Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Neighborhood Disadvantage as a Moderator of Children's Response to a Dyadic Positive Affect Intervention for Children of Mothers with Depressive Symptoms.

Journal of child and adolescent psychopharmacology·2026
Same author

Modeling Rare Events and Nonmonotone Nonignorable Missingness of Time-Varying Outcomes and Predictors in Binary Time-Series Daily Diary Data: A Bayesian Selection Model.

Psychometrika·2026
Same author

Factors influencing patient discussion of genetic test results with health care providers: Insights from a hospital-based population genetic screening program.

Genetics in medicine : official journal of the American College of Medical Genetics·2026
Same author

The Role of Neurobehavioral Attention Bias on Relations between Preference for Digital Media Use and Social Anxiety Symptoms Across Adolescence.

Brain and environment·2026
Same author

Peer and familial influences on the association between behavioral inhibition and trajectories of social anxiety symptoms across adolescence.

Journal of research on adolescence : the official journal of the Society for Research on Adolescence·2026
Same author

Associations Between New Mothers' Neural Reward Response and Perceptions of Their Own Infant.

Developmental psychobiology·2026

Related Experiment Video

Updated: Jan 9, 2026

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
07:31

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

7.5K

Concurrent and Prospective Prediction of Suicidal Ideation in Adolescents Using Multimethod Data and Machine

Lindsay Dickey1, Griffin B Murch1, Samantha Pegg1

  • 1Vanderbilt University, Nashville, Tennessee.

JAACAP Open
|December 10, 2025
PubMed
Summary

Machine learning accurately predicted adolescent suicidal ideation using diverse data. Cognitive depression symptoms and positive affect were key predictors, outperforming chronic stress and neural measures.

Keywords:
adolescentsemotionmachine learningrisk factorssuicidal ideation

More Related Videos

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment
05:19

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment

Published on: July 7, 2023

3.2K
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

11.1K

Related Experiment Videos

Last Updated: Jan 9, 2026

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
07:31

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

7.5K
Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment
05:19

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment

Published on: July 7, 2023

3.2K
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

11.1K

Area of Science:

  • Adolescent psychiatry
  • Machine learning in healthcare
  • Suicidality research

Background:

  • Adolescent suicidal ideation (SI) rates remain high despite prevention efforts.
  • Identifying robust predictors of SI is crucial for effective intervention.
  • Current predictive models need integration of diverse risk factors and methods.

Purpose of the Study:

  • To predict concurrent and prospective suicidal ideation (SI) in adolescents using machine learning.
  • To evaluate the utility of multimethod data including clinical, self-report, and neural measures.
  • To identify key predictors of SI in a sample of adolescents at risk for depression.

Main Methods:

  • Utilized machine learning (random forest classification) with synthetic minority oversampling technique.
  • Employed multimethod data: clinical diagnoses, chronic stress, internalizing symptoms, affect, and neural measures.
  • Assessed SI at baseline, 6-month, and 1-year follow-ups using self-report and clinical interviews.

Main Results:

  • Random forest models achieved high precision and recall (F1s = 0.81-0.85) in predicting SI.
  • Cognitive symptoms of depression and average positive affect emerged as significant predictors.
  • Chronic stress and neural measures showed limited predictive value in this cohort.

Conclusions:

  • Machine learning with multimethod data shows promise for predicting adolescent SI.
  • Further research is needed to replicate and extend these findings.
  • Highlights the importance of cognitive and affective factors in adolescent suicidality.