Factors for evaluating the progress of chronic tonsillitis based on multifactor regression analysis

Abstract

The aim is to propose an approach to predicting the risk of progression of chronic tonsillitis in patients based on multivariate regression analysis for timely, convenient, and accurate diagnosis with subsequent selection of effective treatment and preventive measures in ENT departments (otolaryngology departments). A number of 100 patients with various forms of chronic tonsillitis, whose average age was 37 years, and 51 women and 49 men, were examined according to a specially developed questionnaire to predict the risk of ChT progression. The most probable indicators of chronic tonsillitis progression were selected to build a multivariate regression model for predicting the risk of ChT progression, 13 probable factors of the ChT progression were analyzed, and 9 factors were used to build a multivariate regression model. Histogram of the residual deviations is distributed symmetrically, approaching the curve of the normal distribution of the residuals and the absence of systematic deviations from the normal-probability straight line, so we conclude that the statistical hypothesis that their distribution conforms to the normal distribution law is not rejected. The residuals relative to the predicted values are scattered chaotically, which indicates the absence of dependence on the predicted values for the risk of chronic tonsillitis progression. The coefficient of determination was calculated, which is 0.8258, which claims that 82.58% of the factors are considered in the prediction model of the risk of chronic tonsillitis progression. The coefficient of determination indicates how well the obtained observations confirm the mathematical model. The proposed multivariate regression model that considers the risk factors for the ChT progression makes it possible to predict potential meta tonsillar complications and the possibility of timely disease prevention.