Journal of Korea Society of Industrial Information Systems (한국산업정보학회논문지)

Korea Society of Industrial Information Systems (한국산업정보학회)
권호 표지
DOI QR코드

DOI QR Code

Development of Long-Term Hospitalization Prediction Model for Minor Automobile Accident Patients

자동차 사고 경상환자의 장기입원 예측 모델 개발

  • Received : 2023.08.25
  • Accepted : 2023.11.19
  • Published : 2023.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

The cost of medical treatment for motor vehicle accidents is increasing every year. In this study, we created a model to predict long-term hospitalization(more than 18 days) among minor patients, which is the main item of increasing traffic accident medical expenses, using five algorithms such as decision tree, and analyzed the factors affecting long-term hospitalization. As a result, the accuracy of the prediction models ranged from 91.377 to 91.451, and there was no significant difference between each model, but the random forest and XGBoost models had the highest accuracy of 91.451. There were significant differences between models in the importance of explanatory variables, such as hospital location, name of disease, and type of hospital, between the long-stay and non-long-stay groups. Model validation was tested by comparing the average accuracy of each model cross-validated(10 times) on the training data with the accuracy of the validation data. To test of the explanatory variables, the chi-square test was used for categorical variables.

자동차보험 교통사고 진료비는 매년 증가하고 있다. 본 연구는 교통사고 진료비용 상승의 주요 항목인 경상환자 중 장기입원환자(18일 이상)를 예측하는 모델을 decision tree 등 5개 알고리즘을 이용하여 생성하고, 장기입원에 영향을 미치는 요인을 분석했다. 그 결과, 예측 모델의 정확도는 91.377 ~ 91.451이며 각 모델 사이에 큰 차이점은 없었으나 random forest와 XGBoost 모델이 91.451로 가장 높았다. 설명변수 중요도에 있어서 병원 소재지, 상병명, 병원 종류 등 장기환자군과 비 장기입원 환자군 사이에 모델마다 상당한 차이가 있었다. 모델 평가는 훈련 데이터의 교차검증(10회)한 모델별 평균 정확도와 실험 데이터의 정확도를 상호 비교한 결과로 검정했다. 설명변수 유의성 검증을 위해 범주형 변수는 카이제곱 테스트를 실시하였다. 본 논문의 연구 결과는 경상 환자들의 과잉진료 및 사회적 보험료 비용을 줄이는 진료행태 분석에 도움이 될 것이다.

Keywords

Acknowledgement

이 논문은 한국연구재단 바이오·의료기술개발사업(NRF-2022M3A9E4017033) 및 2019년도 강릉원주대학교 신임교원 연구비 지원에 의하여 수행한 연구임.

References

  1. Abujaber, M. A. F., Al-Majali, O., Azab, M., Ababneh, B., Alqasrawi, O., Abusamak, M., Al-Hadidi, D. and Al-Mousa, D. (2020). Predictors of prolonged hospital stay following a motor vehicle crash: A systematic review and meta-analysis, Injury Epidemiology, 7(1), 50
  2. Adeleke, I. F., Adebiyi, M. O. and Adekunle, O. B. (2018). Predicting the length of hospital stay of road traffic accident victims: A comparative study between regression analysis and decision tree techniques, Journal of P ublic Health, 26(4), 375-382.
  3. Almuheidi, S., Alaklabi, A., Miroshnichenko, A. and Almutairi, A., (2021). Prediction of hospital stay in acute traumatic brain injury: A machine learning approach, Journal of Head Trauma Rehabilitation, 36(1), E31-E37.
  4. Byun, K. K., Lee, D. G. and Lee, H. D. (2023). Machine Learning-Based Prediction Technology for Medical Treatment Period of Automobile Insurance Accident Patients, Convergence security journal, Vol.23 No.1, 89-95
  5. FSS. (2022). Reorganization of compensation process in line with the implementation of measures for auto insurance miner patients, Press Release(Reported on Dec. 29, 2022.)
  6. HIRA. (2022). Car Insurance Medical Expenses Statistics
  7. Jeon, Y. S. (2022). Changes in the Economic Environment and Over-Treatment of Minor Patients in Auto Insurance, KIRI Report, Vol. 542, 8-13.
  8. KoROAD. (2023). Traffic Accident Analysis System.
  9. Lee, D. G., Byun, K. K., Lee, H. D. and Shin, S. H. (2023). The Prediction of Survival of Breast Cancer Patients Based on Machine Learning Using Health Insurance Claim Data, Korea Industrial Information Systems Society Journal, 28(2), 1-9.
  10. MLIT. (2022). Prevention of leakage of car insurance money, such as excessive medical treatment for minor patients, Press Release, (Reported on Aug. 7th, 2022)
  11. MOHW. HIRA. (2023). Healthcare utilization statistics for 2021
  12. Kang, S. O., Kim, S. H. and Ryu, M. H. (2022). Analysis of Hypertension Risk Factors by Life Cycle Based on Machine Learning, Korea Industrial Information Systems Society Journal, 27(5), 73-82.
  13. Park, D. A., Hwang, J. S., Lee, S. H., Sul, A. R., Choi, W. J., Oh, S. H., Lee, J. Y., Lee, Y. K., Lee, D. H. and Choi, S. G. (2014). Systematic review of diagnostic tests. National Evidence-based Healthcare Collaborating Agency.
  14. Yun, S. O., Jung, J. G., Wo, H. G. and Kim, J. E. (2022). Breast Cancer Survival Prediction: Model Comparison and Effect of Genetic Features, Database Research, 38(1), 3-15.