AUTHOR=Xu Haibo , Wu Xiang , Liu Xin 

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

JOURNAL=Frontiers in Public Health

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/public-health/articles/10.3389/fpubh.2022.990235

DOI=10.3389/fpubh.2022.990235

ISSN=2296-2565

ABSTRACT=Serious psychological and mental health problems are often accompanied by some clinical symptoms, such as headache, palpitations, slow thinking, etc. However, its early clinical symptoms are relatively hidden, and even the patients themselves cannot detect them, and it is easy to miss the best time for treatment. Especially due to the negative impact of COVID-19, the number of patients with mental health problems has increased sharply, and how to accurately and quickly screen out early psychological symptoms has become particularly important. Artificial intelligence technology provides more objective and efficient screening tools for the clinical diagnosis and treatment of mentally ill patients. In order to identify the early psychological problem using objective quantitative detection methods, this paper proposed an intelligent measurement and evaluation method for psychological problems by analyzing and calculating personal structured and unstructured clinical data. Firstly, based on traditional methods, utilize the psychological assessment scales based on human-computer interaction to conduct health questionnaires for college students. Secondly, integrate machine learning technology to identify the state of participating students and assess the severity of participants' mental problems. Finally, the experiments have shown that the incidence of moderate or higher stress, anxiety, and depression was 51.3%, 67.5%, and 48.6% among the participating college students. Compared to DASS-21 questionnaires alone, the interactive multimodal emotion recognition method proposed in this paper has more clear advantages, providing an effective way for large-scale mental health screening, monitoring, and intervening in college students' mental health problems.