ADVERTISEMENT
EHR-Based Model Gauges Suicide Risk in Nonpsychiatric Settings
A machine learning algorithm that used information from an electronic health record (EHR) system to gauge a patient’s suicide risk in real time showed good performance in nonpsychiatric clinical settings in an 11-month prospective trial at Vanderbilt University Medical Center, Nashville, Tennessee. Researchers published their findings online in JAMA Network Open.
“Today across the medical center, we cannot screen every patient for suicide risk in every encounter—nor should we,” said Colin Walsh, MD, assistant professor of biomedical informatics, medicine and psychiatry. “But we know some individuals are never screened despite factors that might put them at higher risk. This risk model is a first pass at that screening and might suggest which patients to screen further in settings where suicidality is not often discussed.”
The observational study spanned 77,973 patients seen for any reason in adult inpatient, emergency department, and ambulatory surgery settings at Vanderbilt University Medical Center between June 2019 and April 2020.
Clinicians’ Language Choice Can Impact Care of Patients With Suicidal Ideation
The Vanderbilt Suicide Attempt and Ideation Likelihood model was implemented in a vendor-supplied EHR system to predict the risk of 30-day return visits suicidal ideation and suicide attempt. The algorithm stratified patients into 8 groups based on risk scores.
Patients in the top stratum accounted for more than a third of suicide attempts and about half of cases of suicidal ideation documented in the study, researchers reported. In the highest risk quantiles, numbers needed to screen—or the number of patients who need to be screened to prevent the adverse event—were 23 for suicidal ideation and 271 for suicide attempt, the study found.
“Here, for every 271 people identified in the highest predicted risk group, one returned for treatment for a suicide attempt,” said Dr. Walsh. “This number is on a par with numbers needed to screen for problems like abnormal cholesterol and certain cancers…Our results suggest artificial intelligence might help as one step in directing limited clinical resources to where they are most needed.”
—Jolynn Tumolo
References
Walsh CG, Johnson KB, Ripperger M, et al. Prospective validation of an electronic health record–based, real-time suicide risk model. JAMA Network Open. 2021;4(3):e211428.
