Discovery of Intentional Self-Harm Patterns from Suicide and Self-Harm Surveillance Reports

다국어 초록 (Multilingual Abstract)

Objectives: The purpose of this study was to identify patterns of self-harm risk factors from suicide and self-harm surveillance reports in Thailand. Methods: This study analyzed data from suicide and self-harm surveillance reports submitted to Khon Kaen Rajanagarindra Psychiatric Hospital, Thailand. The process of identifying patterns of self-harm risk factors involved: data preprocessing (namely, data preparation and cleaning, missing data management using listwise deletion and expectation-maximization techniques, subgrouping factors, determining the target factors, and data correlation for learning); classifying the risk of self-harm (severe or mild) using 10-fold cross-validation with the support vector machine, random forest, multilayer perceptron, decision tree, k-nearest neighbors, and ensemble techniques; data filtering; identifying patterns of self-harm risk factors using 10-fold cross-validation with the classification and regression trees (CART) technique; and evaluating patterns of self-harm risk factors. Results: The random forest technique was most accurate for classifying the risk of self-harm, with specificity, sensitivity, and F-score of 92.84%, 93.12%, and 91.46%, respectively. The CART technique was able to identify 53 patterns of self-harm risk, consisting of 16 severe self-harm risk patterns and 37 mild self-harm risk patterns, with an accuracy of 92.85%. In addition, we discovered that the type of hospital was a new risk factor for severe selfharm. Conclusions: The procedure presented herein could identify patterns of risk factors from self-harm and assist psychiatrists in making decisions related to self-harm among patients visiting hospitals in Thailand.

참고문헌 (Reference)

1 National News Bureau of Thailand, "Warning issued over suicide rates among workers and unemployed"

2 Choi SB, "Ten-year prediction of suicide death using Cox regression and machine learning in a nationwide retrospective cohort study in South Korea" 231 : 8-14, 2018

3 The ASEAN Post, "Suicides on the rise in Thailand"

4 Gulabutr V, "Suicide risk factors of Royal Thai Police Officers" 4 (4): 65-80, 2017

5 Zalar B, "Suicide and suicide attempt descriptors by multimethod approach" 30 (30): 317-322, 2018

6 Lee SY, "Serum miRNA as a possible biomarker in the diagnosis of bipolar II disorder" 10 (10): 1131-, 2020

7 Onishi K, "Risk factors and social background associated with suicide in Japan : a review" (34) : 35-50, 2015

8 Miche M, "Prospective prediction of suicide attempts in community adolescents and young adults, using regression methods and machine learning" 265 : 570-578, 2020

9 Chen Q, "Predicting suicide attempt or suicide death following a visit to psychiatric specialty care : a machine learning study using Swedish national registry data" 17 (17): e1003416-, 2020

10 Subramanian J, "Overfitting in prediction models : is it a problem only in high dimensions?" 36 (36): 636-641, 2013

11 Little TD, "On the joys of missing data" 39 (39): 151-162, 2014

12 Ibrahim JG, "Model selection criteria for missing-data problems using the EM algorithm" 103 (103): 1648-1658, 2008

13 World Health Organization, "Mental health and substance use" World health Organication

14 Edgcomb JB, "Machine learning to differentiate risk of suicide attempt and self-harm after general medical hospitalization of women with mental illness" 59 : S58-S64, 2021

15 Lin GM, "Machine learning based suicide ideation prediction for military personnel" 24 (24): 1907-1916, 2020

16 Ilias Tougui ; Abdelilah Jilbab ; Jamal El Mhamdi, "Impact of the Choice of Cross-Validation Techniques on the Results of Machine Learning-Based Diagnostic Applications" 대한의료정보학회 27 (27): 189-199, 2021

17 Myers TA, "Goodbye, listwise deletion : presenting hot deck imputation as an easy and effective tool for handling missing data" 5 (5): 297-310, 2011

18 Mitchell TM, "Does machine learning really work?" 18 (18): 11-, 1997

19 Zheng L, "Development of an early-warning system for high-risk patients for suicide attempt using deep learning and electronic health records" 10 (10): 72-, 2020

20 Shen Y, "Detecting risk of suicide attempts among Chinese medical college students using a machine learning algorithm" 273 : 18-23, 2020

21 Çolakoglu N, "Comparison of multi-class classification algorithms on early diagnosis of heart diseases" 162-171, 2019

22 Wang Y, "Classification of unmedicated bipolar disorder using whole-brain functional activity and connectivity : a radiomics analysis" 30 (30): 1117-1128, 2020

23 Alimardani F, "Classification of bipolar disorder and schizophrenia using steady-state visual evoked potential based features" 6 : 40379-40388, 2018

24 Department of Mental Health, Ministry of Public Health, "Annual report 2020" Ministry of Public Health

25 Achalia R, "A proof of concept machine learning analysis using multimodal neuroimaging and neurocognitive measures as predictive biomarker in bipolar disorder" 50 : 101984-, 2020

26 Bin-Hezam R, "A machine learning approach towards detecting dementia based on its modifiable risk factors" 10 (10): 1-9, 2019

27 Santos-Mayo L, "A computer-aided diagnosis system with EEG based on the P3b wave during an auditory odd-ball task in schizophrenia" 64 (64): 395-407, 2017

28 Mansourian M, "A comprehensive review of computer-aided diagnosis of major mental and neurological disorders and suicide : a biostatistical perspective on data mining" 11 (11): 393-, 2021

29 Boonkwang K, "A comparison of data mining techniques for suicide attempt characteristics mapping and prediction" 488-493, 2018