본문 바로가기
KERD
논문KCI 등재

메타분석에 기반한 자살 예측 연구에서 전통적 통계 기법과 머신러닝 기반 접근법의 예측력 비교

Comparison between Machine Learning and Traditional Tecnique for Suicide Prediction based on Meta-analysis

서종한|권혁준
한국문화및사회문제심리학회 (Korean Psychological Association of Culture and Social Issues)|2024.08|한국심리학회지: 문화 및 사회문제 (Korean Psychological Journal of Culture and Social Issues)|제30권 제3호|pp. 239-265|DOI http://dx.doi.org/10.20406/kjcs.2024.8.30.3.239

1

조회

0

다운로드

0

인용

0

참고문헌

키워드

메타분석자살Machine learningSuicide머신러닝Meta-analysis메타회귀분석Meta-regression자살 예측Suicide prediction
주제분류심리과학

초록

본 연구는 자살 관련 행동에 대해 전통적인 예측 모형(기법)과 머신러닝 알고리즘을 활용한 연구의 예측력을 비교하기 위한 목적에서 수행되었다. 따라서 체계적 리뷰 수준에서 벗어나 메타분석을 통해 과학적으로 두 가지 기법의 예측력에 대해 살펴보고, 지역적인 수준에서 특히 국내 연구를 통해 알 수 있는 변인들을 분석하여 추후 자살 관련 행동 예측 연구에 도움을 주고자 하였다. 이를 위해 머신러닝을 사용한 연구 50개와 전통적 기법을 활용한 연구 74개로 총 124개의 문헌이 메타분석에 포함되었다. 연구 결과 전통적 기법을 활용한 연구들의 통합 AUC는 .770으로 머신러닝을 활용한 연구들의 통합 AUC값인 .853보다 낮은 것으로 나타났다. 특히 아시아권의 연구(AUC = .944)가 서양(AUC = .820)과 한국(AUC = .864)의 연구에 비해 높은 정확도를 나타내었다. 국내 연구에서의 조절효과를 추가적으로 분석한 결과 남성의 비율이 많을수록, 예측 대상이 자살 시도일수록 예측 정확도가 높았으며, 예측 대상이 자살 사망일수록, 그리고 신경망분석(Neural Network)을 활용한 연구일수록 예측 정확도가 낮았다. 본 연구는 자살 관련 행동의 예측에 대한 다양한 연구결과를 종합하고, 머신러닝을 활용한 예측의 효과성을 검증하는 한편, 국내에서 활용가능한 변인을 탐색하는 데 그 의의가 있다.

Abstract

The purpose of this study was to compare the predictive accuracy of traditional prediction models (methods) and machine learning algorithms in predicting suicidal behaviors. The research aimed to go beyond a systematic review level and scientifically examine the predictive capabilities of these two techniques through meta-analysis, analyzing variables identified through domestic research, particularly at the regional level. In order to achieve this, a total of 124 studies, including 50 studies utilizing machine learning and 74 studies employing traditional methods, were included in the meta-analysis. The results of the study revealed that the integrated area under the curve (AUC) for studies using traditional methods was .770, which was lower than the integrated AUC value of .853 for studies using machine learning. Particularly, studies conducted in Asia (AUC = .944) demonstrated higher accuracy compared to studies in Western countries (AUC = .820) and Korea (AUC = .864). Additional analysis of the moderating effects in domestic research indicated that a higher proportion of males and the prediction of suicide attempts were associated with higher prediction accuracy. On the other hand, prediction accuracy was lower when the prediction target was suicide deaths and when studies utilized neural network analysis. This study synthesized various research findings on the prediction of suicidal behaviors, verified the effectiveness of prediction using machine learning, and holds significance in exploring variables applicable in the context of South Korea.

