Machine learning could use EHRs to predict suicide risk

Listen

Machine learning could use real-time predictive models to assess suicide attempt risk in nonpsychiatric settings in a large clinical system, according to a March 12 study published in JAMA Network Open.

The study followed 30-day suicide risk attempts among 77,973 patients in nonpsychiatric clinical settings in real time  from June 2019 to April 2020.

Three things to know:

  1. The numbers needed to screen for suicide risk were reasonable for algorithmic screening and required no additional data collection or in-person screening, the report says.

  2. Risk models can be implemented with accurate performance, but it is not equal in all clinical settings. It will require the model to be recalibrated prior to deploying.

  3. Model data used to predict suicide risk includes age, race, gender, medication, past healthcare utilization, patient zip code and prior medical conditions.

The next step is pairing the model with low-cost, low-harm preventive strategies to build a preventive model for future suicidality, the report suggests.

Copyright © 2021 Becker's Healthcare. All Rights Reserved. Privacy Policy. Cookie Policy. Linking and Reprinting Policy.

 

Featured Whitepapers

Featured Webinars