Stroke Data Analysis and Prediction

This paper explores the impact of strokes on society and emphasizes collaborative efforts to enhance stroke management. By leveraging technology and medical records, caregivers gain insights into relevant risk factors for stroke prediction. This paper systematically examines various components in electronic health records for effective stroke forecasting. Employing diverse statistical methods and principal component analysis, we identify the most significant factors for stroke prediction. Using statistical methods and principal component analysis, we identify age, heart disease, average glucose level, and hypertension as crucial factors. Our findings indicate that age, heart disease, average glucose level, and hypertension emerge as the most critical factors for detecting stroke in patients. Furthermore, a perceptron neural network utilizing these attributes achieves superior accuracy and lower miss rates compared to other methods on a balanced dataset.