Brain Stroke Prediction Using Deep Learning

Authors

  • Chinthalapati Nandini, Dr.V.Sudarshan Author

DOI:

https://doi.org/10.64751/np5mhd37

Abstract

Stroke is one of the leading causes of death and long-term disability worldwide, making early prediction essential for timely medical intervention and improved patient outcomes. Traditional prediction methods often rely on manual analysis and conventional machine learning techniques, which may struggle to capture complex relationships among diverse clinical factors. This study presents a Deep Learning-based Brain Stroke Prediction framework designed to analyze patient health records and estimate the likelihood of stroke occurrence with enhanced accuracy. The proposed model utilizes patient attributes such as age, gender, hypertension, heart disease, glucose level, body mass index (BMI), smoking status, and other relevant medical indicators to learn hidden patterns associated with stroke risk. Before training, the dataset undergoes preprocessing steps including handling missing values, encoding categorical variables, feature normalization, and data balancing to improve model performance. A deep neural network is then trained to classify patients into stroke and non-stroke categories. The effectiveness of the proposed approach is evaluated using performance metrics such as accuracy, precision, recall, F1-score, and ROC-AUC. Experimental results demonstrate that the deep learning model provides reliable prediction performance and outperforms several traditional classification methods in identifying individuals at risk. The proposed system can serve as a clinical decision-support tool, assisting healthcare professionals in early diagnosis, preventive care, and personalized treatment planning, ultimately contributing to reduced mortality and improved quality of patient care.

Downloads

Published

2025-11-18

How to Cite

Chinthalapati Nandini, Dr.V.Sudarshan. (2025). Brain Stroke Prediction Using Deep Learning. International Journal of AI Electrical Civil and Mechanical Engineering, 1(4), 58-64. https://doi.org/10.64751/np5mhd37