Study Finds AI Effective in Identifying Suicide Risk in Patients

New Delhi: Artificial intelligence (AI) can assist doctors in identifying patients at risk of suicide, potentially enhancing prevention efforts in routine medical settings, according to new research published in JAMA Network Open.

The study explored two approaches to integrating AI into clinical workflows: interruptive pop-up alerts that directly notified doctors during their workflow and a passive system that displays risk information in patients' electronic health records without immediate alerts.

The findings revealed that the interruptive alerts were significantly more effective. Doctors conducted suicide risk assessments for 42% of patients flagged by the interruptive system, compared to only 4% with the passive approach, as per inputs from IANS.

Colin Walsh, an associate professor of biomedical informatics, medicine, and psychiatry at Vanderbilt University Medical Center, emphasized the importance of such interventions. “Most people who die by suicide have seen a health care provider in the year before their death, often for reasons unrelated to mental health,” he said.

The research team tested their AI-powered system, the Vanderbilt Suicide Attempt and Ideation Likelihood (VSAIL) model, in three neurology clinics. This model analyzes routine data from electronic health records to estimate a patient’s 30-day risk of a suicide attempt. The system was designed to support doctors in identifying high-risk patients and prompting focused screening conversations during regular clinic visits.

“Universal screening isn't practical in every setting. We developed VSAIL to help identify high-risk patients and prompt focused screening conversations,” Walsh explained, according to IANS.

The researchers suggested that similar AI-based systems could be adapted for use in other medical settings. However, Walsh cautioned that healthcare systems must balance the effectiveness of interruptive alerts with their potential drawbacks, such as workflow disruption.

The study highlights the need for better suicide prevention strategies, particularly as 77% of people who die by suicide have contact with primary care providers within a year before their death, as per IANS.

The results underscore how automated risk detection combined with well-designed alerts can help identify more patients in need of suicide prevention services, the researchers concluded.