Date of Publication :25th June 2024

Abstract:The brain stroke prediction project endeavours to construct an effective machine learning model for anticipating the likelihood of stroke occurrence based on diverse demographic, lifestyle, and health-related attributes. Utilizing a dataset encompassing features such as age, gender, hypertension, heart disease, average glucose level, body mass index, smoking status, among others, seven distinct classification algorithms were trained and assessed. Notably, both Logistic Regression and Support Vector Classifier achieved an accuracy score of approximately 97.16 percentage. The Random Forest Classifier emerged as the most promising model with the highest accuracy of around 97.2 percentage. This project underscores the potential of machine learning in facilitating early detection and intervention strategies to mitigate stroke risks effectively within clinical settings.

Reference :