Predicting Stroke Risk: A Logistic Regression and Data Visualization Approach

Abstract

Strokes significantly threaten global health, underscoring the urgent need for accurate predictive models to aid in prevention efforts. This study delves into the application of logistic regression and data visualization techniques to analyze a dataset comprising 5110 stroke patients and their characteristics. This paper identifies key attributes associated with stroke risk, including age, hypertension, heart disease, and glucose levels. The logistic regression model demonstrates a high accuracy of approximately 95%, with nuanced insights provided by comparing single-year versus multi-year data models. This paper demonstrates the power of data visualization and machine learning to analyze complex relationships between patient attributes and stroke incidence, concluding that the integration of advanced analytics into clinical practice can significantly bolster stroke prevention, emphasizing a personalized approach to healthcare that prioritizes early detection and intervention. The study contributes to the medical community’s arsenal against strokes, offering a robust healthcare predictive modeling framework. The synergy between data science and medicine plays a critical role in mitigating the impact of stroke, enhancing outcomes, and optimizing allocations.