A direct comparison of theory-driven and machine learning prediction of suicide: A meta-analysis.

Theoretically-driven models of suicide have long guided suicidology; however, an approach employing machine learning models has recently emerged in the field. Some have suggested that machine learning models yield improved prediction as compared to theoretical approaches, but to date, this has not b...

Full description

Saved in:
Bibliographic Details
Main Authors: Katherine M Schafer, Grace Kennedy, Austin Gallyer, Philip Resnik
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2021-01-01
Series:PLoS ONE
Online Access:https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0249833&type=printable
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850181421204766720
author Katherine M Schafer
Grace Kennedy
Austin Gallyer
Philip Resnik
author_facet Katherine M Schafer
Grace Kennedy
Austin Gallyer
Philip Resnik
author_sort Katherine M Schafer
collection DOAJ
description Theoretically-driven models of suicide have long guided suicidology; however, an approach employing machine learning models has recently emerged in the field. Some have suggested that machine learning models yield improved prediction as compared to theoretical approaches, but to date, this has not been investigated in a systematic manner. The present work directly compares widely researched theories of suicide (i.e., BioSocial, Biological, Ideation-to-Action, and Hopelessness Theories) to machine learning models, comparing the accuracy between the two differing approaches. We conducted literature searches using PubMed, PsycINFO, and Google Scholar, gathering effect sizes from theoretically-relevant constructs and machine learning models. Eligible studies were longitudinal research articles that predicted suicide ideation, attempts, or death published prior to May 1, 2020. 124 studies met inclusion criteria, corresponding to 330 effect sizes. Theoretically-driven models demonstrated suboptimal prediction of ideation (wOR = 2.87; 95% CI, 2.65-3.09; k = 87), attempts (wOR = 1.43; 95% CI, 1.34-1.51; k = 98), and death (wOR = 1.08; 95% CI, 1.01-1.15; k = 78). Generally, Ideation-to-Action (wOR = 2.41, 95% CI = 2.21-2.64, k = 60) outperformed Hopelessness (wOR = 1.83, 95% CI 1.71-1.96, k = 98), Biological (wOR = 1.04; 95% CI .97-1.11, k = 100), and BioSocial (wOR = 1.32, 95% CI 1.11-1.58, k = 6) theories. Machine learning provided superior prediction of ideation (wOR = 13.84; 95% CI, 11.95-16.03; k = 33), attempts (wOR = 99.01; 95% CI, 68.10-142.54; k = 27), and death (wOR = 17.29; 95% CI, 12.85-23.27; k = 7). Findings from our study indicated that across all theoretically-driven models, prediction of suicide-related outcomes was suboptimal. Notably, among theories of suicide, theories within the Ideation-to-Action framework provided the most accurate prediction of suicide-related outcomes. When compared to theoretically-driven models, machine learning models provided superior prediction of suicide ideation, attempts, and death.
format Article
id doaj-art-a758aca4dc1c4845a77fbaffcc5e47cf
institution OA Journals
issn 1932-6203
language English
publishDate 2021-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-a758aca4dc1c4845a77fbaffcc5e47cf2025-08-20T02:17:54ZengPublic Library of Science (PLoS)PLoS ONE1932-62032021-01-01164e024983310.1371/journal.pone.0249833A direct comparison of theory-driven and machine learning prediction of suicide: A meta-analysis.Katherine M SchaferGrace KennedyAustin GallyerPhilip ResnikTheoretically-driven models of suicide have long guided suicidology; however, an approach employing machine learning models has recently emerged in the field. Some have suggested that machine learning models yield improved prediction as compared to theoretical approaches, but to date, this has not been investigated in a systematic manner. The present work directly compares widely researched theories of suicide (i.e., BioSocial, Biological, Ideation-to-Action, and Hopelessness Theories) to machine learning models, comparing the accuracy between the two differing approaches. We conducted literature searches using PubMed, PsycINFO, and Google Scholar, gathering effect sizes from theoretically-relevant constructs and machine learning models. Eligible studies were longitudinal research articles that predicted suicide ideation, attempts, or death published prior to May 1, 2020. 124 studies met inclusion criteria, corresponding to 330 effect sizes. Theoretically-driven models demonstrated suboptimal prediction of ideation (wOR = 2.87; 95% CI, 2.65-3.09; k = 87), attempts (wOR = 1.43; 95% CI, 1.34-1.51; k = 98), and death (wOR = 1.08; 95% CI, 1.01-1.15; k = 78). Generally, Ideation-to-Action (wOR = 2.41, 95% CI = 2.21-2.64, k = 60) outperformed Hopelessness (wOR = 1.83, 95% CI 1.71-1.96, k = 98), Biological (wOR = 1.04; 95% CI .97-1.11, k = 100), and BioSocial (wOR = 1.32, 95% CI 1.11-1.58, k = 6) theories. Machine learning provided superior prediction of ideation (wOR = 13.84; 95% CI, 11.95-16.03; k = 33), attempts (wOR = 99.01; 95% CI, 68.10-142.54; k = 27), and death (wOR = 17.29; 95% CI, 12.85-23.27; k = 7). Findings from our study indicated that across all theoretically-driven models, prediction of suicide-related outcomes was suboptimal. Notably, among theories of suicide, theories within the Ideation-to-Action framework provided the most accurate prediction of suicide-related outcomes. When compared to theoretically-driven models, machine learning models provided superior prediction of suicide ideation, attempts, and death.https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0249833&type=printable
spellingShingle Katherine M Schafer
Grace Kennedy
Austin Gallyer
Philip Resnik
A direct comparison of theory-driven and machine learning prediction of suicide: A meta-analysis.
PLoS ONE
title A direct comparison of theory-driven and machine learning prediction of suicide: A meta-analysis.
title_full A direct comparison of theory-driven and machine learning prediction of suicide: A meta-analysis.
title_fullStr A direct comparison of theory-driven and machine learning prediction of suicide: A meta-analysis.
title_full_unstemmed A direct comparison of theory-driven and machine learning prediction of suicide: A meta-analysis.
title_short A direct comparison of theory-driven and machine learning prediction of suicide: A meta-analysis.
title_sort direct comparison of theory driven and machine learning prediction of suicide a meta analysis
url https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0249833&type=printable
work_keys_str_mv AT katherinemschafer adirectcomparisonoftheorydrivenandmachinelearningpredictionofsuicideametaanalysis
AT gracekennedy adirectcomparisonoftheorydrivenandmachinelearningpredictionofsuicideametaanalysis
AT austingallyer adirectcomparisonoftheorydrivenandmachinelearningpredictionofsuicideametaanalysis
AT philipresnik adirectcomparisonoftheorydrivenandmachinelearningpredictionofsuicideametaanalysis
AT katherinemschafer directcomparisonoftheorydrivenandmachinelearningpredictionofsuicideametaanalysis
AT gracekennedy directcomparisonoftheorydrivenandmachinelearningpredictionofsuicideametaanalysis
AT austingallyer directcomparisonoftheorydrivenandmachinelearningpredictionofsuicideametaanalysis
AT philipresnik directcomparisonoftheorydrivenandmachinelearningpredictionofsuicideametaanalysis