Heart disease prediction using logistic regression
*S. Baby LathaCorresponding authorbabylatha.as@bhc.edu.inDepartment of Actuarial ScienceBishop Heber College (Affiliated to Bharathidasan University)Trichy, Tamil Nadu, 620017, IndiaView full profile → , R. Abinayaabinayarajagopal2@gmail.comDepartment of Actuarial ScienceBishop Heber College (Affiliated to Bharathidasan University)Trichy, Tamil Nadu, 620017, IndiaView full profile →
* Corresponding author · click or hover a name for details
- Received:
- 02 Jun 2025
- Published Online:
- 08 May 2026
- Article type:
- Research Article
- Language:
- EN
- Article no.:
- JSMS-1587
- Pages:
- 787–802
Abstract
Heart disease remains a major global health concern and one of the leading causes of mortality, emphasizing the importance of early detection and reliable risk assessment. This research investigates the effectiveness of Logistic Regression (LR) in predicting heart disease risk using the Heart Disease Statlog dataset. Various clinical and demographic parameters including age, cholesterol levels, exercise-induced angina, and ST depression were examined to build a predictive model. The dataset was subjected to preprocessing, feature selection, and exploratory data analysis (EDA) before model training. Evaluation metrics such as accuracy (92.59%), precision (94.7%), recall (85.7%), and AUC-ROC (0.95) demonstrated strong model performance. The study underscores the interpretability of LR for medical diagnosis while recognizing its limitations in modeling complex non-linear patterns. Future studies may enhance prediction accuracy by employing advanced machine learning techniques and integrating real-time health monitoring systems. Overall, the findings support improvements in early disease detection, healthcare decision-making, and actuarial risk analysis in the health insurance sector.
Keywords
Subject Classifications
References
[1] R. Torthi, A. D. K. Marapatla, S. Mande, H. K. V. Gadiraju, and C. Kanumuri, “Heart disease prediction using random forest based hybrid optimization algorithms,” Int. J. Intell. Eng. Syst., vol. 17, no. 2 (2024).
[2] S. Hossain, M. K. Hasan, M. O. Faruk, N. Aktar, R. Hossain, and K. Hossain, “Machine learning approach for predicting cardiovascular disease in Bangladesh: Evidence from a cross-sectional study in 2023,” BMC Cardiovasc. Disord., vol. 24, no. 1, p. 214 (2024).
[3] P. Deepika, “Heart disease prediction using classification with different decision tree techniques,” Int. J. Eng. Res. Technol., vol. 12, no. 5, pp. 45–50 (2023).
[4] A. K. Pandey, P. Pandey, K. L. Jaiswal, and A. K. Sen, “A heart disease prediction model using decision tree,” IOSR J. Comput. Eng., vol. 25, no. 4, pp. 10–17 (2023).
[5] S. Narayan and J. Gobal, “Optimal decision tree fuzzy rule-based classifier for heart disease prediction using improved cuckoo search algorithm,” Int. J. Intell. Eng. Syst., vol. 16, no. 3, pp. 112–121 (2023).
[6] Z. Khan, S. Anwar, and G. Sikandar, “Heart disease prediction using hybrid random forest and linear model,” Int. J. Emerg. Eng. Technol., vol. 2, no. 1, pp. 6–12 (2023).
[7] M. Rababa, H. Alshraideh, and J. Abu-Khalaf, “Evaluating the accuracy of the CDC heart disease survey data using support vector machines,” Comput. Biol. Med., vol. 153, p. 106512 (2023).
[8] N. M. Lutimath, N. Sharma, and B. K. Byregowda, “Prediction of heart disease using random forest,” in Proc. 2021 Emerging Trends in Industry 4.0 (ETI 4.0), pp. 1–4 (May 2021).
[9] L. Yang, H. Wu, X. Jin, P. Zheng, S. Hu, X. Xu, W. Yu, and J. Yan, “Study of cardiovascular disease prediction model based on random forest in eastern China,” Sci. Rep., vol. 10, no. 1, p. 5245 (2020).
[10] S. Akila and S. Chandramathi, “A hybrid method for coronary heart disease risk prediction using decision tree and multi-layer perceptron,” Indian J. Sci. Technol., vol. 8, no. 34, pp. 1–7 (2015).
[11] V. Sabarinathan and V. Sugumaran, “Diagnosis of heart disease using decision tree,” Int. J. Res. Comput. Appl. Inf. Technol., vol. 2, no. 6, pp. 74–79 (2014).
[12] W. Wiharto, H. Kusnanto, and R. Widayanto, “Performance analysis of multiclass support vector machine classification for diagnosing coronary heart diseases,” Health Inform. J., vol. 21, no. 3, pp. 199–211 (2015).
[13] E. J. Benjamin, S. M. Al-Khatib, P. Desvigne-Nickens, A. Alonso, L. Djoussé, D. E. Forman, A. S. Go, P. G. Hylek, S. L. Johnson, J. M. Maddox, M. E. McCabe, J. P. Piccini, and E. Z. Soliman, “Research priorities in the secondary prevention of atrial fibrillation: A National Heart, Lung, and Blood Institute virtual workshop report,” J. Am. Heart Assoc., vol. 10, no. 16, p. e021566 (2021), doi: 10.1161/JAHA.121.021.
[14] M. A. Miah, M. M. Rahman, and S. Alam, “Comparative analysis of machine learning models for myocardial infarction prediction,” J. Biomed. Inform., vol. 136, p. 104198 (2023).
[15] B. Duraisamy, R. Sunku, K. Selvaraj, V. V. R. Pilla, and M. Sanikala, “Heart disease prediction using support vector machine,” Multidiscip. Sci. J., vol. 6, p. e2024ss0104 (2024).
[16] B. M. Hardas, M. G. Aush, and V. Raut, “Data-driven optimization strategies for enhanced cardiovascular risk assessment,” J. Stat. Manag. Syst. vol. 27, no. 2, pp. 315–325 (2024), doi: 10.47974/JSMS-1257
[17] S. B. Latha and S. Prettha, “Technology adoption alters the insurance industry’s competitive landscape in India,” in Generative AI Foundations, Developments, and Applications, IGI Global Scientific Publishing, pp. 219–250 (2025).
