Journal of the Korean Society of School Health (한국학교보건학회지)

The Korean Society of School Health (한국학교보건학회)
권호 표지
DOI QR코드

DOI QR Code

Predicting Mental Health Risk based on Adolescent Health Behavior: Application of a Hybrid Machine Learning Method

청소년 건강행태에 따른 정신건강 위험 예측: 하이브리드 머신러닝 방법의 적용

  • Eun-Kyoung Goh (Dong-A University Human Life Research Center) ;
  • Hyo-Jeong Jeon (Department of Child Studies, Dong-A University) ;
  • Hyuntae Park (Department of Health Science, Dong-A University) ;
  • Sooyol Ok (Department of Computer Engineering, Dong-A University)
  • 고은경 (동아대학교 휴먼라이프리서치센터) ;
  • 전효정 (동아대학교 아동학과) ;
  • 박현태 (동아대학교 건강과학과) ;
  • 옥수열 (동아대학교 컴퓨터공학과)
  • Received : 2023.12.05
  • Accepted : 2023.12.22
  • Published : 2023.12.31
⟨ Previous Next ⟩

Abstract

Purpose: The purpose of this study is to develop a model for predicting mental health risk among adolescents based on health behavior information by employing a hybrid machine learning method. Methods: The study analyzed data of 51,850 domestic middle and high school students from 2022 Youth Health Behavior Survey conducted by the Korea Disease Control and Prevention Agency. Firstly, mental health risk levels (stress perception, suicidal thoughts, suicide attempts, suicide plans, experiences of sadness and despair, loneliness, and generalized anxiety disorder) were classified using the k-mean unsupervised learning technique. Secondly, demographic factors (family economic status, gender, age), academic performance, physical health (body mass index, moderate-intensity exercise, subjective health perception, oral health perception), daily life habits (sleep time, wake-up time, smartphone use time, difficulty recovering from fatigue), eating habits (consumption of high-caffeine drinks, sweet drinks, late-night snacks), violence victimization, and deviance (drinking, smoking experience) data were input to develop a random forest model predicting mental health risk, using logistic and XGBoosting. The model and its prediction performance were compared. Results: First, the subjects were classified into two mental health groups using k-mean unsupervised learning, with the high mental health risk group constituting 26.45% of the total sample (13,712 adolescents). This mental health risk group included most of the adolescents who had made suicide plans (95.1%) or attempted suicide (96.7%). Second, the predictive performance of the random forest model for classifying mental health risk groups significantly outperformed that of the reference model (AUC=.94). Predictors of high importance were 'difficulty recovering from daytime fatigue' and 'subjective health perception'. Conclusion: Based on an understanding of adolescent health behavior information, it is possible to predict the mental health risk levels of adolescents and make interventions in advance.

Keywords

Acknowledgement

본 연구는 동아대학교 교내 학술연구비 지원에 의해 연구됨.

