Predicting the classification of heart failure patients using optimized machine learning algorithms

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)...

Full description

Bibliographic Details
Main Authors: Ahmed, Marzia, Mohd Herwan, Sulaiman, Hassan, Md Maruf, Bhuiyan, Touhid
Format: Article
Language:English
Published: IEEE 2025
Subjects:
Online Access:http://umpir.ump.edu.my/id/eprint/44038/
http://umpir.ump.edu.my/id/eprint/44038/1/Predicting%20the%20Classification%20of%20Heart%20Failure%20Patient.pdf
_version_ 1848827016647802880
author Ahmed, Marzia
Mohd Herwan, Sulaiman
Hassan, Md Maruf
Bhuiyan, Touhid
author_facet Ahmed, Marzia
Mohd Herwan, Sulaiman
Hassan, Md Maruf
Bhuiyan, Touhid
author_sort Ahmed, Marzia
building UMP Institutional Repository
collection Online Access
description 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.
first_indexed 2025-11-15T03:54:01Z
format Article
id ump-44038
institution Universiti Malaysia Pahang
institution_category Local University
language English
last_indexed 2025-11-15T03:54:01Z
publishDate 2025
publisher IEEE
recordtype eprints
repository_type Digital Repository
spelling ump-440382025-03-11T05:06:20Z http://umpir.ump.edu.my/id/eprint/44038/ Predicting the classification of heart failure patients using optimized machine learning algorithms Ahmed, Marzia Mohd Herwan, Sulaiman Hassan, Md Maruf Bhuiyan, Touhid TK Electrical engineering. Electronics Nuclear engineering 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. IEEE 2025-02-19 Article PeerReviewed pdf en cc_by_4 http://umpir.ump.edu.my/id/eprint/44038/1/Predicting%20the%20Classification%20of%20Heart%20Failure%20Patient.pdf Ahmed, Marzia and Mohd Herwan, Sulaiman and Hassan, Md Maruf and Bhuiyan, Touhid (2025) Predicting the classification of heart failure patients using optimized machine learning algorithms. IEEE Access, 13. 30555 -30569. ISSN 2169-3536. (Published) https://doi.org/10.1109/ACCESS.2025.3541069 https://doi.org/10.1109/ACCESS.2025.3541069
spellingShingle TK Electrical engineering. Electronics Nuclear engineering
Ahmed, Marzia
Mohd Herwan, Sulaiman
Hassan, Md Maruf
Bhuiyan, Touhid
Predicting the classification of heart failure patients using optimized machine learning algorithms
title Predicting the classification of heart failure patients using optimized machine learning algorithms
title_full Predicting the classification of heart failure patients using optimized machine learning algorithms
title_fullStr Predicting the classification of heart failure patients using optimized machine learning algorithms
title_full_unstemmed Predicting the classification of heart failure patients using optimized machine learning algorithms
title_short Predicting the classification of heart failure patients using optimized machine learning algorithms
title_sort predicting the classification of heart failure patients using optimized machine learning algorithms
topic TK Electrical engineering. Electronics Nuclear engineering
url http://umpir.ump.edu.my/id/eprint/44038/
http://umpir.ump.edu.my/id/eprint/44038/
http://umpir.ump.edu.my/id/eprint/44038/
http://umpir.ump.edu.my/id/eprint/44038/1/Predicting%20the%20Classification%20of%20Heart%20Failure%20Patient.pdf