참고문헌 (90)

  1. 권혁준, "머신러닝 기반 한국경찰 자살 생각 위험요인 탐색 : 랜덤포레스트를 중심으로", 치안정책연구, 36(4), pp.7~48 (2022)
  2. 김효창, "자살 : 문화심리학적 관점에서의 조망", 한국심리학회지 : 문화 및 사회문제, 16(2), pp.165~178 (2010)
  3. 이택호, "랜덤포레스트 머신러닝 기법을 활용한 전통적 비행이론기반 청소년 온, 오프라인 비행 예측요인연구", 한국심리학회지 : 문화 및 사회문제, 28(4), pp.661~690 (2022)
  4. 정기성, "인공신경망 분석을 활용한 인천시 주거취약계층의 행복주택 입주의향에 미치는 요인 분석", 주택연구, 26(3), pp.55~78 (2018)
  5. 홍기혜, "랜덤포레스트 머신러닝 알고리즘 기반 남․여 청소년의 자살생각 예측 및 분석", 한국사회복지학, 72(3), pp.157~180 (2020)
  6. Adamou, M., "Toward automatic risk assessment to support suicide prevention", Crisis, 40(4) (2018)[DOI]
  7. Bae, S. M., "Neuropsychiatric disease and treatment", pp.2367~2375 (2015)
  8. Bayramli, I., "Predictive structured–unstructured interactions in EHR models : A case study of suicide prediction", NPJ Digital Medicine, 5(1), pp.15~ (2022)[DOI]
  9. Bayramli, I., "Temporally informed random forests for suicide risk prediction", Journal of the American Medical Informatics Association, 29(1), pp.62~71 (2022)[DOI]
  10. Beck, A. T., "Development of suicidal intent scales" (1974), Charles Press Publishers
  11. Belsher, B. E., "Prediction models for suicide attempts and deaths : a systematic review and simulation", JAMA Psychiatry, 76(6), pp.642~651 (2019)[DOI]
  12. Berkelmans, G., "Identifying socio-demographic risk factors for suicide using data on an individual level", BMC Public Health, 21(1), pp.1~8 (2021)[DOI]
  13. Bhak, Y., "Depression and suicide risk prediction models using blood-derived multi-omics data", Translational Psychiatry, 9(1), pp.262~ (2019)[DOI]
  14. "Predicting adolescent suicide attempts with neural networks" (2017)[URL]
  15. Boudreaux, E. D., "Applying machine learning approaches to suicide prediction using healthcare data : overview and future directions", Frontiers in Psychiatry, 12, pp.707916~ (2021)[DOI]
  16. Bryan, C. J., "Advances in the assessment of suicide risk", Journal of Clinical Psychology, 62(2), pp.185~200 (2006)[DOI]
  17. Burke, T. A., "The use of machine learning in the study of suicidal and non-suicidal self-injurious thoughts and behaviors : A systematic review", Journal of Offective Disorders, 245, pp.869~884 (2019)[DOI]
  18. Byeon, H., "Prediction of adolescent suicidal ideation after the COVID-19 pandemic : A nationwide survey of a representative sample of Korea", Frontiers in Pediatrics, 10, pp.951439~ (2022)[DOI]
  19. Chan, L. F., "Suicide attempts among depressed inpatients with depressive disorder in a Malaysian sample : psychosocial and clinical risk factors", Crisis, 32(5), pp.283~287 (2011)[DOI]
  20. Cheng, Q., "Assessing suicide risk and emotional distress in Chinese social media: a text mining and machine learning study", Journal of Medical Internet Research, 19(7), pp.e243~ (2017)[DOI]
  21. Choi, S. B., "Ten-year prediction of suicide death using Cox regression and machine learning in a nationwide retrospective cohort study in South Korea", Journal of Affective Disorders, 231, pp.8~14 (2018)[DOI]
  22. Chou, P. H., "A machine-learning model to predict suicide risk in Japan based on national survey data", Frontiers in Psychiatry, 13, pp.918667~ (2022)[DOI]
  23. Cohen, J., "Integration and validation of a natural language processing machine learning suicide risk prediction model based on open-ended interview language in the emergency department", Frontiers in Digital Health, 4, pp.818705~ (2022)[DOI]
  24. Cohen, J., "A feasibility study using a machine learning suicide risk prediction model based on open-ended interview language in adolescent therapy sessions", International Journal of Environmental Research and Public Health, 17(21), pp.8187~ (2020)[DOI]
  25. Cohen, S., "Contrasting the Hassles Scale and the Perceived Stress Scale : Who's really measuring appraised stress?", American Psychologist, 41(6), pp.716~718 (1986)
