Early diabetes risk prediction method based on deep PCA transformation

A technology for risk prediction and diabetes, which is applied in the field of data processing, can solve problems such as the inability to effectively realize early diagnosis of diabetes, and achieve the effect of early auxiliary diagnosis
CN112635064AActive Publication Date: 2021-04-09山西三友和智慧信息技术股份有限公司
8 Cites 1 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
山西三友和智慧信息技术股份有限公司
Publication Date
2021-04-09

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
Patent Text Reader

Abstract

The invention belongs to the technical field of data processing, and particularly relates to an early diabetes risk prediction method based on deep PCA transformation, which comprises the following steps: inputting an early diabetes data set; preprocessing the data, calculating a Pearson correlation coefficient, and filtering redundant features to obtain input data; extracting a feature set of input data through depth PCA to serve as input of a training logistic regression classifier; training a logistic regression classifier based on the feature set for judging a to-be-evaluated case sample; inputting new case sample information, and outputting a result of judging whether the sample suffers from diabetes or not and a corresponding confidence coefficient. Effective extraction of case sample binarization information is realized through a deep PCA-based feature transformation method, and meanwhile, a logistic regression classifier is established to realize judgment of a diseased sample and output a confidence quantitative index of a result, so that early auxiliary diagnosis of an existing diabetes case is conveniently and effectively realized, and an illness state is discovered in time.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the technical field of data processing, and in particular relates to an early diabetes risk prediction method based on deep PCA transformation. Background technique

[0002] According to the report of the World Health Organization in 2018, diabetes is one of the fastest growing chronic life-threatening diseases, which has affected 422 million people worldwide. Since diabetes has a relatively long asymptomatic period, about 50% of diabetic patients are due to Prolonged asymptomatic periods without timely diagnosis, however early detection of diabetes is important for patient management and is only possible through proper assessment of common and less common signs and symptoms Different stages were found.

[0003] Reasons for problems or defects: Currently, the diagnosis of diabetes basically relies on clinicopathological analysis, which cannot effectively realize the early diagnosis of diabetes. Contents of the invention [...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More