BACKGROUND
There has been a surge of interest in leveraging artificial intelligence (AI) to improve outcomes in mental health care. Therefore, understanding the current trends and identifying gaps and opportunities in the rapidly evolving intersection of the fields is crucial for shaping future research and advancing AI-informed mental health care.
OBJECTIVE
This study performed a comprehensive bibliometric analysis and systematic literature review (SLR) with the primary goal of identifying and analyzing current research trends, gaps and opportunities in the use of AI in mental health care.
METHODS
We collected publication data from two reputable databases, Web of Science and Scopus, and applied bibliometric analysis techniques. Additionally, we conducted a structured SLR of the 50 most influential papers determined by their citation to identify the main thrust of AI-informed mental health care.
RESULTS
The key finding reveals a growing emphasis on using AI for mental health care assessment, diagnosis, treatment, and support. Prediction and detection in mental health care have also received attention. Monitoring and prognosis remain underexplored. Machine Learning and Deep Learning were the dominant trends between 2021 and 2022. This was likely because of the focus on mental health due to the COVID-19 pandemic. There was little to no discussion about using AI to understand the long-term impact and sustainability of mental health interventions. This includes comparative analyses and validation, user-centered approaches, and the utilization of longitudinal studies and real-world data.
CONCLUSIONS
The study calls for further investigation into leveraging AI to predict, detect, monitor and prognosticating mental health conditions using more approaches such as Computer Vision and virtual agents such as Chatbots and generative AI. By addressing the identified gaps, the effectiveness and ethical considerations of AI-driven interventions in mental health care can be significantly enhanced.
CLINICALTRIAL