Designing a Clinical Decision Support Tool That Leverages Machine Learning for Suicide Risk Prediction: Development Study in Partnership With Native American Care Providers.
Native American health
implementation
machine learning
suicide prevention
Journal
JMIR public health and surveillance
ISSN: 2369-2960
Titre abrégé: JMIR Public Health Surveill
Pays: Canada
ID NLM: 101669345
Informations de publication
Date de publication:
02 09 2021
02 09 2021
Historique:
received:
20
10
2020
accepted:
15
06
2021
revised:
10
03
2021
entrez:
2
9
2021
pubmed:
3
9
2021
medline:
6
11
2021
Statut:
epublish
Résumé
Machine learning algorithms for suicide risk prediction have been developed with notable improvements in accuracy. Implementing these algorithms to enhance clinical care and reduce suicide has not been well studied. This study aims to design a clinical decision support tool and appropriate care pathways for community-based suicide surveillance and case management systems operating on Native American reservations. Participants included Native American case managers and supervisors (N=9) who worked on suicide surveillance and case management programs on 2 Native American reservations. We used in-depth interviews to understand how case managers think about and respond to suicide risk. The results from interviews informed a draft clinical decision support tool, which was then reviewed with supervisors and combined with appropriate care pathways. Case managers reported acceptance of risk flags based on a predictive algorithm in their surveillance system tools, particularly if the information was available in a timely manner and used in conjunction with their clinical judgment. Implementation of risk flags needed to be programmed on a dichotomous basis, so the algorithm could produce output indicating high versus low risk. To dichotomize the continuous predicted probabilities, we developed a cutoff point that favored specificity, with the understanding that case managers' clinical judgment would help increase sensitivity. Suicide risk prediction algorithms show promise, but implementation to guide clinical care remains relatively elusive. Our study demonstrates the utility of working with partners to develop and guide the operationalization of risk prediction algorithms to enhance clinical care in a community setting.
Sections du résumé
BACKGROUND
Machine learning algorithms for suicide risk prediction have been developed with notable improvements in accuracy. Implementing these algorithms to enhance clinical care and reduce suicide has not been well studied.
OBJECTIVE
This study aims to design a clinical decision support tool and appropriate care pathways for community-based suicide surveillance and case management systems operating on Native American reservations.
METHODS
Participants included Native American case managers and supervisors (N=9) who worked on suicide surveillance and case management programs on 2 Native American reservations. We used in-depth interviews to understand how case managers think about and respond to suicide risk. The results from interviews informed a draft clinical decision support tool, which was then reviewed with supervisors and combined with appropriate care pathways.
RESULTS
Case managers reported acceptance of risk flags based on a predictive algorithm in their surveillance system tools, particularly if the information was available in a timely manner and used in conjunction with their clinical judgment. Implementation of risk flags needed to be programmed on a dichotomous basis, so the algorithm could produce output indicating high versus low risk. To dichotomize the continuous predicted probabilities, we developed a cutoff point that favored specificity, with the understanding that case managers' clinical judgment would help increase sensitivity.
CONCLUSIONS
Suicide risk prediction algorithms show promise, but implementation to guide clinical care remains relatively elusive. Our study demonstrates the utility of working with partners to develop and guide the operationalization of risk prediction algorithms to enhance clinical care in a community setting.
Identifiants
pubmed: 34473065
pii: v7i9e24377
doi: 10.2196/24377
pmc: PMC8446841
doi:
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Langues
eng
Sous-ensembles de citation
IM
Pagination
e24377Subventions
Organisme : NIMH NIH HHS
ID : K01 MH116335
Pays : United States
Organisme : NLM NIH HHS
ID : T15 LM007450
Pays : United States
Organisme : NIMH NIH HHS
ID : U19 MH113136
Pays : United States
Informations de copyright
©Emily E Haroz, Fiona Grubin, Novalene Goklish, Shardai Pioche, Mary Cwik, Allison Barlow, Emma Waugh, Jason Usher, Matthew C Lenert, Colin G Walsh. Originally published in JMIR Public Health and Surveillance (https://publichealth.jmir.org), 02.09.2021.
Références
Psychiatr Serv. 2001 Jun;52(6):828-33
pubmed: 11376235
Br J Psychiatry. 2017 Jun;210(6):396-402
pubmed: 28428338
Crisis. 2013 Jan 1;34(1):32-41
pubmed: 22846445
Am J Public Health. 2014 Jun;104 Suppl 3:e18-23
pubmed: 24754618
JAMA Psychiatry. 2015 Jan;72(1):49-57
pubmed: 25390793
Psychol Bull. 2017 Feb;143(2):187-232
pubmed: 27841450
Psychol Med. 2016 Jul;46(9):2009-10
pubmed: 27091309
Behav Sci Law. 2019 May;37(3):214-222
pubmed: 30609102
Adm Policy Ment Health. 2015 Sep;42(5):533-44
pubmed: 24193818
JAMA Psychiatry. 2019 Aug 1;76(8):869-870
pubmed: 31241754
Am J Community Psychol. 2019 Sep;64(1-2):137-145
pubmed: 31313327
Suicide Life Threat Behav. 2019 Apr;49(2):614-626
pubmed: 29665120
Am J Public Health. 2016 Dec;106(12):2183-2189
pubmed: 27736202
Br J Psychiatry. 2017 Jun;210(6):387-395
pubmed: 28302700
J Am Med Inform Assoc. 2017 Nov 1;24(6):1102-1110
pubmed: 28637180
Mol Psychiatry. 2020 Jan;25(1):168-179
pubmed: 31570777
Inj Prev. 2019 Sep;25(Suppl 1):i18-i24
pubmed: 30317220
Int J Methods Psychiatr Res. 2017 Sep;26(3):
pubmed: 28675617
Suicide Life Threat Behav. 2020 Apr;50(2):422-436
pubmed: 31692064
J Child Psychol Psychiatry. 2018 Dec;59(12):1261-1270
pubmed: 29709069
Implement Sci. 2009 Aug 07;4:50
pubmed: 19664226
JAMA Psychiatry. 2019 Jun 1;76(6):642-651
pubmed: 30865249
Am Indian Alsk Native Ment Health Res. 2016;23(1):105-124
pubmed: 28562844