  26. Coley, R. Y., "Clinical risk prediction models and informative cluster size : Assessing the performance of a suicide risk prediction algorithm", Biometrical Journal, 63(7), pp.1375~1388 (2021)[DOI]
  27. Corke, M., "Meta-analysis of the strength of exploratory suicide prediction models; from clinicians to computers", BJPsych open, 7(1), pp.e26~ (2021)[DOI]
  28. Czyz, E. K., "Predicting short-term suicidal thoughts in adolescents using machine learning : Developing decision tools to identify daily level risk after hospitalization", Psychological Medicine, 53(7), pp.2982~2991 (2023)[DOI]
  29. Delgado-Gomez, D., "Suicide attempters classification : Toward predictive models of suicidal behavior", Neurocomputing, 92, pp.3~8 (2012)[DOI]
  30. Demi̇rbaş, H., "An examination of suicide probability in alcoholic in-patients", Alcohol and Alcoholism, 38(1), pp.67~70 (2003)[DOI]
  31. Edgcomb, J. B., "Predicting suicidal behavior and self-harm after general hospitalization of adults with serious mental illness", Journal of Psychiatric Research, 136, pp.515~521 (2021)[DOI]
  32. Franklin, J. C., "Virtual reality suicide : Development of a translational approach for studying suicide causes", Behaviour Research and Therapy, 120, pp.103360~ (2019)[DOI]
  33. Franklin, J. C., "Risk factors for suicidal thoughts and behaviors : A meta-analysis of 50 years of research", Psychological Bulletin, 143(2), pp.187~232 (2017)[DOI]
  34. Fulginiti, A., "Getting to the root of the problem : A decision-tree analysis for suicide risk among young people experiencing homelessness", Journal of the Society for Social Work and Research, 13(2), pp.327~352 (2022)[DOI]
  35. Gladstone, G. L., "Indicators of suicide over 10 years in a specialist mood disorders unit sample", Journal of Clinical Psychiatry, 62(12), pp.945~951 (2001)
  36. Goldston, D. B., "Suicide attempts among formerly hospitalized adolescents : A prospective naturalistic study of risk during the first 5 years after discharge", Journal of the American Academy of Child & Adolescent Psychiatry, 38(6), pp.660~671 (1999)[DOI]
  37. Gómez, J. M, "Language technologies for suicide prevention in social media", Proceedings of the Workshop on Natural Language Processing in the 5th Information Systems Research Working Days (JISIC), pp.21~29 (2014)
  38. Gradus, J. L., "Predicting sex-specific nonfatal suicide attempt risk using machine learning and data from Danish national registries", American Journal of Epidemiology, 190(12), pp.2517~2527 (2021)[DOI]
  39. Han, K., "College students’ screening early warning factors in identification of suicide risk", Frontiers in Genetics, 13, pp.977007~ (2022)[DOI]
  40. Haroz, E. E., "Reaching those at highest risk for suicide : development of a model using machine learning methods for use with Native American communities", Suicide and Life-Threatening Behavior, 50(2), pp.422~436 (2020)[DOI]
  41. Hawkins, D. M., "The problem of overfitting", Journal of Chemical Information and Computer Sciences, 44(1), pp.1~12 (2004)[DOI]
  42. Hopkins, D., "Structured data vs. unstructured data in machine learning prediction models for suicidal behaviors : A systematic review and meta-analysis", Frontiers in Digital Health, 4, pp.945006~ (2022)[DOI]
  43. Horvath, A., "Predicting suicidal behavior without asking about suicidal ideation : machine learning and the role of borderline personality disorder criteria", Suicide and Life-Threatening Behavior, 51(3), pp.455~466 (2021)[DOI]
  44. Jiang, T., "Using machine learning to predict suicide in the 30 days after discharge from psychiatric hospital in Denmark", The British Journal of Psychiatry, 219(2), pp.440~447 (2021)[DOI]
  45. Joiner, T., "Suicide Science: Expanding the Boundaries", pp.17~32 (2002)
  46. Jung, J. S., "Prediction models for high risk of suicide in Korean adolescents using machine learning techniques", PLoS one, 14(6), pp.e0217639~ (2019)[DOI]
