A New System Helps Doctors Identify Patients at Risk for Suicide
A new study from Vanderbilt University Medical Center has shown that clinical alerts driven by artificial intelligence (AI) can help doctors identify patients at risk for suicide, potentially improving prevention efforts in routine medical settings.
The study, published in JAMA Network Open, found that interruptive alerts were much more effective in prompting doctors to screen patients for suicide risk during regular clinic visits. In the study, doctors were 42% more likely to conduct suicide risk assessments when alerted by the AI system, compared to 4% with a passive system that simply displayed risk information in the patient’s electronic chart.
The AI system, called the Vanderbilt Suicide Attempt and Ideation Likelihood model (VSAIL), analyzes routine information from electronic health records to calculate a patient’s 30-day risk of suicide attempt. In earlier testing, the model was found to be effective in identifying high-risk patients, with one in 23 individuals flagged by the system later reporting suicidal thoughts.
The study involved 7,732 patient visits over six months, with the AI system identifying 596 total screening alerts. While the interruptive alerts were more effective, they could potentially contribute to “alert fatigue,” when doctors become overwhelmed by frequent automated notifications.
The researchers suggested that similar systems could be tested in other medical settings, noting that the automated system flagged only about 8% of all patient visits for screening, making it more feasible for busy clinics to implement suicide prevention efforts. The study’s findings suggest that automated risk detection combined with well-designed alerts could help identify more patients who need suicide prevention services.