Brain metastasis tumor prognostic index reduction and classification method based on rough set optimization

Abstract

The invention discloses a brain metastasis tumor prognosis index reduction and classification method based on rough set optimization. The method comprises the following steps: A, collecting and cleaning data, acquiring clinical case data of a brain metastatic tumor patient, and filtering prognosis index related information; selecting related prognosis indexes as condition attributes, and selectingbenign and malignant tumors corresponding to each case as decision attributes to form a decision table; B, according to the decision table formed by reduction in the step A, searching for a reductionattribute set with the minimum number of condition attributes, the maximum dependency degree of the condition attributes relative to label categories and the minimum relevancy between the condition attributes in the decision space by adopting a dynamic group optimization algorithm; and C, classifying the brain metastases prognostic index set reduced in the step B. According to the method, on thebasis of the obtained clinical data of the brain metastatic tumor, the classification precision which is the same as or even higher than that before reduction is obtained by directly reducing and classifying through an algorithm without manual reduction screening diagnosis.

Description

technical field [0001] The invention relates to the technical field of bioinformatics analysis, in particular to a method for reducing and classifying prognosis indicators of brain metastases based on rough set optimization. Background technique [0002] Under the current technical conditions, prognostic indicators are usually used in radiotherapy for brain metastases to guide patient decision-making and clinical trial analysis. Clinically, it is difficult and less sensitive to explore the prognostic indicators of cancer patients with brain metastases. Using bioinformatics methods to solve clinical problems is an important application in the field of artificial intelligence. [0003] As an important generalization model of rough sets, fuzzy rough sets can directly process real-valued data, avoid the problem of information loss caused by data discretization, and thus reflect the essential characteristics of data more objectively. Fuzzy rough sets have been effectively applie...

AI Technical Summary

Problems solved by technology

It is effective not only for cancer metastatic lesions, but also for multiple metastatic lesions. At present, the selection of the best prognostic indicators is a heavy task and is still in the exploratory stage. For the SRS treatment of NSSLC brain metastases, the selection of the best prognostic indicators to predict the prognosis Therefore, how to effectively reduce the prognostic indicators to reduce the human and financial resources consumed in classification has become an important research direction of bioinformatics

Images