Psoriasis treatment effect evaluation system based on Bayesian network maximum entropy self-learning extension set pair analysis

Abstract

The invention relates to a psoriasis treatment effect evaluation system based on Bayesian network maximum entropy self-learning extension set pair analysis. The system comprises the following steps: selecting a disease for treatment effect evaluation, and constructing a treatment effect evaluation Bayesian network; inviting experts to score, and obtaining the weight of each index by using an AHP method; performing self-learning by taking the AHP weight as an initial weight and combining with a Bayesian network, setting the information entropy to reach the maximum value, and outputting the weight after self-learning; obtaining the comprehensive weight of the symptom index according to the hierarchical relationship of the Bayesian network; constructing a treatment effect evaluation ESPA model based on the obtained symptom index comprehensive weight, and calculating a CD corresponding to each patient symptom index; and evaluating the treatment effect of the patient. The method has the advantages that a disease comprehensive evaluation network of a plurality of clinical indexes is constructed through Bayesian network analysis and is combined with the maximum entropy principle; wherein the index weight is determined through the self-learning process, the disease treatment effect is evaluated through analysis by using the extension set on the basis, and support is provided for assisting clinical decision making.

Description

technical field [0001] The invention relates to the technical field of curative effect evaluation, in particular to a psoriasis curative effect evaluation system based on Bayesian network maximum entropy self-learning extended set pair analysis. Background technique [0002] Efficacy evaluation has always been a key point in clinical diagnosis and treatment and clinical research. Various psoriasis assessment tools have been proposed to assess the severity of psoriasis, among which the Psoriasis Area and Severity Index (PASI) and Body Surface Area (BSA) are the most commonly used. ), however, psoriasis is a systemic disease, and the way to evaluate the curative effect from the skin lesions is not comprehensive enough, and it is greatly affected by the subjective factors of doctors. The World Health Organization (WHO) also pointed out that the currently used PASI and Patient-reported outcomes, such as clinical outcome measures such as the Dermatology Life Quality Index (DLQI)...

AI Technical Summary

Problems solved by technology

[0011] and about a kind of comprehensive clinical manifestation of the present invention, laboratory index, quality of life and accompanying symptoms etc. clinical curative effect is evaluated, through Bayesian network analysis Construct a disease comprehensive evaluation network of multiple clinical indicators, and combine it with the principle of maximum entropy, determine the index weight through the self-learning process, and use the extended set to analyze the curative effect of the disease on this basis, and provide support for clinical decision-making There are no relevant reports on the evaluation method and system of disease efficacy based on Bayesian network maximum entropy self-learning and extended set pair analysis

Images