Prediction model of influencing factors of quality of life in middle-aged and elderly patients with chronic diseases based on machine learning

To predict the model of influencing factors of the quality of life of patients with chronic diseases in China, which is beneficial to improve the quality of life of patients with chronic diseases, and to formulate effective intervention measures for them. Methods: According to the data of China Health and Retirement Longitudinal Study (CHARLS) in 2020, 1187 subjects who met the research criteria were screened by lasso algorithm, and five machine learning algorithms (logistic regression, support vector machine, random forest, decision tree, naive Bayes) were evaluated. In order to select the best model to predict the influencing factors. Results: The lasso algorithm screened 24 possible related variables to determine 7 variables, compared the performance of five different machine learning models on the test set, and the results showed that the logical regression model performed better. Conclusion: Logistic regression in the prediction model based on machine learning can accurately obtain the influencing factors of the quality of life of patients with chronic diseases, and provide the basis for the follow-up research.