Cardiovascular complications, particularly heart failure, remain a serious global health concern and contribute significantly to mortality rates. To reduce associated risks and improve survival outcomes, an effective early prediction mechanism is highly necessary. In this study, a predictive framework based on machine learning techniques is developed to identify potential heart failure cases. Four classification models—K-Nearest Neighbors (KNN), Random Forest, Support Vector Classifier (SVC), and Gradient Boosting Classifier—are implemented and compared. Prior to model training, the dataset undergoes sy
stematic preprocessing steps, including handling missing or inconsistent data, identifying the most influential features, and applying normalization techniques to ensure balanced model learning. The effectiveness of each classifier is assessed using performance indicators such as accuracy, precision, recall, and F1-measure. Comparative evaluation shows that KNN and Random Forest deliver more reliable and consistent prediction results than SVC and Gradient Boosting. The analysis indicates that ensemble learning strategies are particularly suitable for managing intricate medical datasets with multiple influencing factors. The final system acts as an intelligent clinical support tool, assisting healthcare practitioners in detecting high-risk patients early and enabling timely medical intervention and treatment planning.
Keywords
Heart Failure Prediction, Machine Learning, K-Nearest Neighbors (KNN), Random Forest, Support Vector Classifier (SVC), Gradient Boosting, Classification Algorithms, Medical Data Analysis, Predictive Modeling, Healthcare Analytics.
Conclusion
The results of the study indicate that machine learning methods are capable of accurately identifying heart failure cases. Among the tested approaches, K-Nearest Neighbors and Random Forest produced the best performance, each reaching an accuracy of 89%, reflecting strong reliability and effectiveness. The Support Vector Classifier achieved a comparable accuracy of 88%, whereas the Gradient Boosting Classifier recorded 86%. These outcomes highlight that both ensemble-based models and instance-driven algorithms are particularly suitable for this type of prediction task. In summary, data-oriented machine learning models offer dependable assistance for early detection, which can support clinical decisions and contribute to better patient care.
References
[1]Ananey-Obiri, D.; Sarku, E. Predicting the Presence of Heart Diseases Using Comparative Data Mining and Machine Learning Algorithms. Int. J. Comput. Appl. 2020, 176, 17–21.
[2]Drozdz, K.; Nabrdalik, K.; Kwiendacz, H.; Hendel, M.; Olejarz, A.; Tomasik, A.; Bartman, W.; Nalepa, J.; Gumprecht, J.; Lip, G.Y.H. Risk factors for cardiovascular disease in patients with metabolic-associated fatty liver disease: A machine learning approach. Cardiovasc. Diabetol. 2022, 21, 240.
[3]Gupta, A.; Kumar, R.; Singh Arora, H.; Raman, B. MIFH: A Machine Intelligence Framework for Heart Disease Diagnosis. IEEE Access 2020, 8, 14659–14674.
[4]Hasan, N.; Bao, Y. Comparing different feature selection algorithms for cardiovascular disease prediction. Health Technol. 2020, 11, 49–62.
[5] Manu Siddhartha Heart Disease Dataset (Comprehensive). Available online:https://ieeedataport.org/authors/manu-siddhartha (accessed on 12 November 2022).
[6] Rani, P.; Kumar, R.; Ahmed, N.M.O.S.; Jain, A. A Decision Support System for Heart Disease Prediction Based upon Machine Learning. J. Reliab. Intell. Environ. 2021, 7, 263–275.
[7] Tama, B.A.; Im, S.; Lee, S. Improving an Intelligent Detection System for Coronary Heart Disease Using a Two-Tier Classifier Ensemble. BioMed Res. Int. 2020, 2020, 9816142.
[8] Shah, D.; Patel, S.; Bharti, S.K. Heart Disease Prediction using Machine Learning Techniques. SN Comput. Sci. 2020, 1, 345
[9]Vembandasamy, K.; Sasipriya, R.; Deepa, E. Heart Diseases Detection Using Naive Bayes Algorithm. Int. J. Innov. Sci. Eng. Technol. 2015, 2, 441–444.
[10] Yilmaz, R.; Yagin, F.H. Early Detection of Coronary Heart Disease Based on Machine Learning Methods. Med. Rec. 2021, 4, 1–6.
How to Cite This Paper
A.Gowtham, Dr.S.Selvakani, Mrs.K.Vasumathi (2026). MACHINE LEARNING–BASED HEART FAILURE PREDICTION. International Journal of Computer Techniques, 13(2). ISSN: 2394-2231.
