Analysis of risk factors for multi-drug resistant bacterial infections and prevention and control based on logistic regression analysis

Logistic regression and neural networks have developed rapidly in recent years, and the poor diet of people in modern society has led to the emergence of various diseases in which drug-resistant bacterial infections occur during treatment, so this paper proposes logistic regression to analyze risk factors and preventive control of multi-drug-resistant bacterial infections. A logistic regression model was established to determine the magnitude of the effect of each factor on the dependent variable based on the standardized values, and the prevalence was recoded in the prediction stage, with the screened indicators serving as factors and covariates. The number of neurons in the input and output layers is determined, and the weights are continuously adjusted in iterations to calculate the average error rate between the actual number of morbidities and the predicted values. The gradient explosion and dispersion problems of in-depth analysis are solved by selecting the maximum probability for classification. The error values were calculated by using the cost function, adjusting the model parameters, comparing the errors between predicted and observed values, and updating the weights with the hidden layer error values, thus improving the accuracy of the model for analyzing risk factors of multi-drug resistant bacterial infections and preventing and controlling the deterioration of the disease. The analysis of the results showed that the logistic regression analysis method, using the area of the ROC curve as a discriminant, yielded an AUC of 0.831 in this study, which combined with the neural network model to predict multi-drug resistant bacteria infections with a higher accuracy of 85.6%, identify the potential risk of multi-drug resistant bacteria occurrence, and prevent the aggravation of the infection.