In this paper, the disease of cerebral stroke is studied mainly. According to the basic information of the patient, Linear fitting method is applied to calculate between the number of sick and age by using MATLAB software. According to data of pressure, temperature and humidity, nondimensionalizing by normalization method, linear regressions are analysed between the number of the patient and pressure, temperature, humidity. According to the important feature and the key indicators of cerebral stroke, high-risk groups are proposed to the early warning and intervene.