Diagnosis and treating rules mining method based on Boolean matrix

Abstract

The invention discloses a diagnosis and treating rules mining method based on Boolean matrix. The method comprises the steps: 1, acquiring basic diagnosis and treating data; 2, mining diagnosis and treating rules; 3, setting parameters of diagnosis and treating rules; judging whether the setting of all parameters of the diagnosis and treating rules are completed or not; if yes, performing step 5; or else, performing the step 3; 5, performing structuralized modeling on the diagnosis and treating rules; 6, storing diagnosis and treating rules data. The structuralized modeling is performed on the diagnosis and treating rules, thus presentation and storage structures of the diagnosis and treating rules are standardized; meanwhile, the Boolean maxis is applied to the diagnosis and treating rules mining method, thus the mining of the diagnosis and treating rules are efficient and more storage space is saved.

Description

technical field [0001] The invention belongs to the field of computer technology, and further relates to a method for mining diagnosis and treatment rules based on a Boolean matrix. The invention uses an association rule mining method based on a Boolean matrix to explore attention-worthy associations and correlations among a large number of data items, and digs out frequently used rule sets as the driving force of the rule engine. As an important part of decision support system, rule engine can assist doctors to make accurate and comprehensive decisions in clinical diagnosis and treatment activities. Background technique [0002] With the advent of the era of big data, the traditional rule extraction scheme can no longer meet the basic needs of complex analysis and processing of a large amount of medical data to obtain valuable decision-making information. Moreover, due to the unstructured and semi-structured non-standard and non-uniform description forms of the rules, a se...

AI Technical Summary

Problems solved by technology

However, the disadvantage of this method is that this method mines association rules for plant and animal data sets of molecular genetic markers, and the data structure of the "feature data set" established cannot reasonably and effectively analyze the diagnosis and treatment rules. Representation is not conducive to the use, sharing, maintenance and updating of medical rules

However, the shortcoming of this method is that this method still uses the traditional association rule mining idea, and obtains k+1 frequent itemsets through the analysis of k frequent itemsets, and does not solve the two key problems of huge number of candidate itemsets and frequent database scanning. problem, the efficiency of the algorithm needs to be improved

Images