  47. Kessler, R. C., "Clinical epidemiological research on suicide-related behaviors—where we are and where we need to go", JAMA Psychiatry, 76(8), pp.777~778 (2019)[DOI]
  48. Kessler, R. C., "Suicide prediction models : a critical review of recent research with recommendations for the way forward", Molecular Psychiatry, 25(1), pp.168~179 (2020)[DOI]
  49. Kim, K. W., "Classification of adolescent psychiatric patients at high risk of suicide using the personality assessment inventory by machine learning", Psychiatry Investigation, 18(11), pp.1137~ (2021)[DOI]
  50. Kim, S., "The effectiveness of predicting suicidal ideation through depressive symptoms and social isolation using machine learning techniques", Journal of Personalized Medicine, 12(4), pp.516~ (2022)[DOI]
  51. Kim, S., "Detecting suicidal risk using MMPI-2 based on machine learning algorithm", Scientific Reports, 11(1), pp.15310~ (2021)[DOI]
  52. Kleespies, P. M., "An evidence-based approach to evaluating and managing suicidal emergencies", Journal of Clinical Psychology, 56(9), pp.1109~1130 (2000)[DOI]
  53. Large, M. M., "Can we usefully stratify patients according to suicide risk?", Bmj, 359 (2017)
  54. Levis, M., "Natural language processing of clinical mental health notes may add predictive value to existing suicide risk models", Psychological Medicine, 51(8), pp.1382~1391 (2021)[DOI]
  55. Lim, J. S., "Prediction models for suicide attempts among adolescents using machine learning techniques", Clinical Psychopharmacology and Neuroscience, 20(4), pp.609~ (2022)[DOI]
  56. Lin, G. M., "Machine learning based suicide ideation prediction for military personnel", IEEE Journal of Biomedical and Health Informatics, 24(7), pp.1907~1916 (2020)[DOI]
  57. Linthicum, K. P., "Machine learning in suicide science : Applications and ethics", Behavioral Sciences & the Law, 37(3), pp.214~222 (2019)[DOI]
  58. Lu, H., "Development and Value Evaluation of a Simple Prediction Model of Suicidal Behavior in Depressive Disorder", Chinese General Practice, 23(26), pp.3247~ (2020)[DOI]
  59. Macalli, M., "A machine learning approach for predicting suicidal thoughts and behaviours among college students", Scientific Reports, 11(1), pp.11363~ (2021)[DOI]
  60. Mann, J. J., "Can biological tests assist prediction of suicide in mood disorders?", International Journal of Neuropsychopharmacology, 9(4), pp.465~474 (2006)[DOI]
  61. Mann, J. J., "Toward a clinical model of suicidal behavior in psychiatric patients", American Journal of Psychiatry, 156(2), pp.181~189 (1999)[DOI]
  62. Matykiewicz, P., "Clustering Semantic Spaces of Suicide Notes and Newsgroups Articles", Proceedings of the BioNLP 2009 Workshop, pp.179~184 (2009)
  63. McHugh, C. M., "Predictive modelling of deliberate self-harm and suicide attempts in young people accessing primary care : a machine learning analysis of a longitudinal study", Social Psychiatry and Psychiatric Epidemiology, 58(6), pp.893~905 (2023)[DOI]
  64. Min, S., "Acoustic analysis of speech for screening for suicide risk: machine learning classifiers for between-and within-person evaluation of suicidality", Journal of Medical Internet Research, 25, pp.e45456~ (2023)[DOI]
  65. Nordin, N., "A comparative study of machine learning techniques for suicide attempts predictive model", Health Informatics Journal, 27(1), pp.1460458221989395~ (2021)[DOI]
  66. Obeid, J. S., "Identifying and predicting intentional self-harm in electronic health record clinical notes: deep learning approach", JMIR Medical Informatics, 8(7), pp.e17784~ (2020)[DOI]
  67. Oh, B., "Prediction of suicidal ideation among Korean adults using machine learning : a cross-sectional study", Psychiatry Investigation, 17(4), pp.331~ (2020)[DOI]
  68. REF070236795Oh, J., "Classification of suicide attempts through a machine learning algorithm based on multiple systemic psychiatric scales", Frontiers in Psychiatry, 8, pp.192~ (2017)[DOI]
