Analysis of Adolescent Tuberculosis Prevention and Treatment by Combining Data Membership and Fuzzy Clustering Algorithm

To provide effective suggestions for tuberculosis prevention and control, fuzzy c-Means (FCM) algorithm was used to build a data mining model for adolescent tuberculosis. At the same time, the membership degree is used to determine the criterion parameters and achieve model improvement. The improved FCM clustering accuracy is 97.65% and 94.65%, respectively, which is better than traditional FCM models. The results showed that the pass rate of nuclear disease prevention and control core knowledge was 94.20%, and the total awareness rate of tuberculosis prevention and control among middle school students was 76.2%. According to the analysis results, tuberculosis prevention suggestions are given. The traditional FCM is prone to local convergence and parameterization problems, data membership parameters and relative entropy are introduced for improvement. The two-dimensional data analysis capabilities of the data mining model were tested. This research provides important technical support for tuberculosis data analysis and prevention, and helps to improve the effectiveness and efficiency of tuberculosis prevention and control.