Florida State University, Department of Psychology, Tallahassee, Florida, United States of America.
Walter Reed National Military Medical Center, Bethesda, Maryland, United States of America.
PLoS One. 2021 Apr 12;16(4):e0249833. doi: 10.1371/journal.pone.0249833. eCollection 2021.
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.
理论驱动的自杀模型长期以来一直指导着自杀学研究；然而，最近该领域出现了一种采用机器学习模型的方法。有人认为，机器学习模型的预测效果优于理论方法，但迄今为止，这一点尚未以系统的方式进行研究。本研究直接比较了广泛研究的自杀理论（即生物社会、生物学、意念-行动和绝望理论）与机器学习模型，比较了这两种不同方法的准确性。我们使用 PubMed、PsycINFO 和 Google Scholar 进行文献检索，从理论相关结构和机器学习模型中收集效应量。合格的研究是预测自杀意念、自杀企图或死亡的前瞻性研究文章，发表时间在 2020 年 5 月 1 日之前。共有 124 项研究符合纳入标准，对应 330 个效应量。理论驱动的模型对意念（wOR = 2.87；95%CI，2.65-3.09；k = 87）、企图（wOR = 1.43；95%CI，1.34-1.51；k = 98）和死亡（wOR = 1.08；95%CI，1.01-1.15；k = 78）的预测效果不佳。一般来说，意念-行动（wOR = 2.41，95%CI = 2.21-2.64，k = 60）优于绝望（wOR = 1.83，95%CI 1.71-1.96，k = 98）、生物学（wOR = 1.04；95%CI.97-1.11，k = 100）和生物社会（wOR = 1.32，95%CI 1.11-1.58，k = 6）理论。机器学习对意念（wOR = 13.84；95%CI，11.95-16.03；k = 33）、企图（wOR = 99.01；95%CI，68.10-142.54；k = 27）和死亡（wOR = 17.29；95%CI，12.85-23.27；k = 7）的预测效果均优于理论驱动模型。我们研究的结果表明，在所有理论驱动的模型中，自杀相关结果的预测效果均不佳。值得注意的是，在自杀理论中，意念-行动框架内的理论对自杀相关结果的预测最为准确。与理论驱动的模型相比，机器学习模型对自杀意念、自杀企图和死亡的预测效果更好。
Depress Anxiety. 2017-10-24
Transl Psychiatry. 2016-9-13
J Med Internet Res. 2025-4-17
Curr Psychiatry Rep. 2025-5
JMIR Public Health Surveill. 2025-1-29
BMC Psychiatry. 2024-11-21
Npj Ment Health Res. 2024-11-6
Suicide Life Threat Behav. 2021-2
Int J Environ Res Public Health. 2020-8-15
JAMA Psychiatry. 2019-6-1
Suicide Life Threat Behav. 2018-8-11
J Child Psychol Psychiatry. 2018-3-1
Zotero 插件
