Stroke Prognosis Using ML Classification Algorithms

Stroke is one of the worst diseases on the planet, responsible for many fatalities both directly and indirectly. Numerous data mining techniques are used by the healthcare industry to aid in early disease identification and diagnosis. Many stroke risk factors are examined in the body of current research. We start by examining the characteristics of people who have strokes more frequently than others. The dataset is sourced from a publically available source, and various classification techniques are used to predict the likelihood of a stroke. Extreme Gradient Boosting was used to achieve accurate percentage. Reducing bias and enhancing model performance by applying a range of tactics, such as Random oversampling, a method that duplicates examples of the minority class to balance the distribution of classes.