Prediction of Suicidal Ideation among Korean Adults Using Machine Learning: A Cross-Sectional Study
2
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
Objective Suicidal ideation (SI) precedes actual suicidal event. Thus, it is important for the prevention of suicide to screen the individuals with SI. This study aimed to identify the factors associated with SI and to build prediction models in Korean adults using machine learning methods. Methods The 2010–2013 dataset of the Korea National Health and Nutritional Examination Survey was used as the training dataset (n=16,437), and the subset collected in 2015 was used as the testing dataset (n=3,788). Various machine learning algorithms were applied and compared to the conventional logistic regression (LR)-based model. Results Common risk factors for SI included stress awareness, experience of continuous depressive mood, EQ-5D score, depressive disorder, household income, educational status, alcohol abuse, and unmet medical service needs. The prediction performances of the machine learning models, as measured by the area under receiver-operating curve, ranged from 0.794 to 0.877, some of which were better than that of the conventional LR model (0.867). The Bayesian network, LogitBoost with LR, and ANN models outperformed the conventional LR model. Conclusion A machine learning-based approach could provide better SI prediction performance compared to a conventional LRbased model. These may help primary care physicians to identify patients at risk of SI and will facilitate the early prevention of suicide.
Abstract
Objective Suicidal ideation (SI) precedes actual suicidal event. Thus, it is important for the prevention of suicide to screen the individuals with SI. This study aimed to identify the factors associated with SI and to build prediction models in Korean adults using machine learning methods. Methods The 2010–2013 dataset of the Korea National Health and Nutritional Examination Survey was used as the training dataset (n=16,437), and the subset collected in 2015 was used as the testing dataset (n=3,788). Various machine learning algorithms were applied and compared to the conventional logistic regression (LR)-based model. Results Common risk factors for SI included stress awareness, experience of continuous depressive mood, EQ-5D score, depressive disorder, household income, educational status, alcohol abuse, and unmet medical service needs. The prediction performances of the machine learning models, as measured by the area under receiver-operating curve, ranged from 0.794 to 0.877, some of which were better than that of the conventional LR model (0.867). The Bayesian network, LogitBoost with LR, and ANN models outperformed the conventional LR model. Conclusion A machine learning-based approach could provide better SI prediction performance compared to a conventional LRbased model. These may help primary care physicians to identify patients at risk of SI and will facilitate the early prevention of suicide.
참고문헌 (45)
- Neeleman J, "The suicidal process; prospective comparison between early and later stages", J Affect Disord, 82, pp.43~52 (2004)
- Borges G, "Twelve-month prevalence of and risk factors for suicide attempts in the World Health Organization World Mental Health Surveys", J Clin Psychiatry, 71, pp.1617~1628 (2010)
- Brailovskaia J, "Positive mental health moderates the association between suicide ideation and suicide attempts", J Affect Disord, 245, pp.246~249 (2018)
- Gvion Y, "Aggression, impulsivity, and suicide behavior : a review of the literature", Arch Suicide Res, 15, pp.93~112 (2011)
- Bergfeld IO, "Treatment-resistant depression and suicidality", J Affect Disord, 235, pp.362~367 (2018)
- Ten Have M, "Prevalence and risk factors for first onset of suicidal behaviors in the Netherlands Mental Health Survey and Incidence Study-2", J Affect Disord, 147, pp.205~211 (2013)
- de Heer EW, "Pain as a risk factor for suicidal ideation. A population-based longitudinal cohort study", Gen Hosp Psychiatry (2018)
- Holden KB, "Prevalence and correlates of depressive symptoms and resiliency among African American women in a community-based primary health care center", J Health Care Poor Underserved, 24, pp.79~93 (2013)
- Landa A, "Unmet need for treatment of depression among immigrants from the former USSR in the US : a primary care study", Int J Psychiatry Med, 50, pp.271~289 (2015)
- Lehmann M, "Suicidal ideation in patients with coronary heart disease and hypertension : Baseline results from the DEPSCREEN-INFO clinical trial", Clin Psychol Psychother, 25, pp.754~764 (2018)
- Strupp J, "Risk factors for suicidal ideation in patients feeling severely affected by multiple sclerosis", J Palliat Med, 19, pp.523~528 (2016)
- Dinov ID, "Predictive big data analytics : a study of parkinson’s disease using large, complex, heterogeneous, incongruent, multi-source and incomplete observations", PLoS One, 11, pp.e0157077~ (2016)
- Zhang Y, "Application and exploration of big data mining in clinical medicine", Chin Med J(Engl), 129, pp.731~738 (2016)
