GUI Base Prediction of Heart Stroke Stages by Finding the Accuracy using Machine Learning Algorithm

Several types of predictive techniques have been used in clinical decision-making, such as identifying a disease or diagnosis, assessing a patient's prognosis, and providing treatment recommendations. Unfortunately, these techniques are not able to capture the underlying knowledge because they are not able to mimic the complexity of medical issue representation.To address this issue, a hospital dataset was used to develop a machine learning model that can perform predictive analysis on heart stroke. The symptoms of atrial fibrillation, which are known to be a major risk factor for stroke, are included in this dataset. The machine learning model was able to capture various pieces of information, such as multivariate analysis, variable identification, and univariate analysis.This work was devised with the intent of developing a machine learning model that can perform predictive analysis on heart stroke in patients. It can then classify the data collected by the model and provide a prediction for the severity of the condition. To achieve this, we proposed a method that combines the capabilities of machine learning and supervised classification.Furthermore, the efficiency of GUI based on the suggested machine learning algorithm technique can be compared to quality standards when equated with other models available for health care system data.