Technological solutions could assist in decreasing waitlists and disparities in access to therapy having sparse clinical resources that are incapable to keep pace with high rates of mental illness.
The logo for the SPEAC trial studying a voice-enabled artificial intelligence counselor for depression and anxiety. Image Credit: University of Illinois Chicago
Recent advances in AI have fueled interest in the use of chatbots and virtual assistants for mental health treatment.
A new study led by researchers from the University of Illinois Chicago, with collaborators at Washington University and Pennsylvania State University, found that an AI voice assistant app delivering a form of psychotherapy can help patients with mild anxiety and depression.
The article, reported in the journal Translational Psychiatry, reports alterations caused in brain activity together with enhanced anxiety and depression symptoms following the use of the AI voice assistant, known as Lumen, for eight sessions of problem-solving therapy.
According to the co-first author Dr. Olusola A. Ajilore, the outcomes of this pilot study, the first to test an AI voice-based virtual coach for behavioral therapy, provide proof that virtual therapy has the potential to play a role in filling the gaps in mental health care.
We’ve had an incredible explosion of need, especially in the wake of COVID, with soaring rates of anxiety and depression and not enough practitioners. This kind of technology may serve as a bridge. It’s not meant to be a replacement for traditional therapy, but it may be an important stop-gap before somebody can seek treatment.
Dr. Olusola A. Ajilore, Study Co-First Author and Professor of Psychiatry, University of Illinois Chicago
A $2 million grant in 2020 was received by Ajilore and study senior author Dr. Jun Ma, the Beth and George Vitoux Professor of Medicine at UIC, to develop an AI coach named Lumen for treating mild-to-moderate depression and anxiety.
Lumen, which functions as a skill in the Amazon Alexa application, provides evidence-based problem-solving therapy. This helps patients to come up with a positive mindset and skills for resolving daily issues that result in emotional distress.
Ma stated, “It’s about changing the way people think about problems and how to address them, and not being emotionally overwhelmed. It’s a pragmatic and patient-driven behavior therapy that’s well established, which makes it a good fit for delivery using voice-based technology.”
Following the development of Lumen with their collaborators at Washington University in St. Louis and Pennsylvania State University, the scientists recruited 63 patients for a pilot study of its effect on anxiety and depression symptoms and activity in brain areas earlier shown to be linked to the benefits of problem-solving therapy.
Two-thirds of the patients made use of Lumen on a study-provided iPad for eight problem-solving therapy sessions, with the rest acting as a “waitlist” control getting no intervention.
Following the intervention, the Lumen group displayed decreased scores for anxiety, depression, and psychological distress than the control group. Also, the Lumen group displayed improvements in problem-solving skills that related to increased activity in the dorsolateral prefrontal cortex, a brain area that is associated with cognitive control.
In combination, the outcome offers a hopeful link between behavioral and neurological effects that assists in the additional investigation of the intervention.
With this experimental therapeutics approach, you have an idea of why things work. More importantly, you have an idea for whom these things work best for. In precision psychiatry, the mantra is finding the right treatment for the right person at the right time. These neural targets might actually serve as a biomarker for who will do best with this type of treatment.
Dr. Olusola A. Ajilore, Study Co-First Author and Professor of Psychiatry, University of Illinois Chicago
Furthermore, the intervention displayed particularly promising outcomes for women and underrepresented populations. Seeing effects in such populations was satisfying for the scientists, who developed and tested Lumen with feedback from such groups.
Ma stated, “If this form of treatment might actually offer, not only just access, but greater benefits to ethnic and racial minorities, that’s very meaningful.”
Another lesson of this pilot is that if you’re trying to design a digital mental health intervention to help a diverse patient population, you have to have that diverse patient population involved in the development of that intervention in order for them to get the maximum benefit from it.
Dr. Olusola A. Ajilore, Study Co-First Author and Professor of Psychiatry, University of Illinois Chicago
Building on the success of the pilot study, the research team is currently conducting a bigger trial comparing the usage of Lumen with both a control group on a waitlist and patients getting human-coached problem-solving therapy.
However, they stress that the virtual coach does not require to execute better compared to a human therapist to fill a desperate requirement in the mental health system.
Ma stated, “The way we should think about digital mental health service is not for these apps to replace humans, but rather to recognize what a gap we have between supply and demand, and then find novel, effective, and safe ways to deliver treatments to individuals who otherwise do not have access, to fill that gap.”
“Then there is more of an opportunity to think about how we allocate our very limited resources so that we can serve more patients who need care,” added Ma.
Also, the team will consider combining the dramatic advance that has been made recently in AI language models, like ChatGPT, for future iterations of Lumen or other digital interventions. However, with all such AI uses in psychiatry and medicine, the hype should be verified with cautious research.
Ajilore stated, “In the wake of this AI revolution and large language models over the last year, having a solid evidence base and careful, rigorous scientific work behind this approach is absolutely what’s needed before we actually start deploying it with our patients.”
Journal Reference
Kannampallil, T., et al. (2023) Effects of a virtual voice-based coach delivering problem-solving treatment on emotional distress and brain function: a pilot RCT in depression and anxiety. Translational Psychiatry. https://doi.org/10.1038/s41398-023-02462-x.