Gaussian fuzzy clustering computing method for differentiating and diagnosing chronic bronchitis

Abstract

The invention relates to a Gaussian fuzzy clustering computing method for differentiating and diagnosing chronic bronchitis. The method comprises the steps of obtaining inspection data of diagnosed chronic bronchitis patients from an electronic medical record system; calculating the initial clustering number through utilization of a hierarchical clustering algorithm; randomly selecting a clustering center according to the initial clustering number; mapping the clustering center and samples to a Hilbert space through mapping; calculating a membership matrix of the samples according to the clustering center in the Hilbert space; calculating a new clustering center through utilization of the calculated membership matrix; continuously and iteratively calculating the membership matrix and the clustering center until the change of the clustering center is smaller than a threshold value; calculating clustering granularity values according to the obtained clustering centers; circulating all initial clustering numbers and carrying out the steps; and taking the clustering center with the minimum granularity value as a final clustering result. The method can be used for finely classifying chronic bronchitis symptoms, and certain facilitation for diagnosing the chronic bronchitis is provided.

Description

technical field [0001] The invention relates to a Gaussian fuzzy clustering calculation method for differential diagnosis of chronic bronchitis. technical background [0002] Chronic bronchitis is considered to be nonspecific inflammation in the tissues surrounding the trachea and bronchi. Clinical practice shows that the further subdivision of chronic bronchitis is of great significance for the diagnosis and treatment of the disease. According to the different characteristics of the disease and whether there are complications, chronic bronchitis can be further diagnosed as chronic bronchitis with respiratory tract infection, simple chronic bronchitis, chronic bronchitis with emphysema, mucopurulent bronchitis, etc. . The further clinical classification of chronic bronchitis often comes from the doctor's clinical experience and subjective judgment, which often has the disadvantage of being too subjective. Therefore, an intelligent algorithm is used to analyze the clinical ...

AI Technical Summary

Problems solved by technology

In traditional clustering algorithms, the fuzzy weighting parameter m is often directly assigned a value of 2. This method of setting a value has no theoretical verification process and is not convincing.

Images