Asthma prognosis evaluation method and device

Abstract

An embodiment of the invention provides an asthma prognosis evaluation method and a device, wherein the method and the device relate to the field of data processing technology. The method comprises the steps of extracting characteristic values of multiple evaluation characteristics of a patient, then inputting the characteristic values of the multiple evaluation characteristics of the patient intoN classifying sub-models of a nonlinear classifying model, determining N classes which correspond with the patient, wherein each classifying sub-model corresponds with a prognosis evaluation year limit, the kinds which correspond with the patient comprise asthma recurrence and asthma no-recurrence, and N is an integer which is higher than 0. Afterwards, an evaluation result of the patient in theprognosis evaluation year limit which corresponds with the N classifying sub-modules is determined according to the N classes which correspond with the patient. The nonlinear classifying model is usedfor evaluating the asthma prognosis condition. The influence of nonlinear influence factors to asthma prognosis evaluation is sufficiently considered. Compared with a traditional regression analysismodel, the asthma prognosis evaluation method and the device have an advantage of higher evaluation accuracy.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of data processing, and in particular to a method and device for evaluating the prognosis of asthma. Background technique [0002] Infantile asthma (infantile asthma) is a common pulmonary disease in children. It is a reversible and obstructive respiratory disease characterized by recurrent cough, wheezing and dyspnea, accompanied by airway hyperresponsiveness. Asthma is a common chronic respiratory disease that seriously endangers children's health. It has a high incidence rate and often presents as a recurrent chronic disease course, which seriously affects children's study, life and activities, and affects children's growth and development. Due to untimely or inappropriate treatment, many children with asthma eventually develop into adult asthma, protracted recovery, impaired lung function, and some children even completely lose their ability to perform physical activities. Seve...

AI Technical Summary

Problems solved by technology

At present, traditional statistical methods are mainly used to evaluate the prognosis of asthma, such as multivariate analysis, linear regression, logistic regression, lasso regression and other common regression analysis models, but the regression analysis model does not perform well when dealing with nonlinear relationships, and affects The factors of asthma prognosis assessment include many non-linear factors, which makes the accuracy of asthma prognosis assessment low

Images