Score: 0

Enhancing Stroke Diagnosis in the Brain Using a Weighted Deep Learning Approach

Published: April 17, 2025 | arXiv ID: 2504.13974v1

By: Yao Zhiwan, Reza Zarrab, Jean Dubois

Potential Business Impact:

Helps doctors find strokes faster and prevent them.

Business Areas:
Image Recognition Data and Analytics, Software

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.

Page Count
10 pages

Category
Computer Science:
Machine Learning (CS)