Predicting Lifetime Suicide Attempts in a Community Sample of Adolescents Using Machine Learning Algorithms

被引:9
作者
Jankowsky, Kristin [1 ,2 ]
Steger, Diana [1 ]
Schroeders, Ulrich [1 ]
机构
[1] Univ Kassel, Kassel, Germany
[2] Univ Kassel, Inst Psychol, Holland Str 36-38, D-34127 Kassel, Germany
基金
英国科研创新办公室;
关键词
suicide prediction; suicide risk screening; adolescents; machine learning; NONSUICIDAL SELF-INJURY; ATTEMPT HISTORY; YOUNG-ADULTS; RISK-FACTORS; METAANALYSIS; HARM; BEHAVIORS; PREVENTION; THOUGHTS; IDEATION;
D O I
10.1177/10731911231167490
中图分类号
B849 [应用心理学];
学科分类号
040203 ;
摘要
Suicide is a major global health concern and a prominent cause of death in adolescents. Previous research on suicide prediction has mainly focused on clinical or adult samples. To prevent suicides at an early stage, however, it is important to screen for risk factors in a community sample of adolescents. We compared the accuracy of logistic regressions, elastic net regressions, and gradient boosting machines in predicting suicide attempts by 17-year-olds in the Millennium Cohort Study (N = 7,347), combining a large set of self- and other-reported variables from different categories. Both machine learning algorithms outperformed logistic regressions and achieved similar balanced accuracies (.76 when using data 3 years before the self-reported lifetime suicide attempts and .85 when using data from the same measurement wave). We identified essential variables that should be considered when screening for suicidal behavior. Finally, we discuss the usefulness of complex machine learning models in suicide prediction.
引用
收藏
页码:557 / 573
页数:17
相关论文
共 74 条
[1]   The meta-analysis of clinical judgment project:: Fifty-six years of accumulated research on clinical versus statistical prediction [J].
AEgisdottir, S ;
White, MJ ;
Spengler, PM ;
Maugherman, AS ;
Anderson, LA ;
Cook, RS ;
Nichols, CN ;
Lampropoulos, GK ;
Walker, BS ;
Cohen, G ;
Rush, JD .
COUNSELING PSYCHOLOGIST, 2006, 34 (03) :341-382
[2]   How we ask matters: The impact of question wording in single-item measurement of suicidal thoughts and behaviors [J].
Ammerman, Brooke A. ;
Burke, Taylor A. ;
Jacobucci, Ross ;
McClure, Kenneth .
PREVENTIVE MEDICINE, 2021, 152 :106472
[3]   Development and Validation of Empirically Derived Frequency Criteria for NSSI Disorder Using Exploratory Data Mining [J].
Ammerman, Brooke A. ;
Jacobucci, Ross ;
Kleiman, Evan M. ;
Muehlenkamp, Jennifer J. ;
McCloskey, Michael S. .
PSYCHOLOGICAL ASSESSMENT, 2017, 29 (02) :221-231
[4]  
[Anonymous], 2015, B WORLD HEALTH ORGAN, V93, P516
[5]   Nonsuicidal Self-Injury and Suicidal Behaviors in Girls: The Case for Targeted Prevention in Preadolescence [J].
Beauchaine, Theodore P. ;
Hinshaw, Stephen P. ;
Bridge, Jeffrey A. .
CLINICAL PSYCHOLOGICAL SCIENCE, 2019, 7 (04) :643-667
[6]   Method of self-harm in adolescents and young adults and risk of subsequent suicide [J].
Beckman, Karin ;
Mittendorfer-Rutz, Ellenor ;
Waern, Margda ;
Larsson, Henrik ;
Runeson, Bo ;
Dahlin, Marie .
JOURNAL OF CHILD PSYCHOLOGY AND PSYCHIATRY, 2018, 59 (09) :948-956
[7]   Prediction Models for Suicide Attempts and Deaths: A Systematic Review and Simulation [J].
Belsher, Bradley E. ;
Smolenski, Derek J. ;
Pruitt, Larry D. ;
Bush, Nigel E. ;
Beech, Erin H. ;
Workman, Don E. ;
Morgan, Rebecca L. ;
Evatt, Daniel P. ;
Tucker, Jennifer ;
Skopp, Nancy A. .
JAMA PSYCHIATRY, 2019, 76 (06) :642-651
[8]   Artificial Intelligence and Suicide Prevention: A Systematic Review of Machine Learning Investigations [J].
Bernert, Rebecca A. ;
Hilberg, Amanda M. ;
Melia, Ruth ;
Kim, Jane Paik ;
Shah, Nigam H. ;
Abnousi, Freddy .
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH, 2020, 17 (16) :1-25
[9]   Childhood adversity and risk of suicide: cohort study of 548 721 adolescents and young adults in Sweden [J].
Bjorkenstam, Charlotte ;
Kosidou, Kyriaki ;
Bjorkenstam, Emma .
BMJ-BRITISH MEDICAL JOURNAL, 2017, 357 :j1334
[10]   Treating PTSD Within the Context of Heightened Suicide Risk [J].
Bryan, Craig J. .
CURRENT PSYCHIATRY REPORTS, 2016, 18 (08)