  69. Park, H., "A Machine Learning Approach for Predicting Wage Workers’ Suicidal Ideation", Journal of Personalized Medicine, 12(6), pp.945~ (2022)[DOI]
  70. Park, H., "Using Boosted Machine Learning to Predict Suicidal Ideation by Socioeconomic Status among Adolescents", Journal of Personalized Medicine, 12(9), pp.1357~ (2022)[DOI]
  71. Rabani, S. T., "Detection of suicidal ideation on Twitter using machine learning & ensemble approaches", Baghdad Science Journal, 17(4), pp.1328~1328 (2020)[DOI]
  72. Ryu, S., "Detection of suicide attempters among suicide ideators using machine learning", Psychiatry Investigation, 16(8), pp.588~ (2019)[DOI]
  73. Ryu, S., "Use of a machine learning algorithm to predict individuals with suicide ideation in the general population", Psychiatry Investigation, 15(11), pp.1030~ (2018)[DOI]
  74. Sanderson, M., "Predicting death by suicide following an emergency department visit for parasuicide with administrative health care system data and machine learning", EClinicalMedicine, 20 (2020)[DOI]
  75. Schafer, K. M., "A direct comparison of theory-driven and machine learning prediction of suicide: A meta-analysis", PloS one, 16(4), pp.e0249833~ (2021)[DOI]
  76. Shen, Y., "Detecting risk of suicide attempts among Chinese medical college students using a machine learning algorithm", Journal of Affective Disorders, 273, pp.18~23 (2020)[DOI]
  77. Shin, D., "Detection of depression and suicide risk based on text from clinical interviews using machine learning : possibility of a new objective diagnostic marker", Frontiers in Psychiatry, 13, pp.801301~ (2022)[DOI]
  78. Šimundić, A. M, "Measures of diagnostic accuracy : basic definitions", ejifcc, 19(4), pp.203~ (2009)
  79. Skogman, K., "Sex differences in risk factors for suicide after attempted suicide : a follow-up study of 1052 suicide attempters", Social Psychiatry and Psychiatric Epidemiology, 39, pp.113~120 (2004)[DOI]
  80. Song, S. I., "A machine learning approach for predicting suicidal ideation in post stroke patients", Scientific Reports, 12(1), pp.15906~ (2022)[DOI]
  81. Su, C., "Machine learning for suicide risk prediction in children and adolescents with electronic health records", Translational Psychiatry, 10(1), pp.413~ (2020)[DOI]
  82. Su, R., "Machine learning-based prediction for self-harm and suicide attempts in adolescents", Psychiatry Research, 328, pp.115446~ (2023)[DOI]
  83. Tantithamthavorn, C., "An empirical comparison of model validation techniques for defect prediction models", IEEE Transactions on Software Engineering, 43(1), pp.1~18 (2016)[DOI]
  84. Tsui, F. R., "Natural language processing and machine learning of electronic health records for prediction of first-time suicide attempts", JAMIA open, 4(1) (2021)[DOI]
  85. Tu, J. V., "Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes", Journal of Clinical Epidemiology, 49(11), pp.1225~1231 (1996)[DOI]
  86. Van Vuuren, C. L., "Comparing machine learning to a rule-based approach for predicting suicidal behavior among adolescents : Results from a longitudinal population-based survey", Journal of Affective Disorders, 295, pp.1415~1420 (2021)[DOI]
  87. Velupillai, S., "Risk assessment tools and data-driven approaches for predicting and preventing suicidal behavior", Frontiers in Psychiatry, 10, pp.36~ (2019)[DOI]
  88. Walsh, C. G., "Predicting risk of suicide attempts over time through machine learning", Clinical Psychological Science, 5(3), pp.457~469 (2017)[DOI]
  89. Zheng, S., "Can cognition help predict suicide risk in patients with major depressive disorder? A machine learning study", BMC psychiatry, 22(1), pp.1~13 (2022)[DOI]
  90. Zuromski, K. L., "Assessment of a risk index for suicide attempts among US army soldiers with suicide ideation: analysis of data from the army study to assess risk and resilience in servicemembers (Army STARRS)", JAMA network open, 2(3), pp.e190766~e190766 (2019)[DOI]

