Machine Learning-Based Evaluation of Suicide Risk Assessment in Crisis Counseling Calls.

Journal: Psychiatric services (Washington, D.C.)
PMID:

Abstract

OBJECTIVE: Counselor assessment of suicide risk is one key component of crisis counseling, and standards require risk assessment in every crisis counseling conversation. Efforts to increase risk assessment frequency are limited by quality improvement tools that rely on human evaluation of conversations, which is labor intensive, slow, and impossible to scale. Advances in machine learning (ML) have made possible the development of tools that can automatically and immediately detect the presence of risk assessment in crisis counseling conversations.

Authors

  • Zac E Imel
    University of Utah.
  • Brian Pace
    Lyssn, Seattle, WA.
  • Brad Pendergraft
    Lyssn.io, Seattle (Imel, Pace, Pruett, Tanana, Soma, Atkins); Protocall Services, Portland, Oregon (Pendergraft); Harborview Medical Center, University of Washington, Seattle (Comtois).
  • Jordan Pruett
    Lyssn.io, Seattle (Imel, Pace, Pruett, Tanana, Soma, Atkins); Protocall Services, Portland, Oregon (Pendergraft); Harborview Medical Center, University of Washington, Seattle (Comtois).
  • Michael Tanana
    Lyssn, Seattle, WA.
  • Christina S Soma
    Department of Educational Psychology.
  • Kate A Comtois
    Lyssn.io, Seattle (Imel, Pace, Pruett, Tanana, Soma, Atkins); Protocall Services, Portland, Oregon (Pendergraft); Harborview Medical Center, University of Washington, Seattle (Comtois).
  • David C Atkins
    University of Washington.