Related Experiment Video
Updated: Sep 26, 2025
05:19
Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment
Published on: July 7, 2023
2.6K
The Effectiveness of Predicting Suicidal Ideation through Depressive Symptoms and Social Isolation Using Machine
1Department of Psychiatry, Hanyang University Medical Center, Seoul 04763, Korea.
Journal of Personalized Medicine
|April 23, 2022
Summary
Combining depression and social isolation assessments effectively predicts suicidal ideation. Machine learning models accurately identified at-risk individuals, highlighting the importance of both factors.
Area of Science:
- Psychiatry
- Public Health
- Computational Medicine
Background:
- Social isolation is a significant risk factor for suicidal ideation.
- Early identification of individuals at risk is crucial for intervention.
Purpose of the Study:
- To investigate the combined predictive power of depression and social isolation for suicidal ideation.
- To evaluate the efficacy of machine learning models in this prediction.
Main Methods:
- Analysis of data from 7994 community residents.
- Utilized Patient Health Questionnaire-9 (PHQ-9) for depression and Lubben Social Network Scale (LSNS) for social isolation.
- Applied machine learning algorithms including K-Nearest Neighbors, Random Forest, and Neural Network Classification.
Main Results:
- Machine learning models demonstrated high predictive performance (AUC 0.643-0.836, specificity 0.959-0.987).
- Models incorporating both depression and social isolation (model 2) showed improved validation accuracy over depression-only models (model 1).
Conclusions:
- Machine learning techniques integrating depression and social isolation are effective for predicting suicidal ideation.
- Assessing both depression and social isolation is vital for comprehensive risk evaluation.
