New research shows an artificial intelligence (AI) tool effectively detected distress in hospital workers’ conversations with their therapists. Published in the Journal of Medical Internet Research AI, the findings suggest a potential new use of AI to screen for depression and anxiety.

During the COVID-19 pandemic, virtual psychotherapy grew as a treatment option for strained healthcare workers. Researchers examined a series of digitalized session transcripts using an AI technique called natural language processing (NLP). They identified common phrases used by patients and tied the terms to mental illness. NLP combs through data to pinpoint keywords that capture the meaning of a body of text.

The study, led by NYU Langone Health psychologist Matteo Malgaroli, PhD, is the first application of NLP to identify markers of psychological distress in healthcare workers, according to the authors.

“Our findings show that those working on the hospital floor during the most intense moments of the pandemic faced unique challenges that put them at higher risk for serious mental health concerns.”

Matteo Malgaroli, PhD

“Our findings show that those working on the hospital floor during the most intense moments of the pandemic faced unique challenges on top of their regular job-related stressors that put them at higher risk for serious mental health concerns,” says Dr. Malgaroli.

Teletherapy Transcripts as Screening Tools

Analysis involved treatment transcripts from more than 800 physicians, nurses, and emergency medical staff. Also included were transcripts from 820 people receiving psychotherapy during the first U.S. wave of COVID-19 but not working in healthcare.

The study revealed that among healthcare workers, those who spoke to their therapists specifically about working in a hospital unit, lack of sleep, or mood issues were more likely to get an anxiety and depression diagnosis compared with healthcare workers who did not discuss these topics. These risks were not seen in workers from other fields who discussed the pandemic or their jobs.

“These results suggest that natural language processing may one day become an effective screening tool for detecting and tracking anxiety and depression symptoms.”

Naomi M. Simon, MD

“These results suggest that natural language processing may one day become an effective screening tool for detecting and tracking anxiety and depression symptoms,” says study co-author Naomi M. Simon, MD, a professor and vice chair in the Department of Psychiatry.

While the overall heightened risk for anxiety and depression among those who discussed working in a hospital was small (3.6 percent), the study authors say they expect the model to capture additional signs of distress as more data are added.

Confidential Self-Assessments

Dr. Malgaroli notes that another potential use for this model could be to provide healthcare workers a way to record themselves answering brief questions. The NLP model could potentially detect their risks for mental health conditions and provide confidential feedback, including resources to seek additional support if they chose it.

The researchers caution that the report only captured the mental state of patients early in their treatment. The team now plans to explore how the discussion topics change over time as therapy progresses.