The Journal of Information Systems (한국정보시스템학회지:정보시스템연구)

Korea Association of Information Systems (한국정보시스템학회)
권호 표지
DOI QR코드

DOI QR Code

Development of a Predictive Model forOccupational Disability Grades Using Workers'Compensation Insurance Data

산재보험 빅데이터를 활용한 장해등급 예측 모델 개발

  • 최근호 (국립한밭대학교 융합경영학과) ;
  • 김민정 (한국소비자원 정책연구실) ;
  • 이정화 (근로복지공단 근로복지연구원)
  • Received : 2024.08.05
  • Accepted : 2024.09.11
  • Published : 2024.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

Purpose A prediction model for occupational injuries can support more proactive, efficient, and effective policy-making. This study aims to develop a model that predicts the severity of occupational injuries, classified into 15 disability grades in South Korea, using machine learning techniques applied to COMWEL data. The primary goal is to improve prediction accuracy, offering an advanced tool for early intervention and evidence-based policy implementation. Design/methodology/approach The data analyzed in this study consists of 290,157 administrative records of occupational injury cases collected between 2018 and 2020 by the Korea Workers' Compensation & Welfare Service, based on the 'Workers' Compensation Insurance Application Form' submitted for occupational injury treatment. Four machine learning models - Decision Tree, DNN, XGBoost, and LightGBM - were developed and their performances compared to identify the optimal model. Additionally, the Permutation Feature Importance (PFI) method was used to assess the relative contribution of each variable to the model's performance, helping to identify key variables. Findings The DNN algorithm achieved the lowest Mean Absolute Error (MAE) of 0.7276. Key variables for predicting disability grades included the severity index, primary disease code, primary disease site, age at the time of the injury, and industry type. These findings highlight the importance of early policy intervention and emphasize the role of both medical and socioeconomic factors in model predictions. The academic and policy implications of these results were also discussed.

