청소년 건강행태 온라인 조사를 통한 청소년기 자살시도 예측 모델 개발
Development of Prediction Model for Suicide Attempts Using the Korean Youth Health Behavior Web-Based Survey in Korean Middle and High School Students
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Objectives Assessing the risks of youth suicide in educational and clinical settings is crucial. Therefore, this study developed a machine learning model to predict suicide attempts using the Korean Youth Risk Behavior Web-based Survey (KYRBWS). Methods KYRBWS is conducted annually on Korean middle and high school students to assess their health-related behaviors. The KYRBWS data for 2021, which showed 1206 adolescents reporting suicide attempts out of 54848, was split into the training (n=43878) and test (n=10970) datasets. Thirty-nine features were selected from the KYRBWS questionnaire. The balanced accuracy of the model was employed as a metric to select the best model. Independent validations were conducted with the test dataset of 2021 KYRBWS (n=10970) and the external dataset of 2020 KYRBWS (n=54948). The clinical implication of the prediction by the selected model was measured for sensitivity, specificity, true prediction rate (TPR), and false prediction rate (FPR). Results Balanced bag of histogram gradient boosting model has shown the best performance (balanced accuracy=0.803). This model shows 76.23% sensitivity, 83.08% specificity, 10.03% TPR, and 99.30% FPR for the test dataset as well as 77.25% sensitivity, 84.62% specificity, 9.31% TPR, and 99.45% FPR for the external dataset, respectively. Conclusion These results suggest that a specific machine learning model can predict suicide attempts among adolescents with high accuracy.
Abstract
Objectives Assessing the risks of youth suicide in educational and clinical settings is crucial. Therefore, this study developed a machine learning model to predict suicide attempts using the Korean Youth Risk Behavior Web-based Survey (KYRBWS). Methods KYRBWS is conducted annually on Korean middle and high school students to assess their health-related behaviors. The KYRBWS data for 2021, which showed 1206 adolescents reporting suicide attempts out of 54848, was split into the training (n=43878) and test (n=10970) datasets. Thirty-nine features were selected from the KYRBWS questionnaire. The balanced accuracy of the model was employed as a metric to select the best model. Independent validations were conducted with the test dataset of 2021 KYRBWS (n=10970) and the external dataset of 2020 KYRBWS (n=54948). The clinical implication of the prediction by the selected model was measured for sensitivity, specificity, true prediction rate (TPR), and false prediction rate (FPR). Results Balanced bag of histogram gradient boosting model has shown the best performance (balanced accuracy=0.803). This model shows 76.23% sensitivity, 83.08% specificity, 10.03% TPR, and 99.30% FPR for the test dataset as well as 77.25% sensitivity, 84.62% specificity, 9.31% TPR, and 99.45% FPR for the external dataset, respectively. Conclusion These results suggest that a specific machine learning model can predict suicide attempts among adolescents with high accuracy.
참고문헌 (22)
- "Cause of death statistics for 2021"[URL]
- 김민경, "청소년의 건강위험행동과 자살생각, 자살계획, 자살시도 관련 요인", 보건교육건강증진학회지, 36(3), pp.61~71 (2019), 한국보건교육건강증진학회[DOI]
- "Suicide rate 2005-2022"[URL]
- 박은옥, "청소년의 자살시도에 영향을 주는 요인", Journal of Korean Academy of Nursing, 38(3), pp.465~473 (2008), 한국간호과학회
- 손신영, "청소년의 자살생각, 자살계획, 자살시도에 영향을 미치는 요인에 관한 연구", 한국산학기술학회논문지, 15(3), pp.1606~1614 (2014), 한국산학기술학회[DOI]
- 박은옥, "청소년의 자살사고(思考) 관련 요인", 한국학교보건학회지, 22(2), pp.13~23 (2009), 한국학교보건학회
- Lee J, "Prediction model for suicide potential of Korean youth", Korea Software Congress, pp.1501~1503 (2019)
- 박승진, "자살성향 측정척도들의 자살예측력에 대한 고찰", 대한불안의학회지, 9(1), pp.10~18 (2013), 대한불안의학회
- He H, "Learning from imbalanced data", IEEE Trans Knowl Data Eng, 21, pp.1263~1284 (2009)
- "Report on the Korea youth risk behavior web-based survey"[URL]
- "The Korea Youth Risk Behavior Web-based Survey"[URL]
- "Scikit-learn machine learning in python: sklearn.preprocessing. OrdinalEncoder"[URL]
- Chawla NV, "Editorial : special issue on learning from imbalanced data sets", ACM SIGKDD Explor Newsletter, 6, pp.1~6 (2004)
- Lee JH, "Development of machine learning technology for extremely imbalanced data", pp.2019
- "Histogram-based gradient boosting ensembles in python"[URL]
- 정한나, "불균형 이분 데이터 분류분석을 위한 데이터마이닝 절차", 대한산업공학회지, 36(1), pp.13~21 (2010), 대한산업공학회
- "xgboost: eXtreme Gradient Boosting. Package Version: 1.7.5.1"[URL]
- 이윤주, "로지스틱 회귀모형과 의사결정 나무모형을 활용한 청소년 자살 시도 예측모형 비교: 2019 청소년 건강행태 온라인조사를 이용한 2차 자료분석", Journal of Korean Academy of Nursing, 51(1), pp.40~53 (2021), 한국간호과학회
- Ke G, "LightGBM:a highly efficient gradient boosting decision tree", Proceedings of Advances in Neural Information Processing Systems 30 (NIPS 2017) (2017), NIPS
- Whiting D, "How accurate are suicide risk prediction models? Asking the right questions for clinical practice", Evid Based Ment Health, 22, pp.125~128 (2019)
- Grimes DA, "Uses and abuses of screening tests", Lancet, 359, pp.881~884 (2002)
- 김상미, "청소년의 자살 생각·계획·시도 추이: 청소년 건강행태조사중심으로(2011-2020년)", 의료경영학연구, 16(1), pp.37~48 (2022), 경영연구원[DOI]