A measurement method for mental health based on dynamic multimodal feature recognition.

Introduction: The number of college students with mental problems has increased significantly, particularly during COVID-19. However, the clinical features of early-stage psychological problems are subclinical, so the optimal intervention treatment period can easily be missed. Artificial intelligence technology can efficiently assist in assessing mental health problems by mining the deep correlation of multi-dimensional data of patients, providing ideas for solving the screening of normal psychological problems in large-scale college students. Therefore, we propose a mental health assessment method that integrates traditional scales and multimodal intelligent recognition technology to support the large-scale and normalized screening of mental health problems in colleges and universities. Methods: Firstly, utilize the psychological assessment scales based on human-computer interaction to conduct health questionnaires based on traditional methods. Secondly, integrate machine learning technology to identify the state of college students and assess the severity of psychological problems. Finally, the experiments showed that the proposed multimodal intelligent recognition method has high accuracy and can better proofread normal scale results. This study recruited 1,500 students for this mental health assessment. Results: The results showed that the incidence of moderate or higher stress, anxiety, and depression was 36.3, 48.1, and 23.0%, which is consistent with the results of our multiple targeted tests. Conclusion: Therefore, the interactive multimodality emotion recognition method proposed provides an effective way for large-scale mental health screening, monitoring, and intervening in college students' mental health problems.