A Hybrid Brain Stroke Prediction Framework: Integrating Feature Selection, Classification, and Hyperparameter Optimization

A Hybrid Brain Stroke Prediction Framework: Integrating Feature Selection, Classification, and Hyperparameter Optimization

ABSTRACT Stroke is a leading cause of death and disability worldwide, requiring accurate and early prediction to ensure timely medical intervention. This study proposes a hybrid system that combines optimal feature selection and advanced classification techniques to improve stroke prediction perform...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohammad Amin, Khalid M. O. Nahar, Hasan Gharaibeh, Rabia Emhamed Al Mamlook, Ahmad Nasayreh, Nesrine Atitallah, Ali Gharaibeh, Raneem Hamad, Raed Abu Zitar, Aseel Smerat, Laith Abualigah
Format: Article
Language:English
Published: Wiley 2025-07-01
Series:Engineering Reports
Subjects:
ANOVA
brain stroke prediction
feature selection
hyperparameter
machine learning
Online Access:https://doi.org/10.1002/eng2.70213
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:ABSTRACT Stroke is a leading cause of death and disability worldwide, requiring accurate and early prediction to ensure timely medical intervention. This study proposes a hybrid system that combines optimal feature selection and advanced classification techniques to improve stroke prediction performance. We used a publicly available Harvard Stroke Prediction Data Warehouse dataset, applying multiple feature selection methods: ANOVA, chi‐square, mutual information classification, and analysis of variance to identify relevant features. Five classifiers were examined: Random Forest (RF), K‐Nearest Neighbors (KNN), Decision Tree (DT), XGBoost, and Multilayer Perceptron (MLP). MLP was also used for feature selection through its internal representation learning capabilities. The parameters were fine‐tuned using GridSearchCV. The most effective configuration used selected features from a RF with MLP as a classifier, achieving 99.86% accuracy, 1.00% recall, 99.73% precision, and an F1 score of 99.86%. Compared with existing state‐of‐the‐art models, our proposed system demonstrates superior performance. This approach enables earlier and more accurate stroke detection, supporting healthcare providers in delivering personalized and proactive care to at‐risk individuals.
ISSN:2577-8196

Similar Items