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

Anxiety statistically mediates the association between stress and difficulty identifying feelings while depression shows no effect: a cross-sectional study in college students.

BMC psychology·2026
Same author

Phenotypic Clustering of Addictions Reveals Impulsivity Links to Internalizing Disorders: A Network Analysis.

Alpha psychiatry·2026
Same author

Adaptation and validation of the Turkish version of The Brief Screener for Substance and Behavioral Addiction (SSBA).

Frontiers in psychology·2026
Same author

Translational assessment of butyrylcholinesterase activity as a diagnostic biomarker for depression using a chemiluminescent probe.

Scientific reports·2026
Same author

Mitochondrial Insights into Lithium Response in Bipolar Disorder: A State-of-the-Art Review.

Neuropsychobiology·2025
Same author

Parental experiences and support needs following a prenatal diagnosis of congenital heart disease: a qualitative study across the continuum of care in Turkey.

BMJ public health·2025

Related Experiment Video

Updated: May 10, 2025

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

6.9K

Machine learning based identification of suicidal ideation using non-suicidal predictors in a university mental

Muhammed Ballı1, Asli Ercan Dogan2, Sevin Hun Senol3

  • 1Neuroscience PhD Program, Koç University Graduate School of Health Sciences, Koç University , Istanbul, Türkiye.

Scientific Reports
|April 22, 2025
PubMed
Summary
This summary is machine-generated.

Machine learning models accurately predict suicidal ideation in university students using non-suicidal factors. Personality functioning and depressed mood increase risk, while anxiety and repetitive thoughts decrease it, aiding early intervention.

More Related Videos

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

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

Published on: January 11, 2020

7.4K
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

2.1K

Related Experiment Videos

Last Updated: May 10, 2025

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

6.9K
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

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

Published on: January 11, 2020

7.4K
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

2.1K

Area of Science:

  • Psychology
  • Computer Science
  • Public Health

Background:

  • Suicide claims over 700,000 lives globally each year, with mental disorders being a significant risk factor.
  • Predicting suicidal ideation is challenging due to complex, multifaceted contributing factors and limitations of traditional assessment tools.
  • There is a need for advanced predictive approaches that capture the intricate dynamics of suicidal thoughts.

Purpose of the Study:

  • To predict suicidal and self-harm ideation in university students using machine learning models.
  • To identify less obvious risk factors by excluding suicidal behavior-related predictors.
  • To gain deeper insights into the relationships between psychiatric symptoms and suicidal ideation.

Main Methods:

  • Analyzed data from 924 university students seeking mental health services using seven machine learning algorithms.
  • Assessed suicidal ideation using the 9th item of the Patient Health Questionnaire-9 (PHQ-9).
  • Developed predictive models, with the final model using only subdomains from the DSM-5 Level 1 Self Rated Cross-Cutting Symptom Measure, validated on an external dataset of 361 individuals.

Main Results:

  • Machine learning models demonstrated strong predictive accuracy, with logistic regression and neural networks achieving an Area Under the Curve (AUC) of 0.80.
  • The final model achieved an AUC of 0.80 on training data and 0.79 on external validation data.
  • Key predictors included personality functioning and depressed mood (increasing likelihood), while anxiety and repetitive thoughts were associated with decreased likelihood.

Conclusions:

  • Machine learning effectively predicts suicidal ideation without relying on suicide-specific inputs, highlighting the utility of non-suicidal predictors.
  • Personality functioning, depressed mood, and anxiety are critical dimensions influencing suicidal ideation.
  • Findings support enhanced early detection and personalized interventions, particularly for individuals hesitant to disclose suicidal thoughts.