A brain stroke occurs when blood flow to a part of the brain is disrupted, leading to cell death. Traditional stroke diagnosis methods, such as CT scans and MRIs, are costly and time-consuming. This study proposes a weighted voting ensemble (WVE) machine learning model that combines predictions from classifiers like random forest, Deep Learning, and histogram-based gradient boosting to predict strokes more effectively. The model achieved 94.91% accuracy on a private dataset, enabling early risk assessment and prevention. Future research could explore optimization techniques to further enhance accuracy.
@article{arxiv.2504.13974,
title = {Enhancing Stroke Diagnosis in the Brain Using a Weighted Deep Learning Approach},
author = {Yao Zhiwan and Reza Zarrab and Jean Dubois},
journal= {arXiv preprint arXiv:2504.13974},
year = {2025}
}