Cortney VanHook, assistant professor of social work at the University of Illinois, recently published a new study in which he and his co-authors used generative AI to create a personalized mental health treatment plan for a fictitious Black male client, showcasing the potential for integrating this emerging technology into clinical and educational practices.
For their study, Dr. VanHook and his co-authors asked an AI platform to apply three theoretical, evidence-based frameworks to create a simulated case study and treatment plan for a virtual client, “Marcus Johnson,” a 24-year-old, single Black man in Atlanta who works as a software developer. After the authors provided numerous personal details about Marcus’ lifestyle, family, and symptoms, the AI tool determined the factors in Marcus’ life that supported or hindered his use of mental health services, evaluated his access to care, and created reliable measures for ongoing monitoring of his symptoms and functioning.
To ensure the AI-generated simulation reflected real-world clinical practice, the authors reviewed the proposed treatment plan for clinical accuracy and compared the case brief against published research findings. They also verified the materials’ cultural sensitivity and conceptualization of the barriers Black men often face in the U.S. healthcare system.
Notably, the authors highlight that AI models are limited by the data and patterns they are trained with, which may not reflect the full diversity, unpredictability, or emotional nuance of real clinical encounters. Furthermore, such simulations cannot fully substitute for lived experience or capture every factor influencing care. Nonetheless, the authors’ findings suggest generative AI can be a useful tool when educating students about populations they may not be familiar with, but will come in contact with in the field.
“AI is a train that’s already in motion, and it’s picking up speed,” said Dr. VanHook. “So, the question is: How can we use this amazing tool to improve mental health care for many populations? My hope is that it is used in the field, as a tool for teaching and within higher-order management and administration when it comes to mental health services.”
The study authors also included Daniel Abusuampeh of the University of Pittsburgh and Jordan Pollard of the University of Cincinnati.
