Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: May 25, 2026

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Evaluation of suicide behavior screening tools using machine learning and variable importance measures.

Nathan C Carnes¹, James Zouris¹, Craig J Bryan²

¹Naval Health Research Center, San Diego, CA, United States of America.

Journal of Affective Disorders

|May 23, 2026

Summary

This summary is machine-generated.

Related Concept Videos

Survival Tree

Survival Tree

Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a survival tree begins...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Developmental predictors of suicide attempts from childhood to early adulthood: a 15-year prospective cohort study.

Lancet regional health. Americas·2026

Same author

Injury Correlates of Acute Stress Disorder Following Combat Injury.

Military medicine·2026

Same author

Does ecological momentary assessment improve prediction of suicide risk among military personnel and veterans, and how frequent should it be?

Journal of affective disorders·2026

Same author

Feasibility, Acceptability, and Impact of the Couples Crisis Response Plan (CCRP) to Reduce Post-Discharge Suicide Risk: A Randomized Controlled Trial.

Suicide & life-threatening behavior·2026

Same author

Psychometric Properties and Longitudinal Predictors of the Columbia Suicide Severity Rating Scale (C-SSRS) in a Brazilian Community Cohort: A 15-Year Follow-Up Study.

Suicide & life-threatening behavior·2026

Same author

Massed Brief Cognitive Behavioral Therapy (mBCBT) for Suicide Prevention: Results of a Pragmatic Clinical Trial.

Behavior therapy·2026

Same journal

Corrigendum to "Association between lithium and arterial atherosclerosis in physically healthy bipolar disorder" [J. Affect. Disord. 412 (2026): 122115].

Journal of affective disorders·2026

Same journal

Randomized controlled trial of a modular, transdiagnostic, cognitive-behavioral anxiety intervention versus primary care behavioral health treatment as usual.

Journal of affective disorders·2026

Same journal

Trait emotional regulation mediates the protective role of resting-state brain activity against depressive symptoms in late adolescence.

Journal of affective disorders·2026

Same journal

Domain- and item-level symptom thresholds for severe cognitive impairment in major depressive disorder.

Journal of affective disorders·2026

Same journal

Efficacy and safety of Dimdazenil in primary insomnia and depressive episodes/bipolar depressive episode with insomnia: A post-marketing, randomized, open-label, positive-controlled study.

Journal of affective disorders·2026

Same journal

The longitudinal relationship between co-rumination and depressive symptoms in adolescents: A systematic review and meta-analytic structural equation modeling.

Journal of affective disorders·2026

See all related articles

This study enhanced suicide risk screening in military primary care using machine learning. It identified sleep problems and self-conscious emotions as key factors for improving suicide attempt prediction.

Area of Science:

Psychiatry
Machine Learning
Public Health

Background:

Suicide screening in military primary care often uses limited self-report questions.
The PRImary care Screening Methods (PRISM) study aims to improve screening predictive validity.

Purpose of the Study:

To enhance suicide screening in military primary care by identifying key risk and protective factors.
To investigate the utility of machine learning for improving suicide risk assessment.

Main Methods:

Utilized random forests with undersampling and discretized data on 1522 participants.
Analyzed 875 features to predict suicide attempts within 12 months post-baseline.
Employed variable importance measures (VIMs) to identify significant factors.

Keywords:

Machine learning Military Risk and protective factors Self-conscious emotions Sleep disorders Suicide attempt

Related Experiment Videos

Last Updated: May 25, 2026

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Main Results:

Achieved 68.7% out-of-bag accuracy in predicting suicide attempts.
Top predictors included sleep disturbances, trauma-related nightmares, time organization, suicidal ideation, and social self-consciousness.
Social self-consciousness ('feel like people laugh at you') emerged as a significant risk factor, enhancing screening sensitivity and specificity.

Conclusions:

Sleep dysregulation and self-conscious emotions play a crucial role in suicidal behavior.
Machine learning effectively identifies individuals at risk for suicidal behavior in primary care settings.
Supplementing standard screening with identified factors improves prediction accuracy.