Journal of Digital Convergence (디지털융복합연구)

The Society of Digital Policy and Management (한국디지털정책학회)
권호 표지
DOI QR코드

DOI QR Code

Design of Fetal Health Classification Model for Hospital Operation Management

효율적인 병원보건관리를 위한 태아건강분류 모델

  • Received : 2021.03.14
  • Accepted : 2021.05.20
  • Published : 2021.05.28
Download PDF
⟨ Previous Next ⟩

Abstract

The purpose of this study was to propose a model which is suitable for the actual delivery system by designing a fetal delivery hospital operation management and fetal health classification model. The number of deaths during childbirth is similar to the number of maternal mortality rate of 295,000 as of 2017. Among those numbers, 94% of deaths are preventable in most cases. Therefore, in this paper, we proposed a model that predicts the health condition of the fetus using data like heart rate of fetuses, fetal movements, uterine contractions, etc. that are extracted from the Cardiotocograms(CTG) test using a random forest. If the redundancy of the data is unbalanced, This proposed model guarantees a stable management of the fetal delivery health management system. To secure the accuracy of the fetal delivery health management system, we remove the outlier which embedded in the system, by setting thresholds for the upper and lower standard deviations. In addition, as the proportion of the sequence class uses the health status of fetus, a small number of classes were replicated by data-resampling to balance the classes. We had the 4~5% improvement and as the result we reached the accuracy of 97.75%. It is expected that the developed model will contribute to prevent death and effective fetal health management, also disease prevention by predicting and managing the fetus'deaths and diseases accurately in advance.

본 연구에서는 병원에서 실질적인 태아분만 시스템에 관리를 위한 태아건강분류모델을 설계하는 것을 목적으로 한다. 출산 중 사망자 수는 2017년을 기준으로 295,000명인 산모 사망률과 유사하다. 이러한 사망의 94%는 환경에 의해 발생하므로 대부분 예방할 수 있다. 따라서 본 논문에서는 랜덤 포레스트(Random Forest)를 이용하여 Cardiotocograms(CTG) 검사에서 추출한 2개의 데이터(태아의 심박수, 태아의 움직임, 자궁 수축 등)로 태아의 건강을 예측하는 모델을 제안하였다. 본 연구에서 제안된 모델은 태아분만 보건운영 시스템을 안정적으로 관리하기 위해 태아분만에 대한 데이터의 분포가 불균형한 이상 데이터를 갖는 항목을 찾아 표준편차의 상한 및 하한의 임계값을 설정하여 이상값을 제거하여 정확도를 높혔다. 또한 태아의 건강상태를 나타내는 클래스의 비율이 불규칙함으로, 데이터 리샘플링을 이용하여 소수의 클래스를 복제하여 클래스의 균형을 맞추었다. 그 결과 정확도가 4~5% 향상되어 97.75%로 나타났다. 이에 예측 모델을 통해 발생 할 수 있는 태아의 사망과 병을 사전에 정확히 예측하여 우선적으로 관리함으로써 효율적인 태아 보건운영과 태아 사망 및 병 예방에 기여할 수 있을 것이라고 기대한다.

Keywords

References

  1. J. H. Oh. (2021). A study on prediction for reflecting variation of fertility rate by province under ultra-low fertility in Korea. The Korean Journal of applied Statistics, 34(1), 75-98. https://doi.org/10.5351/KJAS.2021.34.1.075
  2. D. C. Kim. (2018). Effect of the Child Benefit on the Increase of the Total Fertility Rate. The Journal of Korean Public Policy, 20(2), 3-25. DOI : 10.37103/kapp.20.2.1
  3. S. M. Lee & H. R. Song. (2018). Proposal on the Definition of the New Social Indicator, the Effective Total Dependency Ratio, and its Application - Focusing on the Effects on Raising Fertility Rate, Migration and Extending Retirement Age. Korea Journal of Population Studies, 41(2), 91-116. DOI : 10.31693/kjps.2018.06.41.2.91
  4. Alison Smale. (2018). What the SDGs mean. UN Chronicle, 55(2), 6-7. DOI : 10.18356/ca912345-en
  5. Priya Priyadarshini & P.C. Abhilash. (2018). Sustainability science and research for attaining UN-SDGs. Journal of Cleaner Production, 184, 609-610. DOI : 10.1016/j.jclepro.2018.02.270
  6. Hossein Foroozand & Steven Weijs. (2017). Entropy Ensemble Filter: A Modified Bootstrap Aggregating (Bagging) Procedure to Improve Efficiency in Ensemble Model Simulation. Entropy, 19(10), 520. DOI : 10.3390/e19100520
  7. S Pavan Kumar Reddy & U Sesadri. (2013). A Bootstrap Aggregating Technique on Link-Based Cluster Ensemble Approach for Categorical Data Clustering. INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY, 10(8), 1913-1921. DOI : 10.24297/ijct.v10i8.1468
  8. Carlos J. Mantas. Javier G. Castellano. Serafin Moral-Garcia & Joaquin Abellan. (2019). A comparison of random forest based algorithms: random credal random forest versus oblique random forest. Soft Computing, 23(21), 10739-10754. DOI : 10.1007/s00500-018-3628-5
  9. Vikas Jain & Ashish Phophalia. (2020). M-ary Random Forest - A new multidimensional partitioning approach to Random Forest. Multimedia Tools and Applications. DOI : 10.1007/s11042-020-10047-9
  10. Robert P. Sheridan. (2013). Using Random Forest To Model the Domain Applicability of Another Random Forest Model. Journal of Chemical Information and Modeling, 53(11), 2837-2850. DOI : 10.1021/ci400482e
  11. Daniel S. Chapman. Aletta Bonn. William E. Kunin & Stephen J. Cornell. (2009). Random Forest characterization of upland vegetation and management burning from aerial imagery. Journal of Biogeography, 37(1), 37-46. DOI : 10.1111/j.1365-2699.2009.02186.x