Diabetes mellitus probability calculation method based on large data of diabetes mellitus system

Abstract

The invention discloses a diabetes mellitus probability calculation method based on large data of a diabetes mellitus system. The diabetes mellitus probability calculation method comprises the following steps: (1) constructing a diabetes mellitus decision tree model; (2) selecting an optimal branch variable of the decision tree model according to the information gain ratio Gains (Xi) of a training sample S; (3) post-pruning a decision tree from bottom to top; and (4) constructing a diabetes mellitus naive Bayes model, and obtaining the diabetes mellitus probability P (C1|y1.y2.y3.....ym) with C1 serving as an output variable on a rth node by utilizing a Bayes formula. According to the diabetes mellitus probability calculation method disclosed by the invention, a two-layer model method with the combination of the decision tree and the naive Bayes model is designed; by extracting the characteristic attribute of diabetes mellitus from the large data, whether the diabetes mellitus occurs or not is forecasted, the probability of the occurrence of the diabetes mellitus is further calculated, and the prevention and the forecast are combined and are relatively overall and accurate.

Description

technical field [0001] The present invention relates to a method for calculating probability, in particular to a method for calculating probability of diabetes based on big data of diabetes system. Background technique [0002] With the development of social economy and the rapid increase of risk factors such as population aging and lifestyle, the prevalence of diabetes is on the rise worldwide. According to the statistics of the World Health Organization: in 1985, there were 30 million people with diabetes in the world, 135 million people in 1995, 177 million people in 2000, and it is estimated that it will reach 300 million people by 2025; about 4 million people die of diabetes and diabetes every year. Diabetes-related diseases account for 9% of the world's deaths. Many diabetic patients cannot be identified early, and the diabetic population is tending to be younger. The prevention and treatment of diabetes has become an important technical issue at present. [0003] Th...

AI Technical Summary

Problems solved by technology

This type of method only provides a preventive function, and the preventive factors are not comprehensive enough. At the same time, it lacks an important predictive function, which brings difficulties to the prevention and treatment of diabetes.

[0005] The second category mainly uses classification methods to predict the risk of diabetes, mainly divided into: high risk, medium risk, and low risk. This classification method has a wide range and is relatively vague

Moreover, the characteristic attributes of diabetes cannot be well screened out only through these classification methods, resulting in larger errors in prediction results

[0006] From the above two types of existing technologies, it can be seen that the current diabetes prevention and treatment technology is not mature enough, and the factors affecting diabetes are relatively complex. Both the simple big data analysis method and the simple prediction method have major defects. Prevention is not comprehensive enough, on the other hand, prediction is not precise enough

Images