Abstract :

Heart Failure (HF) Remains A Leading Cause Of Morbidity And Mortality Worldwide, And Early, Accurate Classification Of Patient Risk Is Essential For Timely Clinical Intervention. This Paper Presents An Optimized Machine Learning Framework For Predicting The Classification Of Heart Failure Patients Using Structured Clinical Record Data. The Proposed Approach Integrates Data Preprocessing, Feature Selection, And Hyperparameter Optimization Applied To Multiple Classifiers, Including Random Forest, Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), And Logistic Regression. Key Clinical Features Analyzed Include Age, Ejection Fraction, Serum Creatinine, Serum Sodium, Platelet Count, And Comorbidity Indicators Such As Diabetes, Anaemia, And Hypertension. Hyperparameters Are Tuned Using Grid Search And Bayesian Optimization To Maximize Predictive Performance While Reducing Overfitting. Models Are Evaluated Using Accuracy, Precision, Recall, F1-score, And AUC-ROC. Experimental Analysis Indicates That The Optimized XGBoost Model Achieves The Strongest Overall Classification Performance, With An Accuracy Of Approximately 96%, Outperforming Nonoptimized Baseline Models And Demonstrating The Practical Value Of Hyperparameter Optimization For Clinical Decision Support In Heart Failure Prediction.

Published:

21-9-2026

Issue:

Vol. 26 No. 9 (2026)

Page Nos:

297 - 302

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite