Prediction of Stroke Probability by Data Analyzing and Model Training

With the improvement of living standard, people pay more and more attention to their health level. With the surge of life pressure, stroke has become a disease of increasing concern. The purpose of this paper is to study the characteristics of the dataset, comprehensively analyze the etiology of stroke, and to help predict the likelihood of future stroke by training and using the model. In order to achieve the purpose, this paper carries out data mining, and then finds the data to observe each element one by one. And by using the tools of the python platform to systematically analyze the data. Finally, the data set is used to train the model and the optimal one is selected as a prediction tool. The result showed that stroke was highly correlated with age and complications of advanced age.