- Jiang F, "Artificial intelligence in healthcare : past, present and future", Stroke Vasc Neurol, 2, pp.230~243 (2017)
- Kim SK, "Osteoporosis risk prediction using machine learning and conventional methods", Conf Proc IEEE Eng Med Biol Soc 2013, pp.188~191 (2013)
- 이수경, "Prediction Model for Health-Related Quality of Life of Elderly with Chronic Diseases using Machine Learning Techniques", Healthcare Informatics Research, 20(2), pp.125~134 (2014), 대한의료정보학회[DOI]
- Jung JS, "Prediction models for high risk of suicide in Korean adolescents using machine learning techniques", PLoS One, 14, pp.e0217639~ (2019)
- Colic S, "Using machine learning algorithms to enhance the management of suicide ideation", Conf Proc IEEE Eng Med Biol Soc, 2018, pp.4936~4939 (2018)
- Carson NJ, "Identification of suicidal behavior among psychiatrically hospitalized adolescents using natural language processing and machine learning of electronic health records", PLoS One, 14, pp.e0211116~ (2019)
- Gong J, "Machine learning discovery of longitudinal patterns of depression and suicidal ideation", PLoS One, 14, pp.e0222665~ (2019)
- Burke TA, "The use of machine learning in the study of suicidal and non-suicidal self-injurious thoughts and behaviors : A systematic review", J Affect Disord, 245, pp.869~884 (2019)
- Chun MY, "Association between sleep duration and musculoskeletal pain: The Korea National Health and Nutrition Examination Survey 2010-2015", Medicine (Baltimore), 97, pp.e13656~ (2018)
- 윤경철, "An Overview of Ophthalmologic Survey Methodology in the 2008- 2015 Korean National Health and Nutrition Examination Surveys", Korean Journal of Ophthalmology, 29(6), pp.359~367 (2015), 대한안과학회
- Witkiewitz K, "Clinical validation of reduced alcohol consumption after treatment for alcohol dependence using the World Health Organization risk drinking levels", Alcohol Clin Exp Res, 41, pp.179~186 (2017)
- Reinert DF, "The Alcohol Use Disorders Identification Test(AUDIT) : a review of recent research", Alcohol Clin Exp Res, 26, pp.272~279 (2002)
- Kotsiantis S, "Handling imbalanced datasets : a review", GESTS Int T Comput Sci Eng, 30, pp.25~36 (2006)
- Hsieh CH, "Novel solutions for an old disease : diagnosis of acute appendicitis with random forest, support vector machines, and artificial neural networks", Surgery, 149, pp.87~93 (2011)
- Awata S, "Prevention of suicide in the elderly", Seishin Shinkeigaku Zasshi, 107, pp.1099~1109 (2005)
- Wang YH, "Association of depressive symptoms and suicidal ideation among university students in China: A systematic review and meta-analysis", Medicine (Baltimore), 96, pp.e6476~ (2017)
- Hegerl U, "Public attitudes towards treatment of depression : effects of an information campaign", Pharmacopsychiatry, 36, pp.288~291 (2003)
- Jorm AF, "Public beliefs about causes and risk factors for mental disorders : changes in Australia over 8 years", Soc Psychiatry Psychiatr Epidemiol, 40, pp.764~767 (2005)
- Paykel ES, "Changes in public attitudes to depression during the Defeat Depression Campaign", Br J Psychiatry, 173, pp.519~522 (1998)
- Lee H, "Age and sex-related differences in risk factors for elderly suicide : Differentiating between suicide ideation and attempts", Int J Geriatr Psychiatry, 33, pp.e300~ (2018)
- Kyung-Sook W, "Marital status integration and suicide : A meta-analysis and meta-regression", Soc Sci Med, 197, pp.116~126 (2018)
- Ki M, "Differentiation of direct and indirect socioeconomic effects on suicide attempts in South Korea", Medicine (Baltimore), 96, pp.e9331~ (2017)
- Darvishi N, "Alcohol-related risk of suicidal ideation, suicide attempt, and completed suicide : a metaanalysis", PLoS One, 10, pp.e0126870~ (2015)
- Goldney RD, "Suicidal ideation and health-related quality of life in the community", Med J Aust, 175, pp.546~549 (2001)
- Kim JH, "The impact of health-related quality of life on suicidal ideation and suicide attempts among Korean older adults", J Gerontol Nurs, 38, pp.48~59 (2012)
- Fassberg MM, "A systematic review of physical illness, functional disability, and suicidal behaviour among older adults", Aging Ment Health, 20, pp.166~194 (2016)
- Liu Y, "Development and validation of a risk prediction algorithm for the recurrence of suicidal ideation among general population with low mood", J Affect Disord, 193, pp.11~17 (2016)
- Liu X, "Proactive Suicide Prevention Online(PSPO) : machine identification and crisis management for Chinese social media users with suicidal thoughts and behaviors", J Med Internet Res, 21, pp.e11705~ (2019)
- Fang X, "Prevalence, risk factors and clinical characteristics of suicidal ideation in Chinese patients with depression", J Affect Disord, 235, pp.135~141 (2018)
- Choi YJ, "The prevalence of suicidal ideation and depression among primary care patients and current management in South Korea", Int J Ment Health Syst, 11, pp.18~ (2017)
- 박상원, "Development of the Suicide Risk Scale for Medical Inpatients", Journal of Korean Medical Science, 33(3), pp.25~35 (2018), 대한의학회
- McDowell AK, "Practical suicide-risk management for the busy primary care physician", Mayo Clin Proc, 86, pp.792~800 (2011)