Method and system of processing and analyzing diagnosis information

Abstract

The invention discloses a method and system of processing and analyzing diagnosis information, and relates to the technical field of medical system. The method of processing and analyzing diagnosis information includes the following steps: establishing characteristic space and label space through a plurality of sample characteristics and label information, and establishing the characteristic vector and the first label vector of the sample; calculating the occurrence number of each label information; calculating the occurrence number that every two label information occur in one sample at the same time; calculating the similarity of every two label information, and establishing a similarity matrix of label-label; reconstructing the first label vector to obtain the second label vector, and according to the second label vector, calculating the occurrence probability of the label information of the target sample; and selecting the preset number of label information as the recommended labelinformation of the target sample. The method and system of processing and analyzing diagnosis information can form the characteristic space and the label information by means of the characteristics corresponding to the disease of a patient, can effectively discover more underlying diseases by means of correlation between the diseases and the complication of the diseases, and can improve the accuracy of diagnosis decision support.

Description

technical field [0001] The invention relates to the technical field of medical systems, in particular to a method and system for processing and analyzing diagnostic information. Background technique [0002] In the era of big data, people have gradually accepted the method of using health big data to assist diagnosis and treatment. With the success of many industrial applications in the use of big data, the health service industry has also begun to use medical big data to improve service efficiency and quality. [0003] Health informatics tools and machine learning techniques are already being used successfully to help doctors diagnose disease and plan treatment more efficiently. Clinical decision support applications include systems that provide diagnosis, personalized drug evaluation, treatment options, and relevant medical knowledge. Clinical decision support applications aim to provide medical staff with professional knowledge, patient information and intelligent means...

AI Technical Summary

Problems solved by technology

However, this algorithm ignores the correlation between labels by estimating the likelihood of each label independently

In the actual diagnosis of diseases, many labels are related. For the application scenarios where the labels are related, the ML-kNN method is not effective.

Images