Application of Intelligent Medical Treatment in Long-Term Mental Health Monitoring and Early Warning of College Students

Abstract

With the rapid development of society and the intensification of competition, the mental health problems of college students have become increasingly prominent, and have become the focus of attention from all walks of life. The traditional mental health monitoring methods have some problems, such as low efficiency, narrow coverage and delayed early warning, so it is difficult to meet the needs of college students' mental health management. Therefore, this article aims to explore the application of smart medical technology in long-term psychological health monitoring and early warning of college students. Based on the basic principles of public health ethics, a comprehensive and intelligent psychological health monitoring system is constructed by integrating advanced technologies such as psychological scales and deep learning. The results showed that in terms of accuracy, the other two models, except for the logistic regression model, achieved an accuracy of over 82% among the three models. Among them, the accuracy of this paper was the highest, indicating that it has better predictive performance. In terms of accuracy, the percentages of logistic regression model and XGBoost model are both below 80%. Especially, the accuracy of the logistic regression model is only 63.7%, while the accuracy of our model is significantly higher, with better reliability and accuracy performance. In the experiment, four different datasets were randomly selected for experimentation. The results indicate that the proposed model has a high degree of consistency with manual processing methods, with a matching degree of over 93.6%. Experimental results show that compared with other models, the proposed model has better performance and can effectively process mental health-related data, and the results have higher accuracy and precision rate, and have higher practical application potential. The experimental results show that the model can effectively extract the psychological keywords features of college students' social software and effectively identify students with different mental health states. According to the relevant data, the risk distribution of students' mental illness and the risk degree of influencing factors can be analyzed, and more targeted strategy suggestions can be provided for psychological intervention of college students.