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

Evaluation of glymphatic system activity by using diffusion tensor image analysis along the perivascular space in patients with differential suicidality.

Brain research bulletin·2026
Same author

Effects of Sulbactam on behavioral and neuronal deficits in an MPTP-induced Parkinson's disease rat model.

Brain research bulletin·2026
Same author

Longitudinal assessment of brain volume and shape alterations in depressive patients with differential suicidality.

Discover mental health·2025
Same author

Longitudinal Functional Magnetic Resonance Imaging of Brain Activity, Connectivity, and Behavior in Breast Cancer Survivors Following Chemotherapy.

Brain connectivity·2025
Same author

The associations between glucose, inflammation, cognitive functions, and white matter structural connectivity in euthymic bipolar patients.

Brain, behavior, and immunity·2025
Same author

Longitudinal analysis of brain functional connectivity and its association with clinical assessment in depressed patients using resting state fMRI.

Scientific reports·2025

Related Experiment Video

Updated: Nov 5, 2025

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

2.8K

Convolutional Neural Network-Based Deep Learning Model for Predicting Differential Suicidality in Depressive Patients

Vincent Chin-Hung Chen1,2, Fu-Te Wong3, Yuan-Hsiung Tsai1,4

  • 1School of Medicine, Chang Gung University, Taoyuan, Taiwan.

The Journal of Clinical Psychiatry
|May 14, 2021
PubMed
Summary

Deep learning using structural MRI can identify individuals at risk of suicide. This advanced technique shows promise for detecting suicidal ideation and attempts, improving upon traditional clinician assessments.

More Related Videos

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

15.9K
Modeling Fast-scan Cyclic Voltammetry Data from Electrically Stimulated Dopamine Neurotransmission Data Using QNsim1.0
07:41

Modeling Fast-scan Cyclic Voltammetry Data from Electrically Stimulated Dopamine Neurotransmission Data Using QNsim1.0

Published on: June 5, 2017

10.1K

Related Experiment Videos

Last Updated: Nov 5, 2025

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

2.8K
Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

15.9K
Modeling Fast-scan Cyclic Voltammetry Data from Electrically Stimulated Dopamine Neurotransmission Data Using QNsim1.0
07:41

Modeling Fast-scan Cyclic Voltammetry Data from Electrically Stimulated Dopamine Neurotransmission Data Using QNsim1.0

Published on: June 5, 2017

10.1K

Area of Science:

  • Neuroimaging
  • Artificial Intelligence
  • Psychiatry

Background:

  • Suicide is a critical public health issue.
  • Current suicide risk assessment by clinicians has limitations in predictive accuracy.
  • Machine learning offers a potential advancement in identifying individuals at risk.

Purpose of the Study:

  • To develop a deep learning algorithm using structural MRI data.
  • To detect suicidal ideation and suicidal attempts.

Main Methods:

  • Recruited 186 participants across four groups: suicidal attempt (SA), suicidal ideation (SI), depressed patients (DP), and healthy controls (HCs).
  • Utilized generalized q-sampling imaging (GQI) data, including generalized fractional anisotropy (GFA), isotropic value of the orientation distribution function (ISO), and normalized quantitative anisotropy (NQA).
  • Trained convolutional neural network (CNN)-based deep learning and DenseNet models.

Main Results:

  • CNN achieved accuracies of 0.916 for SA, 0.792 for SI, and 0.589 for DP against HCs.
  • DenseNet model in SA-ISO reached a best accuracy of 0.937.
  • The SA-NQA model achieved a best accuracy of 0.915.

Conclusions:

  • Deep learning with structural MRI effectively detects varying levels of suicide risk.
  • This method shows potential for suicide prevention and intervention.
  • Further research with larger, diverse populations and prospective studies is recommended.