Keywords

References

  1. 고용노동부, 산업재해현황, 고용노동부, 2024.
  2. 고용노동부, 2022년도 산재보험 사업연보, 고용노동부, 2023. 
  3. 고창완, 김현민, 정영선, 김재희, "차대차 교통사고에 대한 상해 심각도 예측 연구", 한국 ITS 학회 논문지, 제19권, 제4호, 2020, pp. 13-29. 
  4. 근로복지공단, 2022년도 근로복지공단 통계연보, 근로복지공단 근로복지연구원, 2023. 
  5. 박종호, 강성홍, "머신러닝을 이용한 신경계통의 질환 퇴원환자의 중증도 보정재원일수 예측 모형 개발", 한국보건사회연구, 제39권, 제1호, 2019, pp. 390-427. 
  6. 송선영, 오종은, "산재신청 시 사업주 날인제도폐지 정책의 효과성 분석", 근로복지공단 근로복지연구원. 2023. 
  7. 신슬비, 뇌심혈관계 질병 산재DB를 활용한 머신러닝 기반 모델 연구, 근로복지공단 근로복지연구원. 2022. 
  8. 안준모, 문성욱, 이창용, "인텔리전트 규제: 인공지능을 활용한 산재보험 검증 사례를 중심으로", 한국행정연구, 제31권, 제4호, 2022, pp. 27-50. 
  9. 유동희, 정석훈, 이정화, 최근호, "산재보험 빅데이터를 활용한 산재 모니터링 지리정보시스템 개발", 정보시스템연구, 제31권, 제2호, 2022, pp. 217-238. 
  10. 이덕규, 남동현, 허성필, "자동차 사고 경상환자의 장기입원 예측 모델 개발", 한국산업정보학회논문지, 제28권, 제6호, 2023, pp. 11-20. 
  11. 이용범, 조은기, 윤창용, 박성근, "공개 교통사고 데이터베이스와 기계 학습을 이용한 탑승자의 상해 등급 예측에 관한 연구", 전기학회논문지, 제68권, 제7호, 2019, pp. 866-871. 
  12. 장태용, 성윤정, "공공 빅데이터를 이용한 산재환자의 재활 급여현황", 고령자치매작업치료학회지, 재16권, 제2호, 2022, pp. 107-116. 
  13. 전민성, 고재필, 최경주, "이미지 캡셔닝 기반의 새로운 위험도 측정 모델", 정보시스템 연구, 제32권, 제4호, 2023, pp. 119-136. 
  14. 최근호, 이승욱, 산재환자 중증도 지수 개발, 근로복지공단 근로복지연구원, 2016. 
  15. Ayala, F., Lopez-Valenciano, A., Martin, J. A. G., Croix, M. D. S., Vera-Garcia, F. J., del Pilar Garcia-Vaquero, M., Ruiz-Perez, I., and Myer, G. D., "A Preventive Model for Hamstring Injuries In Professional Soccer: Learning Algorithms," International Journal of Sports Medicine, Vol. 40, No. 5, 2019, pp. 344-353. 
  16. Kakhki, F. D., Freeman, S. A., and Mosher, G. A., "Evaluating Machine Learning Performance in Predicting Injury Severity in Agribusiness Industries," Safety Science, Vol. 117, 2019, pp. 257-262. 
  17. Koklonis, K., Sarafidis, M., Vastardi, M., and Koutsouris, D., "Utilization of Machine Learning in Supporting Occupational Safety and Health Decisions in Hospital Workplace," Engineering, Technology & Applied Science Research, Vol. 11, No. 3, 2021, pp. 7262-7272. 
  18. Hallowell, M. R., Alexander, D., and Gambatese, J. A., "Energy-based Safety Risk Assessment: Does Magnitude and Intensity of Energy Predict Injury Severity?," Construction Management and Economics, Vol. 35, No. 1-2, 2017, pp. 64-77. 
  19. Kijowski, R., Liu, F., Caliva, F., and Pedoia, V., "Deep Learning for Lesion Detection, Progression, and Prediction of Musculoskeletal Disease." Journal of Magnetic Resonance Imaging, Vol. 52, No. 6, 2020, pp. 1607-1619. 
  20. Mafi, S., AbdelRazig, Y., and Doczy, R., "Machine Learning Methods to Analyze Injury Severity of Drivers from Different Age and Gender Groups," Transportation Research Record, Vol. 2672, No. 38, 2018, pp. 171-183. 
  21. Sarkar, S., Pramanik, A., Maiti, J., and Reniers, G., "Predicting and Analyzing Injury Severity: A Machine Learning-based Approach using Class-imbalanced Proactive and Reactive Data," Safety Science, Vol. 125, 2020, 104616. 
  22. Sayed, S. A. F., Elkorany, A. M., and Mohammad, S. S., "Applying Different Machine Learning Techniques for Prediction of COVID-19 Severity," Ieee Access, Vol. 9, 2021, pp. 135697-135707. 
  23. Siyuan W., Ying R., and Bisheng X., "Estimation of Urban AQI based on Interpretable Machine Learning," Environmental Science and Pollution Research, Vol. 30, No. 42, 2023, pp. 1-13. 
  24. Yu, H., Yuan, R., Li, Z., Zhang, G., and Ma, D. T., "Identifying Heterogeneous Factors for Driver Injury Severity Variations in Snow-related Rural Single-vehicle Crashes," Accident Analysis & Prevention, Vol. 144, 2020, 105587. 
  25. Zhang, J. Z. Li, Z. Pu and Xu, C., "Comparing Prediction Performance for Crash Injury Severity Among Various Machine Learning and Statistical Methods," in IEEE Access, Vol. 6, 2018, pp. 60079-60087. 
  26. Zoabi, Y., Deri-Rozov, S., and Shomron, N., "Machine Learning-based Prediction of COVID-19 Diagnosis based on Symptoms," npj Digital Medicine, Vol. 4, No. 1, 2021, pp. 1-5.