Clinical alerts driven by artificial intelligence (AI) They can help doctors identify patients at risk for suicide, potentially improving prevention efforts in routine medical settings, according to researchers at Vanderbilt University Medical Center (United States) in a study published in ‘ JAMA Network Open’.
Specifically, the team led by Colin Walsh, associate professor of Biomedical Informatics, Medicine and Psychiatry, tested whether their AI system, called the Vanderbilt Suicide Ideation and Attempt Probability (VSAIL) model, could effectively prompt doctors to three neurology clinics at VUMC a screen patients for suicide risk during regular clinic visits.
AI can help detect suicide
The study compared two approaches: Automatic pop-up alerts that disrupted the physician’s workflow versus a more passive system that simply displayed risk information in the patient’s electronic health record. In this way, it found that the disruptive alerts were much more effective, leading doctors to perform suicide risk assessments in relation to 42% of the screening alerts, compared to only 4% with the passive system. .
“Most people who commit suicide have consulted a health professional in the year before their death, often for reasons unrelated to mental health”Walsh points out. “But universal screening is not practical in all settings. We developed VSAIL to help identify high-risk patients and promote targeted conversations about screening.”
Calls to improve risk screening have led researchers to explore ways to identify patients most in need of screening. The VSAIL model, which Walsh’s team developed at Vanderbilt, analyzes routine information from electronic medical records to estimate a patient’s risk of attempting suicide within 30 days.
In previous prospective tests, in which VUMC patient records were flagged but no alerts were triggered, the model proved effective in identifying high-risk patients: one in 23 individuals flagged by the system subsequently reported suicidal thoughts.
7,732 patient visits over six months
In the new study, when patients identified as high-risk by VSAIL came for appointments at Vanderbilt neurology clinics, their doctors randomly received interrupted or uninterrupted alerts. The research focused on neurology clinics because certain neurological diseases are associated with an increased risk of suicide.
The researchers suggested that similar systems could be tested in other medical settings. “The automated system flagged only about 8% of all patient visits for evaluation”Walsh insists. “This selective approach makes it more feasible for busy clinics to implement suicide prevention efforts”.
The study included 7,732 patient visits over six monthswhich generated a total of 596 detection alerts. During the 30-day follow-up period, a review of VUMC medical records found that no patients in either of the randomized alert groups had experienced episodes of suicidal ideation or suicide attempts.
While interrupted alerts were most effective in prompting assessments, they could potentially contribute to “alert fatigue,” when clinicians are overwhelmed by frequent push notifications. The researchers noted that future studies should examine this concern.
“Healthcare systems must balance the effectiveness of interruption alerts with their potential disadvantages”concludes Walsh. “But these results suggest that automated risk detection combined with well-designed alerts could help us identify more patients in need of suicide prevention services.”.
Sign up for our newsletter and receive the latest technology news in your email.
#manages #identify #patients #risk #suicide
