Machine Learning Approaches in Neuro- Logical Disorder Diagnosis

Brain stroke is a critical medical condition caused by a disruption in blood circulation within the brain, leading to significant damage and potential disabilities. With worldwide implications, it ranks as the second leading cause of death and the third leading cause of disability. Early diagnosis and preventive measures are essential to mitigate these outcomes. This project employs machine learning techniques to develop a reliable diagnostic model that predicts the likelihood of a stroke based on patient data. The dataset comprises various demographic and health-related attributes, such as age, gender, hypertension, heart disease, marital status, occupation, residence type, average glucose level, BMI, smoking status, and stroke occurrence.

Several machine learning models, including Logistic Regression, Naive Bayes, Support Vector Machine (SVM), and K Nearest Neighbors (KNN), were utilized to analyze the dataset. In addition to these traditional models, a neural network architecture was implemented, achieving an accuracy of 95%. The dataset underwent preprocessing through standardization, and a train-validation split ratio of 80:20 was adopted to ensure reliable model evaluation.

The primary goal of this project is to determine the most accurate predictive model among the tested algorithms. The findings contribute to enhancing stroke prediction accuracy, thus aiding in timely intervention and prevention strategies. In subsequent chapters, the project will explore the methodology, data preprocessing steps, model development, and results analysis. By examining the strengths and weaknesses of each algorithm, this work aims to offer valuable insights for healthcare professionals and researchers focused on the diagnosis of neurological disorders.