References

  1. National Center for Mental Health Research Institute. National mental health statistics 2021 [Internet]. Seoul: Author; 2022 [cited 2023 November 29]. Available from: https://www.nmhc.or.kr/sub.php?id=file&mode=view&menukey=18&idx=3600&page=1 
  2. World Health Organization (WHO). World mental health report: transforming mental health for all. Geneva: World Health Organization; 2022. p. 1-272. 
  3. Sayers J. The world health report-mental health: new understanding, new hope. Bull World Health Organ. 2001;79(11):1085. 
  4. Kim JB, Han KH. Anxiety-depression comorbidity and suicide attempts in high-risk adolescents: aggravating effect of lower parental interest in mental health. Mental Health & Social Work. 2020;48(3):5-34. https://doi.org/10.24301/MHSW.2020.09.48.3.5 
  5. Jung JW, Chae HR, Chun JY, Yun SM, Lee HS, Kim ER. Strengthening the mental health care systems for high risk groups. Research Report. Seoul: Korea Institute for Health and Social Affairs; 2012 December, Report No.: Research Monographs 2012-12. 
  6. Ministry of Health and Welfare, Korea Foundation for Suicide Prevention. 2022 White Paper on Suicide Prevention. Seoul: Korea Foundation for Suicide Prevention; 2022. p. 1-247. 
  7. Lee SU, Park JI. Medical policy for suicide prevention. Journal of the Korean Medical Association. 2019;62(2):102-106. https://doi.org/10.5124/jkma.2019.62.2.102 
  8. Choi EJ, Kim MS, Jeon J. A study on supporting for mental health promotion of chilodren and adolescents III. Research Report. Sejong: National Youth Policy Institute; 2013 December, Report No.: 13-R16-1. 
  9. Keyes KM, Gary D, O'Malley PM, Hamilton A, Schulenberg J. Recent increases in depressive symptoms among US adolescents: trends from 1991 to 2018. Social Psychiatry and Psychiatric Epidemiology. 2019;54:987-996. https://doi.org/10.1007/s00127-019-01697-8 
  10. Dohrenwend BP, Levav I, Shrout PE, Schwartz S, Naveh G, Link BG, et al. Socioeconomic status and psychiatric disorders: the causation-selection issue. Science. 1992;255(5047):946-952. https://doi.org/10.1126/science.1546291 
  11. Fletcher JM. Adolescent depression and educational attainment: results using sibling fixed effects. Health Economics. 2010;19(7):855-871. https://doi.org/10.1002/hec.1526 
  12. Zeller MH, Reiter-Purtill J, Jenkins TM, Ratcliff MB. Adolescent suicidal behavior across the excess weight status spectrum. Obesity(Silver Spring). 2013;21(5):1039-1045. https://doi.org/10.1002/oby.20084 
  13. Costigan SA, Lubans DR, Lonsdale C, Sanders T, del Pozo Cruz B. Associations between physical activity intensity and well-being in adolescents. Preventive Medicine. 2019;125:55-61. https://doi.org/10.1016/j.ypmed.2019.05.009 
  14. Oh SY. The association of dietary life, nutrition and mental health in Korean adolescents. Journal of Korea Entertainment Industry Association. 2016;10(5):235-250. https://doi.org/10.21184/jkeia.2016.10.10.5.235 
  15. AlJameel AH, AlSaleh LS, Bawazir NH, AlOmair AS, Almalki SA. How mental health correlates with subjective oral health status: a cross-sectional study among a group of university students. Nigerian Journal of Clinical Practice. 2023;26(11):1716-1722. https://doi.org/10.4103/njcp.njcp_330_23 
  16. Shochat T, Cohen-Zion M, Tzischinsky O. Functional consequences of inadequate sleep in adolescents: a systematic review. Sleep Medicine Reviews. 2014;18(1):75-87. https://doi.org/10.1016/j.smrv.2013.03.005 
  17. Wacks Y, Weinstein AM. Excessive smartphone use is associated with health problems in adolescents and young adults. Frontiers Psychiatry. 2021;12:669042. https://doi.org/10.3389/fpsyt.2021.669042 
  18. Bertasi RAO, Humeda Y, Bertasi TGO, Zins Z, Kimsey J, Pujalte G. Caffeine intake and mental health in college students. Cureus. 2021;13(4):e14313. https://doi.org/10.7759/cureus.14313 
  19. Jacob L, Stubbs B, Koyanagi A. Consumption of carbonated soft drinks and suicide attempts among 105,061 adolescents aged 12-15 years from 6 high-income, 22 middle-income, and 4 low-income countries. Clinical Nutrition. 2020;39(3):886-892. https://doi.org/10.1016/j.clnu.2019.03.028 
  20. Jung HJ, Park KH, Cho YG, Cho JJ, Paek YJ, Song HJ, et al. Night fating tendency and related health risk factors. Korean Journal of Obesity. 2006;15(2):98-105. 
  21. Flannery DJ, Wester KL, Singer MI. Impact of exposure to violence in school on child and adolescent mental health and behavior. Journal of Community Psychology. 2004;32(5):559-573. https://doi.org/10.1002/jcop.20019 
  22. Groenman AP, Janssen TW, Oosterlaan J. Childhood psychiatric disorders as risk factor for subsequent substance abuse: a meta-analysis. Journal of the American Academy of Child & Adolescent Psychiatry. 2017;56(7):556-569. https://doi.org/10.1016/j.jaac.2017.05.004 
  23. Franklin JC, Ribeiro JD, Fox KR, Bentley KH, Kleiman EM, Huang X, et al. Risk factors for suicidal thoughts and behaviors: a meta-analysis of 50 years of research. Psychological Bulletin. 2017;143(2):187-232. https://doi.org/10.1037/bul0000084 
  24. Rezapour M, Hansen L. A machine learning analysis of COVID-19 mental health data. Scientific Reports. 2022;12(1):14965. https://doi.org/10.21203/rs.3.rs-1129807/v1 
  25. Fernandez-Delgado M, Cernadas E, Barro S, Amorim D. Do we need hundreds of classifiers to solve real world classification problems? The Journal of Machine Learning Rsearch. 2014;15(1):3133-3181. https://doi.org/10.5555/2627435.2697065 
  26. Simundic AM. Diagnostic accuracy-part 1: basic concepts: sensitivity and specificity, ROC analysis, STARD statement. Point of Care. 2012;11(1):6-8. https://doi.org/10.1097/POC.0b013e318246a5d6 
  27. Choi A. Emotional well-being of children and adolescents: recent trends and relevant factors. Paris: OECD Publishing: 2018. p. 1-39. 
  28. Moksnes UK, Espnes GA. Stress, sense of coherence and subjective health in adolescents aged 13-18 years. Scandinavian Journal of Public Health. 2017;45(4):397-403. https://doi.org/10.1177/1403494817694974 
  29. Nam SJ, Park JH. Adolescents' satisfaction of body and self-esteem according to obesity and subjective perception of body: verification of moderating effect of sex. Korean Journal of Obesity. 2013;22(4):251-253. https://doi.org/10.7570/kjo.2013.22.4.251 
  30. Kim NY, Shin WK, Kim YK. Study on relevance of high-caffeine drink intake frequency to mental health of adolescents. Journal of the Korean Society of Food Culture. 2017;32(1):66-74. https://doi.org/10.7318/KJFC/2017.32.1.066