cardiovascular disease (cVD) is the leading cause of death worldwide and a major public health concern. CVD prediction is one of the most effective measures for CVD control. In this study, 29930 subjects with high-risk of CVD were selected from 101056 people in 2014, regular follow-up was conducted using electronic health record system. Logistic regression analysis showed that nearly 30 indicators were related to CVD, including male, old age, family income, smoking, drinking, obesity, excessive waist circumference, abnormal cholesterol, abnormal low-density lipoprotein, abnormal fasting blood glucose and else. Several methods were used to build prediction model including multivariate regression model, classification and regression tree (CART), Naïve Bayes, Bagged trees, Ada Boost and Random forest. We used the multivariate regression model as a benchmark for performance evaluation (Area under the curve, AUC = 0.7143). The results showed that the Random Forest was superior to other methods with an AUC of 0.787 and achieved a significant improvement over the benchmark. We provided a CVD prediction model for 3-year risk assessment of CVD. It was based on a large population with high risk of CVD in eastern China using Random Forest algorithm, which would provide reference for the work of cVD prediction and treatment in china. Cardiovascular disease (CVD) is a series of diseases involving the circulatory system, including angina pectoris, myocardial infarction, coronary heart disease, heart failure, arrhythmia and else, which is generally related to atherosclerosis. With the social economy development, the population aging and the urbanization acceleration in China, some changes have taken place in national lifestyles, which leading to a rise of CVD prevalence. In 2016, there were more than 290 million cases of CVD in China, and 4.344 million deaths from it, including 2.098 million deaths from stroke and 1.736 million deaths from coronary heart disease, which bringing heavy social and economic burden 1. CVD is a disease that can be prevented and controlled, and early intervention can effectively control its progress 2. In recent years, many achievements have been made in the study of CVD risk prediction model, but the effect of epidemiological risk factors and biomarkers may be different in different populations, the CVD model has certain population specificity. In addition, there has been no study on CVD risk prediction model based on large cohort population in eastern China. At the same time, a large number of the existing CVD prediction models use multivariable regression method to build prediction models in a linear fashion, but it generally exhibit modest predictive performance, especially for certain sub-populations 3,4. Machine learning (ML) such as random forest (RF) can improve the performance of risk predictions by exploiting large data repositories to identify novel risk predictors and more complex interactions between them 3. In this study, we conducted a CVD prediction model research based on a specific c...

No abstract

No abstract

There is urgent need for further work on promotion of child development in rural China. The World Health Organization's CFD approach and Mother's Card is feasible and effective and should be expanded in use, especially within the national IMCI program.