Universal Journal of Public Health Vol. 12(5), pp. 991 - 998
DOI: 10.13189/ujph.2024.120522
Reprint (PDF) (835Kb)

Exploring Factors Influencing Suicidal Ideation in Workers with Mental Disabilities Using Machine Learning Ensemble Techniques

Haewon Byeon ^1,2,*
1 Department of AI-Software, Inje University, Republic of Korea
² Medical Big Data Research Center, Inje University, Republic of Korea

ABSTRACT

Suicide is a critical public health issue globally, with South Korea exhibiting the leading suicide rate within OECD nations. This study aims to identify factors influencing suicidal ideation among workers with mental disabilities using machine learning ensemble techniques, specifically Bagging and Boosting. Data from the 2022 Ministry of Health and Welfare's "Survey on the Employment Conditions of People with Mental Disabilities" were analyzed, involving 482 respondents. The study employed Odds Ratios (OR) and 95% confidence intervals (CI) to assess key predictors. Significant predictors identified included higher levels of depression (OR=1.10, 95% CI=1.03-1.15), lower mental health confidence (OR=0.95, 95% CI=0.92-0.98), disability registration (OR=1.80, 95% CI=1.20-2.70), discrimination experience (OR=1.06, 95% CI=1.02-1.10), and violence experience (OR=1.25, 95% CI=1.10-1.45). Both individual psychological factors and broader social determinants significantly influence suicidal ideation. The findings underscore the importance of addressing both individual psychological factors and social determinants in mental health interventions. Higher levels of depression and lower mental health confidence were significant predictors, indicating the need for mental health support and confidence-boosting initiatives. Additionally, disability registration, discrimination, and violence experiences emerged as significant factors, suggesting that social support and inclusive environments are crucial. In conclusion, this study highlights the multifaceted nature of suicidal ideation among workers with mental disabilities. Effective interventions should be comprehensive, addressing both personal and environmental influences to bolster their mental well-being and well-being. This study's findings can help develop targeted mental health interventions and assistance networks for this at-risk group.

KEYWORDS
Suicidal Ideation, Mental Disabilities, Machine Learning, Ensemble Methods, Predictive Modelling

Cite This Paper in IEEE or APA Citation Styles
(a). IEEE Format:
[1] Haewon Byeon , "Exploring Factors Influencing Suicidal Ideation in Workers with Mental Disabilities Using Machine Learning Ensemble Techniques," Universal Journal of Public Health, Vol. 12, No. 5, pp. 991 - 998, 2024. DOI: 10.13189/ujph.2024.120522.

(b). APA Format:
Haewon Byeon (2024). Exploring Factors Influencing Suicidal Ideation in Workers with Mental Disabilities Using Machine Learning Ensemble Techniques. Universal Journal of Public Health, 12(5), 991 - 998. DOI: 10.13189/ujph.2024.120522.