Brain stroke prediction using XGBOOST, LGBM, CNN, CNN-LSTM

In the realm of healthcare, the early detection of potentially life-threatening conditions is paramount. This study delves into the development of a machine learning algorithm for the early detection of brain strokes, a critical medical concern. Leveraging a comprehensive dataset encompassing gender, age, hypertension, heart disease, marital status, occupation, residence type, average glucose levels, BMI, and smoking status, we aim to create a robust predictive model. By employing a variety of machine learning algorithms, including XGBoost, Light-GBM, CNN, LSTM, we endeavor to construct a highly accurate and efficient tool for stroke prediction. Early diagnosis of stroke is essential for timely medical intervention and improved patient outcomes. The algorithm's precision and speed are pivotal in achieving this goal. Through extensive experimentation and evaluation of various classifiers, we aim to identify the most effective approach for stroke prediction. Ultimately, this research contributes to the advancement of healthcare by providing a valuable tool for early brain stroke detection, potentially saving lives and reducing the burden on healthcare systems.

Keywords: Machine learning techniques, ML evaluations.