ML-Powered Brain Stroke Prediction Identifying Key Risk Factors for Early Detection
Year: 2025
Type: article
Abstract: This research takes a new direction by applying machine learning techniques to predict the likelihood of cerebrovascular accidents, or simply strokes, from an extensive dataset that was meticulously collected on the top-rated platform Kaggle. Through an extensive and thorough exploratory data analysis, we were able to reveal some of the significant risk factors accountable for these accidents, some of which are but not limited to age, hypertension, presence of cardiovascular disease, and average blood glucose level. In a bid to create effective prediction models, we utilized a series of sophisticated algorithms such as Logistic Regression, Decision Trees, and Random Forests, all of which collectively achieved a whopping accuracy of 95%. The findings demonstrate the remarkable potential of machine learning technology not only to predict strokes, but to identify and prevent them at an early level. This underscores the paramount importance of recognizing these top-risk factors in the framework of predictive modeling.
Author: Serra AKSOY
Language: English
Subfield: Health Information Management
Field: Health Professions
Domain: Health Sciences
Open Access status: hybrid
OpenAlex ID: W4408662279