In recent years, there have been many studies on the prediction of diseases, mainly including the establishment, verification and update of multi-factor prediction models for individual patients. With the accumulation of big data and the update of statistical algorithms, the research of predictive models has more room for development, especially the research of multi-factor predictive models for the occurrence and development of individual patients' diseases. The prediction accuracy of model is the core problem of prediction model research. The factors that affect the prediction accuracy of model include the research object and application scenario, the selection and measurement of prediction indicators, the selection and measurement of outcome indicators and the selection of algorithm for model construction.