Detection of Suicide Attempters among Suicide Ideators Using Machine Learning
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Objective We aimed to develop predictive models to identify suicide attempters among individuals with suicide ideation using a machine learning algorithm. Methods Among 35,116 individuals aged over 19 years from the Korea National Health & Nutrition Examination Survey, we selected 5,773 subjects who reported experiencing suicide ideation and had answered a survey question about suicide attempts. Then, we performed resampling with the Synthetic Minority Over-sampling TEchnique (SMOTE) to obtain data corresponding to 1,324 suicide attempters and 1,330 non-suicide attempters. We randomly assigned the samples to a training set (n=1,858) and a test set (n=796). In the training set, random forest models were trained with features selected through recursive feature elimination with 10-fold cross validation. Subsequently, the fitted model was used to predict suicide attempters in the test set. Results In the test set, the prediction model achieved very good performance [area under receiver operating characteristic curve (AUC)=0.947] with an accuracy of 88.9%. Conclusion Our results suggest that a machine learning approach can enable the prediction of individuals at high risk of suicide through the integrated analysis of various suicide risk factors.
Abstract
Objective We aimed to develop predictive models to identify suicide attempters among individuals with suicide ideation using a machine learning algorithm. Methods Among 35,116 individuals aged over 19 years from the Korea National Health & Nutrition Examination Survey, we selected 5,773 subjects who reported experiencing suicide ideation and had answered a survey question about suicide attempts. Then, we performed resampling with the Synthetic Minority Over-sampling TEchnique (SMOTE) to obtain data corresponding to 1,324 suicide attempters and 1,330 non-suicide attempters. We randomly assigned the samples to a training set (n=1,858) and a test set (n=796). In the training set, random forest models were trained with features selected through recursive feature elimination with 10-fold cross validation. Subsequently, the fitted model was used to predict suicide attempters in the test set. Results In the test set, the prediction model achieved very good performance [area under receiver operating characteristic curve (AUC)=0.947] with an accuracy of 88.9%. Conclusion Our results suggest that a machine learning approach can enable the prediction of individuals at high risk of suicide through the integrated analysis of various suicide risk factors.
참고문헌 (26)
- 김성완, "Suicide, an Urgent Health Issue in Korea", Journal of Korean Medical Science, 28(3), pp.345~347 (2013), 대한의학회
- "OECD Health Statistics 2017"[URL]
- Jeon HJ, "Lifetime prevalence and correlates of suicidal ideation, plan, and single and multiple attempts in a Korean nationwide study", J Nerv Ment Dis, 198, pp.643~646 (2010)
- The Survey of Mental Disorders in Korea 2016, "Ministry of Health and Welfare", Ministry of Health and Welfare, ~ (2017)
- 주영준, "2015 자살 관련 지표들과 추이", 보건행정학회지, 27(1), pp.75~79 (2017), 한국보건행정학회
- 김성완, "자살시도 위험요인 및 자살에 대한 태도 연구", 신경정신의학, 49(4), pp.367~373 (2010), 대한신경정신의학회
- May AM, "Predicting future suicide attempts among depressed suicide ideators : a 10-year longitudinal study", J Psychiatr Res, 46, pp.946~952 (2012)
- Miranda R, "Characteristics of suicidal ideation that predict the transition to future suicide attempts in adolescents", J Child Psychol Psychiatry, 55, pp.1288~1296 (2014)
- Bostwick JM, "Suicide attempt as a risk factor for completed suicide : even more lethal than we knew", Am J Psychiatry, 173, pp.1094~1100 (2016)
- Bostwick JM, "Affective disorders and suicide risk : a reexamination", Am J Psychiatry, 157, pp.1925~1932 (2000)
- Ribeiro JD, "Letter to the Editor: Suicide as a complex classification problem: machine learning and related techniques can advance suicide prediction-a reply to Roaldset (2016)", Psychol Med, 46, pp.2009~2010 (2016)
- Simon GE, "Predicting suicide attempts and suicide deaths following outpatient visits using electronic health records", Am J Psychiatry, 175, pp.951~960 (2018)
- Passos IC, "Identifying a clinical signature of suicidality among patients with mood disorders : a pilot study using a machine learning approach", J Affect Disord, 193, pp.109~116 (2016)
- Oh J, "Classification of suicide attempts through a machine learning algorithm based on multiple systemic psychiatric scales", Front Psychiatry, 8, pp.192~ (2017)
- Seunghyong Ryu, "Use of a Machine Learning Algorithm to Predict Individuals with Suicide Ideation in the General Population", PSYCHIATRY INVESTIGATION, 15(11), pp.1030~1036 (2018), 대한신경정신의학회[DOI]
- Kweon S, "Data resource profile: the Korea National Health and Nutrition Examination Survey (KNHANES)", Int J Epidemiol, 43, pp.69~77 (2014)
- Raghunathan TE, "IVEware: Imputation and Variance Estimation Software User Guide" (2002), University of Michigan
- van Buuren S, "Multiple imputation of discrete and continuous data by fully conditional specification", Stat Methods Med Res, 16, pp.219~242 (2007)
- Li DC, "A learning method for the class imbalance problem with medical data sets", Comput Biol Med, 40, pp.509~518 (2010)
- Blagus R, "SMOTE for high-dimensional class-imbalanced data", BMC Bioinformatics, 14, pp.106~ (2013)
- Chawla NV, "SMOTE : synthetic minority over-sampling technique", J Artif Intell Res, 16, pp.341~378 (2002)
- Breiman L, "Random forests", Mach Learn, 45, pp.5~32 (2001)
- Kim SM, "Psychosocial-environmental risk factors for suicide attempts in adolescents with suicidal ideation : findings from a sample of 73, 238 adolescents", Suicide Life Threat Behav, 45, pp.477~487 (2015)
- Souetre E, "Influence of environmental factors on suicidal behavior", Psychiatry Res, 32, pp.253~263 (1990)
- Choi SB, "Risk factors of suicide attempt among people with suicidal ideation in South Korea : a crosssectional study", BMC Public Health, 17, pp.579~ (2017)
- Jung M, "The relationship between alcohol abuse and suicide risk according to smoking status : a cross-sectional study", J Affect Disord, 244, pp.164~170 (2019)