ID 8845126, 2023.

[9] R. Alizadehsani et al., “A database for using machine learning and data mining techniques for coronary artery disease diagnosis,” Scientific Data, vol. 6, no. 227, 2019.

[10] S. Palaniappan and R. Awang, “Intelligent heart disease prediction system using data mining techniques,” International Journal of Computer Science and Network Security, vol. 8, no. 8, pp. 343–350, 2008.

[11] A. Javeed et al., “An efficient learning system based on support vector machines for heart disease prediction,” IEEE Access, vol. 7, pp. 181876–181887, 2019.

[12] M. Ozcan, “Heart disease prediction using decision tree-based classification and rule extraction,” Biomedical Signal Processing and Control, vol. 68, 2021.

[13] A. Liaqat et al., “An intelligent ensemble-based heart disease prediction system using Random Forest,” Applied Sciences, vol. 11, no. 7, 2021.

[14] A. M. Hasan et al., “Feature selection-based machine learning approach for heart disease prediction,” Computers in Biology and Medicine, vol. 137, 2021.

[15] K. Polat and S. Güneş, “Medical decision support system based on artificial immune recognition for heart disease diagnosis,” Expert Systems with Applications, vol. 38, no. 3, pp. 2512–2516, 2011.

[16] P. Verma et al., “Deep learning-based models for cardiovascular disease prediction: A review,” Journal of Biomedical Informatics, vol. 127, 2022.

[17] N. M. Basha et al., “Lightweight machine learning models for healthcare prediction in resource-limited environments,” Healthcare Analytics, vol. 3, 2023.

[18] S. Bashir, U. Qamar, and F. H. Khan, “IntelliHealth: A medical decision support application using a novel weighted decision tree,” Journal of King Saud University – Computer and Information Sciences, vol. 33, no. 6, pp. 651–660, 2021.

[19] S. Rani and R. K. Kumar, “Predictive modeling of heart disease using machine learning techniques,” International Journal of Computer Applications, vol. 181, no. 18, pp. 1–6, 2018.

[20] M. A. Jabbar, P. Chandra, and B. L. Deekshatulu, “Heart disease prediction system using associative classification and genetic algorithm,” Journal of Information Technology and Software Engineering, vol. 6, no. 2, pp. 1–5, 2016.

[21] M. Rahman, M. M. Islam, and H. A. Rahman, “A machine learning approach for heart disease prediction using ensemble techniques,” Applied Sciences, vol. 10, no. 22, Article no. 8340, 2020.

[22] A. S. Albahri et al., “Systematic review of machine learning techniques for heart disease diagnosis,” Applied Sciences, vol. 10, no. 15, Article no. 5134, 2020.

[23] P. K. Anooj, “Clinical decision support system for heart disease diagnosis using hybrid machine learning techniques,” Journal of Biomedical Informatics, vol. 116, Article no. 103703, 2021.