AI in mental healthcare: 5 questions & answers

It stands to reason that the branch of healthcare most reliant on the use of language in clinical practice would embrace large language AI. But is U.S. mental healthcare on board with the notion? Consider:

1. Could AI help alleviate what the U.S. Surgeon General recently warned about as “our epidemic of loneliness and isolation?”

• AI may potentially provide significant benefits to help resolve this ongoing crisis, but no AI system can yet replicate the intricacies of human nature, interaction, emotion and feeling [needed to improve mental health at the population level]. Healthcare leaders, regulators and innovators … should prioritize training more mental health professionals and increasing patient access to care. Ultimately, whatever the solution may be, the time to act is now—before this epidemic becomes too catastrophic to manage. (Source: Sai Balasubramanian, MD, JD, in Forbes)

2. Burnout is rampant in just about every industry. How might AI reduce workplace stress and improve the mental health status of the U.S. workforce?

• Some individuals just need help with day-to-day stressors, and AI tools like chatbots can point them to on-demand resources. Chatbots can also be a bridge to connect individuals with employer-sponsored therapy sessions or help match people with clinicians or therapists that are a good fit to their needs. (Source: Lucy Roberts, PhD, senior consultant for national engagement and wellbeing at OneDigital, via CNBC.)

3. AI for mental healthcare calls to mind a popular saying: ‘People don’t care how much you know until they know how much you care.’ Will AI ever be able to convey the sense of caring that’s so essential in healthcare?

• Patients suffering from depression, anxiety or other mental health challenges might be able to talk with a chatbot that’s empathetic. In the future, [we] hope to see a lot of explainability and transparency [so] we can all understand the thought processes behind how these models are made. We hope that empathy and compassion will be included as major aspects behind that explained rationale. (Source: Karishma and Pratyush Muthukumar, brother-sister graduate students at UC-Irvine who are developing an empathetic chatbot for use in the medical field, in UCI News)

4. Could AI help foil the plans of a disturbed individual before he or she goes on a deadly rampage?

• Preventing a mass shooting requires more than computerized analysis; it involves the observations of the people who are in the best position to notice red flags in terms of negative affect, expressed grievances and behavioral changes. In this sense, averting a mass shooting requires knowledge and experience that AI doesn’t have. (Source: Wendy Patrick, JD, PhD, MDiv, in Psychology Today)

5. Here’s one for ChatGPT itself. ChatGPT, do you think you will eventually become a substitute for professional advice when it comes to mental health?

• My capabilities are constantly evolving and improving. However, I do not believe that I will ever be a substitute for professional medical or mental health advice. Mental health is a complex and multifaceted issue, and effective treatment often requires personalized assessment and intervention by a qualified mental health professional who can take into account individual needs, circumstances and history. (Source: ChatGPT response via interview by Nicholas Pratt, MD, RN, in Psychiatric Times)