Predicting the Classification of Heart Failure Patients Using Optimized Machine Learning Algorithms - Academic Research

Aug 4, 2026

Upload by Riley

Heart failure is a high-mortality condition that requires accurate survival prediction to enable timely clinical interventions. This study introduces an optimized machine learning framework based on Gradient Boosting Machine (GBM) combined with Adaptive Inertia Weight Particle Swarm Optimization (AIWPSO) to predict survival outcomes. A Kaggle clinical dataset with 299 patients is balanced using SMOTE, then refined via SelectKBest and Chi-square feature selection. AIWPSO tunes GBM hyperparameters by adaptively adjusting inertia weights, while model selection uses AIC and BIC to balance accuracy and complexity. The optimized GBM reaches 94% test accuracy, outperforming conventional ML approaches and supporting interpretable decision support in heart failure management.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages15

Reading Time38 min

AccessFree to download

Abstract

Index Terms

Abbreviations and Terms

Introduction

Related Background (CVD and Heart Failure)

Machine Learning for Clinical Prediction

Received 28 January 2025, accepted 5 February 2025, date of publication 11 February 2025, date of current version 19 February 2025. Digital Object Identifier 10.1109/ACCESS.2025.3541069 Predicting the Classification of Heart Failure Patients Using Optimized Machine Learning Algorithms MARZIA AHMED1,2, MOHD HERWAN SULAIMAN2,(Senior Member, IEEE), MD MARUF HASSAN1,3,(Member, IEEE), AND TOUHID BHUIYAN4 1Department of Software Engineering, Daffodil International University (DIU), Daffodil Smart City, Dhaka 1216, Bangladesh 2Faculty of Electrical and Electronics Engineering Technology, Universiti Malaysia Pahang Al-Sultan Abdullah (UMPSA), Pekan 26600, Malaysia 3Department of Computer Science and Engineering, Southeast University, Dhaka, Bangladesh 4 School of IT, Washington University of Science and Technology (WUST), Alexandria, VA 22314, USA Corresponding author: Marzia Ahmed ([ahmed.marzia32@gmail.com](ahmed.marzia32@gmail.com)) This work was supported by the School of IT, Washington University of Science and Technology (WUST), in Virginia, USA, Program for Scientific Publication. ABSTRACT Heart failure is a critical condition with a high mortality rate, making accurate survival prediction essential for timely interventions. This study proposes an optimized machine learning approach using Gradient Boosting Machine (GBM) and Adaptive Inertia Weight Particle Swarm Optimization (AIWPSO) to predict heart failure survival. The dataset, sourced from Kaggle, includes clinical features such as age, ejection fraction, and serum creatinine levels for 299 heart failure patients. To address the imbalance in survival outcomes, Synthetic Minority Over-sampling Technique (SMOTE) was employed to balance the dataset, followed by SelectKBest and Chi-square feature selection methods to retain the most significant predictors. The optimized hyperparameters for the GBM model were identified using the AIW-PSO algorithm, which effectively balanced exploration and exploitation by adaptively adjusting inertia weights. Model selection was further refined using information criteria, including Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC), ensuring that the best-performing model was chosen based on both predictive accuracy and model complexity. The optimized GBM model achieved a test accuracy of 94%, demonstrating superior performance compared to traditional machine learning models. The study underscores the importance of hyperparameter tuning through metaheuristic algorithms and highlights the potential of AIW-PSO in enhancing model performance for clinical prediction tasks. These findings have significant implications for clinical decision-making, offering a reliable and interpretable tool for predicting patient outcomes in heart failure management. INDEX TERMS Heart failure survival prediction, machine learning algorithms, hyperparameter optimization, class imbalance handling, AIW-PSO optimization. ABBREVIATIONS AND TERMS • AIWPSO: Adaptive Inertia-Weight Particle Swarm Optimization • GBM: Gradient Boosting Machine • SMOTE: Synthetic Minority Over-sampling Technique • ML: Machine Learning • AUC: Area Under the Curve • ROC: Receiver Operating Characteristic • SVM: Support Vector Machine The associate editor coordinating the review of this manuscript and approving it for publication was Yiqi Liu . • HF: Heart failure • GA: Genetic Algorithm • ADASYN: Adaptive Synthetic • ANOVA: Analysis of Variance • AIC: Akaike Information Criterion • SBIC: Schwarz Bayesian Information Criterion • HQIC: Hannan-Quinn Criterion I. INTRODUCTION Cardiovascular diseases (CVDs) include a range of disorders affecting the heart and blood vessels, such as coronary heart disease, stroke, and heart failure (HF) . The World Health 􀀊 2025 The Authors. This work is licensed under a Creative Commons Attribution 4.0 License. VOLUME 13, 2025 For more information, see [https://creativecommons.org/li

FAQs

What machine learning models and optimization method are used in the study?

The approach combines Gradient Boosting Machine (GBM) with Adaptive Inertia Weight Particle Swarm Optimization (AIWPSO) to tune GBM hyperparameters for survival prediction.

How does the study handle class imbalance in survival outcomes?

It uses SMOTE to balance the dataset, followed by feature selection with SelectKBest and Chi-square to retain the most significant predictors.

How were the best GBM hyperparameters and model selected?

AIWPSO identifies optimized GBM hyperparameters, and model selection is refined using information criteria including AIC and BIC to balance predictive accuracy with model complexity.

Aug 4, 2026

Upload by Riley