Personality predicts internalizing symptoms and quality of life in police cadets: a comparison of artificial intelligence and parametric approaches.

IF 3 Q1 CRIMINOLOGY & PENOLOGY

Health and Justice Pub Date : 2025-07-04 DOI:10.1186/s40352-025-00351-7

Macià Buades-Rotger, Ana Martínez Catena, Guillermo Recio, Mireia Cano Gallent, Jordi Niñerola I Maymí, Anna Figueras Masip, David Gallardo-Pujol

{"title":"Personality predicts internalizing symptoms and quality of life in police cadets: a comparison of artificial intelligence and parametric approaches.","authors":"Macià Buades-Rotger, Ana Martínez Catena, Guillermo Recio, Mireia Cano Gallent, Jordi Niñerola I Maymí, Anna Figueras Masip, David Gallardo-Pujol","doi":"10.1186/s40352-025-00351-7","DOIUrl":null,"url":null,"abstract":"Background: Police cadets undergo persistent and elevated stress due to continuous training and evaluation. Identifying resilience and risk factors in this population can thus crucially inform management decisions within the police force. Here, in two large cohorts of police cadets (n = 1069, 30% women and n = 1377, 35% women) we investigated whether broad personality traits could predict internalizing symptoms (somatization, depression, and anxiety) as well as mental health-related quality of life (MHRQoL). Moreover, we compared seven popular artificial intelligence and linear regression models (Elastic Net, General Linear Model, Lasso Regression, Neural Networks, Random Forests, and Support Vector Regression) in predicting MHRQoL as a function of all other variables.Results: A Random Forest accounted for about half of the observed variance in MHRQoL, and outperformed all other models by up to 12% in an out-of-sample cross-validation. In all analyses, emotional stability emerged as the primary personality trait linked to MHRQoL, with anxiety and somatization symptoms partially mediating this relationship.Conclusions: Our findings delineate the personality factors that best predict internalizing symptoms and MHRQoL among cadets, and tentatively suggest that Random Forest models might be a powerful forecasting tool in police management.","PeriodicalId":37843,"journal":{"name":"Health and Justice","volume":"13 1","pages":"43"},"PeriodicalIF":3.0000,"publicationDate":"2025-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12228195/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Health and Justice","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1186/s40352-025-00351-7","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CRIMINOLOGY & PENOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Background: Police cadets undergo persistent and elevated stress due to continuous training and evaluation. Identifying resilience and risk factors in this population can thus crucially inform management decisions within the police force. Here, in two large cohorts of police cadets (n = 1069, 30% women and n = 1377, 35% women) we investigated whether broad personality traits could predict internalizing symptoms (somatization, depression, and anxiety) as well as mental health-related quality of life (MHRQoL). Moreover, we compared seven popular artificial intelligence and linear regression models (Elastic Net, General Linear Model, Lasso Regression, Neural Networks, Random Forests, and Support Vector Regression) in predicting MHRQoL as a function of all other variables.

Results: A Random Forest accounted for about half of the observed variance in MHRQoL, and outperformed all other models by up to 12% in an out-of-sample cross-validation. In all analyses, emotional stability emerged as the primary personality trait linked to MHRQoL, with anxiety and somatization symptoms partially mediating this relationship.

Conclusions: Our findings delineate the personality factors that best predict internalizing symptoms and MHRQoL among cadets, and tentatively suggest that Random Forest models might be a powerful forecasting tool in police management.

查看原文本刊更多论文

人格预测警察学员的内化症状和生活质量：人工智能和参数化方法的比较。

背景：由于持续的训练和评估，警察学员承受着持续和不断增加的压力。因此，确定这一人群的复原力和风险因素可以为警察部队的管理决策提供重要信息。在这里，在两个大型的警察学员队列中（n = 1069, 30%为女性和n = 1377, 35%为女性），我们调查了广泛的人格特征是否可以预测内化症状（躯体化、抑郁和焦虑）以及心理健康相关的生活质量（MHRQoL）。此外，我们比较了七种流行的人工智能和线性回归模型（弹性网络、一般线性模型、Lasso回归、神经网络、随机森林和支持向量回归）在预测MHRQoL作为所有其他变量的函数方面的效果。结果：随机森林在MHRQoL中约占观察到的方差的一半，并且在样本外交叉验证中优于所有其他模型高达12%。在所有分析中，情绪稳定性是与MHRQoL相关的主要人格特征，焦虑和躯体化症状部分介导了这种关系。结论：我们的研究结果描述了最能预测学员内化症状和MHRQoL的人格因素，并初步表明随机森林模型可能是警察管理中一个强大的预测工具。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Health and Justice Social Sciences-Law

CiteScore

4.10

自引率

8.60%

发文量

审稿时长

13 weeks

期刊介绍： Health & Justice is open to submissions from public health, criminology and criminal justice, medical science, psychology and clinical sciences, sociology, neuroscience, biology, anthropology and the social sciences, and covers a broad array of research types. It publishes original research, research notes (promising issues that are smaller in scope), commentaries, and translational notes (possible ways of introducing innovations in the justice system). Health & Justice aims to: Present original experimental research on the area of health and well-being of people involved in the adult or juvenile justice system, including people who work in the system; Present meta-analysis or systematic reviews in the area of health and justice for those involved in the justice system; Provide an arena to present new and upcoming scientific issues; Present translational science—the movement of scientific findings into practice including programs, procedures, or strategies; Present implementation science findings to advance the uptake and use of evidence-based practices; and, Present protocols and clinical practice guidelines. As an open access journal, Health & Justice aims for a broad reach, including researchers across many disciplines as well as justice practitioners (e.g. judges, prosecutors, defenders, probation officers, treatment providers, mental health and medical personnel working with justice-involved individuals, etc.). The sections of the journal devoted to translational and implementation sciences are primarily geared to practitioners and justice actors with special attention to the techniques used.