The Study Of Subhealth Status And Cause Investigation Of College Students Based On Logistic Regression And Decision Tree Model

Health refers not only to the body's good state,but also to the superposition of psychological,social and moral conditions.With the continuous development of medical science,the physical conditions of people are divided into three categories according to the physical conditions of modern people: health,illness,and a sub-health state between them.Nowadays,the number of sub-health patients is increasing.According to the survey,the proportion of truly healthy people does not exceed 3%.Therefore,sub-health is not a case long ago,but it is a phenomenon that actually occurs around us and widely exists.In recent years,with the acceleration of the pace of life and the pressures of daily life,combined with the continuous advancement of science and technology,the rapid development of various computer software and mobile phone applications,and the interaction of various causes,the group of college students has been deeply affected.It has become Asia.Health problems are more prominent in the typical group,so the society should focus more on the sub-health status of college students and how to improve and prevent sub-health.During the survey,we took students from six colleges and universities in Nanchang City as the survey objects.We interviewed students in colleges and universities with questionnaires to assist them in individual cases.We hope to start with the questionnaire data and use basic statistical frequency analysis,chi-square test,and more.Classification Logistic regression and decision tree CHAID model are designed to deeply explore the relationship between the sub-health status of college students and the intrinsic factors.From the results,university students in the sub-health state accounted for about 62% of the interviewees.According to the results of the chi-square test,the basic information of the major and household registration did not pass the test,and in the multi-factor analysis process,the Logistic regression The results suggest that the sub-health status is mainly related to monthly living expenses,whether smoking,drinking,and physical exercise frequency,and the correct rate of discrimination is 81.47%.The result of the decision tree model shows that the analysis result shows that the greatest factor affecting sub-health is the frequency of physical exercise.Second,the secondary variable is monthly living expenses,whether smoking and sleeping status,and whether or not there are three levels of influence on whether to smoke or not.The correct rate of discrimination is 87.1%.Finally,the conclusions and suggestions are based on four levels: social support,family,study,and personal,combined with appropriate guidance given by the analysis results.