AI voice coach can help people with mental health conditions, study finds

Artificial intelligence could be used to treat common mental illnesses, according to a pilot study by University of Illinois Chicago (UIC) researchers.

Researchers recruited more than 60 patients with mild-to-moderate depression or anxiety to investigate whether an AI voice assistant called Lumen could help reduce symptoms.  They also looked at whether there were any changes in activity in brain areas previously shown to be associated with the benefits of problem-solving therapy.

Two-thirds of the participants were randomly assigned as the test group, using Lumen on a study-provided iPad for eight problem-solving therapy sessions over 16 weeks, while the rest served as a control group receiving no intervention. The majority (68%) of participants were women, while 25% were Black, 24% Latino, and 11% Asian.

Lumen participants attended an in-person orientation session with a trained health coach where they received their iPad, intervention workbook, and completed a tutorial on how to interact with Lumen.

After the intervention, study participants using the Lumen app showed decreased scores for depression, anxiety and psychological distress compared with those in the control group.

The Lumen group also showed that activation of the right dorsolateral prefrontal cortext (dlPFC) decreased in the intervention group but increased in the control group. High activity in the right dlPFC is associated with severe depression. “The change in the right dlPFC activation was also correlated positively with self-reported problem-solving ability scores and negatively with the avoidance scores in the Lumen group,” the researchers write.

An ’important stop-gap’

The team said that the findings offered encouraging evidence that virtual therapy can play a role in filling the gaps in mental health care. Dr Olusola A Ajilore, UIC professor of psychiatry and co-first author of the paper, said: “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.”

Ajilore added, however, that the treatment was not intended as a replacement for traditional therapy, but that it could be an “important stop-gap before somebody can seek treatment.”

Lumen, which operates as a skill in the Amazon Alexa application, was developed by Ajilore and fellow researcher Dr Jun Ma, along with collaborators at Washington University in St. Louis and Pennsylvania State University, with the support of a $2 million grant from the National Institute of Mental Health. It delivers problem-solving treatment (PST), a therapy that has been shown to be an effective intervention in treating anxiety and depression when delivered by a therapist. PST is driven by patients. The coach acts as a guide to identify a problem, set a goal, brainstorm solutions, choose a solution, develop an action plan, and to implement and evaluate the plan. The researchers thought this made it a particularly appropriate intervention to deliver through an AI voice assistant.

Ma said: “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 behaviour therapy that’s well established, which makes it a good fit for delivery using voice-based technology.”

There is now a larger trial underway, which compares the use of Lumen with both a control group on a waiting list, and patients receiving human-coached problem-solving therapy. Ma says that the virtual coach doesn’t need to perform better than a human therapist to fill a desperate need in the mental health system: “The way we should think about digital mental health service is not for these apps to replace humans, but rather to recognise 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.”