Disease danger factor extracting method based on combination of clustering and classification

Abstract

The invention discloses a disease danger factor extracting method based on combination of clustering and classification. The method comprises the following steps of according to a user investigation questionnaire, constructing a user information matrix and a label vector; performing attribute segmentation on the user information matrix, thereby obtaining a plurality of user information matrix subsets and an original user information matrix; performing standardizing processing on each user matrix; performing dimension reducing processing on the standard user matrixes for obtaining dimension-reduced matrixes; clustering the dimension-reduced matrixes for obtaining the clustering population in different kinds; constructing a decision tree for each kind of clustering population, and performingstatistics on all decision trees through an integrated concept, and obtaining disease danger factors according to the magnitude of a hierarchy coefficient. Compared with a regression statistics method in the danger factor extracting method in a medical field, the method according to the invention has advantages of sufficiently utilizing original data and reducing an error rate caused by conclusion generation by a single decision tree through combination of clustering and classification.

Description

technical field [0001] The invention belongs to the field of big data technology and medicine, in particular to a method for extracting disease risk factors based on the combination of clustering and classification. Background technique [0002] Gastroesophageal reflux disease refers to a disease in which gastric reflux flows back into the esophagus, causing discomfort symptoms and complications. As a common clinical disease of the digestive system, it generally exists in various Asian and Western countries, and its incidence is increasing year by year. high trend. According to research, gastroesophageal reflux disease is related to various factors such as personal life, eating habits, and mental status, and the condition is prone to change. Therefore, exploring the risk factors of gastroesophageal reflux disease through big data technology is of great significance for the treatment and prevention of the disease. [0003] At present, for the risk factors of gastroesophagea...

AI Technical Summary

Problems solved by technology

Most of the clustering methods currently used for the extraction of disease risk factors are hierarchical clustering. When dividing clusters, professional medical knowledge is often required to determine the characteristics of the clusters, and the amount of calculation is large.

Images