Implementing Machine Learning Models for Suicide Risk Prediction in Clinical Practice: Focus Group Study With Hospital Providers (Preprint)
Authors:
- Kate H BentleyKBKate H Bentley
- Kelly L ZuromskiKZKelly L Zuromski
- Rebecca G FortgangRFRebecca G Fortgang
- Emily M MadsenEMEmily M Madsen
- Daniel KesslerDKDaniel Kessler
- Hyunjoon LeeHLHyunjoon Lee
- Matthew K NockMNMatthew K Nock
- Ben Y ReisBRBen Y Reis
- Victor M CastroVCVictor M Castro
- Jordan W SmollerJSJordan W Smoller
Preprint
- 3 June 2021
- preprint
- Published by JMIR Publications Inc. in JMIR Preprints
Abstract
BACKGROUND Interest in developing machine learning models that use electronic health record data to predict patients’ risk of suicidal behavior has recently proliferated. However, whether and how such models might be implemented and useful in clinical practice remain unknown. To ultimately make automated suicide risk–prediction models useful in practice, and thus better prevent patient suicides, it is critical to partner with key stakeholders, including the frontline providers who will be using such tools, at each stage of the implementation process. OBJECTIVE The aim of this focus group study is to inform ongoing and future efforts to deploy suicide risk–prediction models in clinical practice. The specific goals are to better understand hospital providers’ current practices for assessing and managing suicide risk; determine providers’ perspectives on using automated suicide risk–prediction models in practice; and identify barriers, facilitators, recommendations, and factors to consider. METHODS We conducted 10 two-hour focus groups with a total of 40 providers from psychiatry, internal medicine and primary care, emergency medicine, and obstetrics and gynecology departments within an urban academic medical center. Audio recordings of open-ended group discussions were transcribed and coded for relevant and recurrent themes by 2 independent study staff members. All coded text was reviewed and discrepancies were resolved in consensus meetings with doctoral-level staff. RESULTS Although most providers reported using standardized suicide risk assessment tools in their clinical practices, existing tools were commonly described as unhelpful and providers indicated dissatisfaction with current suicide risk assessment methods. Overall, providers’ general attitudes toward the practical use of automated suicide risk–prediction models and corresponding clinical decision support tools were positive. Providers were especially interested in the potential to identify high-risk patients who might be missed by traditional screening methods. Some expressed skepticism about the potential usefulness of these models in routine care; specific barriers included concerns about liability, alert fatigue, and increased demand on the health care system. Key facilitators included presenting specific patient-level features contributing to risk scores, emphasizing changes in risk over time, and developing systematic clinical workflows and provider training. Participants also recommended considering risk-prediction windows, timing of alerts, who will have access to model predictions, and variability across treatment settings. CONCLUSIONS Providers were dissatisfied with current suicide risk assessment methods and were open to the use of a machine learning–based risk-prediction system to inform clinical decision-making. They also raised multiple concerns about potential barriers to the usefulness of this approach and suggested several possible facilitators. Future efforts in this area will benefit from incorporating systematic qualitative feedback from providers, patients, administrators, and payers on the use of these new approaches in routine care, especially given the complex, sensitive, and unfortunately still stigmatized nature of suicide risk.Keywords
All Related Versions
- Published version: JMIR Formative Research, 6 (3), e30946.
This publication has 33 references indexed in Scilit:
- Predicting Suicidal Behavior From Longitudinal Electronic Health RecordsAmerican Journal of Psychiatry, 2017
- Risk factors for suicidal thoughts and behaviors: A meta-analysis of 50 years of research.Psychological Bulletin, 2017
- Which are the most useful scales for predicting repeat self-harm? A systematic review evaluating risk scales using measures of diagnostic accuracyBMJ Open, 2016
- Effectiveness of Computerized Decision Support Systems Linked to Electronic Health Records: A Systematic Review and Meta-AnalysisAmerican Journal of Public Health, 2014
- Health Care Contacts in the Year Before Suicide DeathJournal of General Internal Medicine, 2014
- The Columbia–Suicide Severity Rating Scale: Initial Validity and Internal Consistency Findings From Three Multisite Studies With Adolescents and AdultsAmerican Journal of Psychiatry, 2011
- Suicide-related discussions with depressed primary care patients in the USA: gender and quality gaps. A mixed methods analysisBMJ Open, 2011
- Contact With Mental Health and Primary Care Providers Before Suicide: A Review of the EvidenceAmerican Journal of Psychiatry, 2002
- The PHQ-9Journal of General Internal Medicine, 2001
- Duration neglect in retrospective evaluations of affective episodes.Journal of Personality and Social Psychology, 1993