관련 논문AI추천

Detection of Suicide Attempters among Suicide Ideators Using Machine Learning이형래, Chul-Eung Kim, Dong-Kyun Lee, Seunghyong Ryu, Sung-Wan Kim대한신경정신의학회 · PSYCHIATRY INVESTIGATION2019 · 제16권 제8호Optimizing Suicide Risk Prediction in Korea: A Comparison of Model Performance Using Resampling Methods and Machine Learning AlgorithmsBong-Jo Kim, Boseok Cha, Dongyun Lee, Eunji Lim, Jae-Won Choi, Nuree Kang, So-Jin Lee, Soyoung Park, Sung Hyo Seo대한신경정신의학회 · PSYCHIATRY INVESTIGATION2025 · 제22권 제11호Use of a Machine Learning Algorithm to Predict Individuals with Suicide Ideation in the General Population박경우, Dong-Kyun Lee, Hyeongrae Lee, Seunghyong Ryu대한신경정신의학회 · PSYCHIATRY INVESTIGATION2018 · 제15권 제11호Prediction Models for Suicide Attempts among Adolescents Using Machine Learning TechniquesBung-Nyun Kim, Chan-Mo Yang, Jae Seok Lim, Ju-Won Baek, Sang Yeol Lee대한정신약물학회 · Clinical Psychopharmacology and Neuroscience2022 · 제20권 제4호Prediction of Suicidal Ideation among Korean Adults Using Machine Learning: A Cross-Sectional StudyBum-Joo Cho, Bumjo Oh, Dong-Hoi Kim, Eun Chong Yeo, Je-Yeon Yun, Jin Kim대한신경정신의학회 · PSYCHIATRY INVESTIGATION2020 · 제17권 제4호의사결정나무분석을 이용한 자살 시도 계획 수준 및 충동성에 대한 심리사회적 예측 요인김효중, 유성은한국임상심리학회 · Korean Journal of Clinical Psychology2021 · 제40권 제3호

이 간행물의 다른 논문 (5건)

만 2세 이하 자녀를 둔 취업모의 육아지원 서비스 이용 과정김은지, 도승이, 최은수, 박준하, 한주연pp. 267-298부부의 외현적 자기애와 결혼만족도의 관계에서 갈등대처방식의 상호의존 매개효과: APIMeM 적용박정윤, 고수연pp. 299-319친사회적 동기가 침묵행동에 미치는 영향: 직무소진의 매개효과와 비대면 근무환경의 차이를 중심으로김봄메, 하규영pp. 321-348잠재프로파일분석(LPA)을 통한 코로나 대유행 시기 성인의 불안 및 분노 증상 유형 분석김성현, 이동훈pp. 349-378성적지향 마이크로어그레션이 성소수자(LGB)의 우울에 미치는 영향: 반추의 매개효과에 대한 사회적 지지와 성정체성 수용의 조절효과유금란, 이현정pp. 379-406
원문 보기