Analysis of Uneven Stroke Prediction Dataset using Machine Learning

Stroke is a sudden interruption in the blood flow to a portion of the brain that can result in the loss of capacity to move certain parts of the body. In this work, all elements that impact this disease are studied, their influences are extracted using exploratory data analysis, and a model is constructed to forecast the disease's likely existence in a patient. Using under sampling and over sampling strategies, several data balancing techniques are used to increase model performance. As a consequence of the findings, a 98 percent accuracy rate has been achieved compared to earlier research. While the class distribution is severely skewed, there are relatively few examples of a class. This study reveals that over-sampling approaches yield better results than under-sampling ones. When sampling-based techniques are used instead of sampling-based approaches, the outcomes improve by 46%.