Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Adjustment of Korean Birth Weight Data

한국 신생아의 출생체중 데이터 보정

  • Shin, Hyungsik (School of Electronic and Electrical Engineering, Hongik University)
  • Received : 2017.01.16
  • Accepted : 2017.01.19
  • Published : 2017.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

Birth weight of a new born baby provides very important information in evaluating many clinical issues such as fetal growth restriction. This paper analyzes birth weight data of babies born in Korea from 2011 to 2013, and it shows that there is a biologically implausible distribution of birth weights in the data. This implies that some errors may be generated in the data collection process. In particular, this paper analyzes the relationship between gestational period and birth weight, and it is shown that the birth weight data mostly of gestational periods from 28 to 32 weeks have noticeable errors. Therefore, this paper employs the finite Gaussian mixture model to classify the collected data points into two classes: non-corrupted and corrupted. After the classification the paper removes data points that have been predicted to be corrupted. This adjustment scheme provides more natural and medically plausible percentile values of birth weights for all the gestational periods.

신생아의 출생체중은 자궁내발육부전이나 과체중출생아를 진단하는 데 사용되는 등, 의학적으로 여러 가지 중요한 정보를 제공한다. 본 논문에서는 2011년부터 2013년까지 한국에서 태어난 신생아의 출생체중 데이터를 분석하고, 생물학적으로 부자연스러운 체중 분포를 관찰할 수 있음을 보인다. 이러한 비상식적인 체중 분포는 데이터 수집과정 등에서 오류가 존재함을 의미하는데, 특히 임신주수가 28주에서 32주인 신생아들의 체중 데이터에서 현저한 오류 데이터를 관찰할 수 있다. 이를 보정하기 위해, 본 논문은 가우시안 혼합 모델을 사용하여 오류 데이터와 정상 데이터를 예측하고, 오류 데이터로 예측된 자료들을 삭제하는 과정을 제안한다. 제안된 보정 과정을 통하여 보다 자연스럽고 의학적으로 의미 있는 출생체중 백분율을 구할 수 있음을 보인다.

Keywords

References

  1. S. Paranjothy, F. Dunstan, W. J. Watkins, M. Hyatt, J. C. Demmler, R. A. Lyons, and D. Fone, "Gestational age, birth weight, and risk of respiratory hospital admission in childhood," Pediatrics, vol. 132, no. 6, pp. e1562-1569, Dec. 2013. https://doi.org/10.1542/peds.2013-1737
  2. J. L. Richards, C. Hansen, C. Bredfeldt, R. A. Bednarczyk, M. C. Steinhoff, D. Adjaye-Gbewonyo, K. Ault, M. Gallagher, W. Orenstein, R. L. Davis, and S. B. Omer, "Neonatal outcomes after antenatal influenza immunization during the 2009 H1N1 influenza pandemic: impact on preterm birth, birth weight, and small for gestational age birth," Clinical Infectious Diseases, vol. 56, no. 9, pp. 1216-1222, May 2013. https://doi.org/10.1093/cid/cit045
  3. J. J. Lee, "Birth weight for gestational age patterns by sex, plurality, and parity in Korean population," Korean Journal of Pediatrics, vol. 50, no. 8, pp. 732-739, Aug. 2007. https://doi.org/10.3345/kjp.2007.50.8.732
  4. G. H. Lee, Y. W. Kim, E. J. Seo, M. S. Son, H. G. Ahn, E. W. Seok, Y. J. Choi, G. J. Kim, S. Y. Kim, B. C. Hwang, Y. D. Choi, S. Y. Kim, and S. J. Sohn, "Change of birth weight-gestational age table," Korean Journal of Obstetrics and Gynecology, vol. 44, no. 10, pp. 1851-1856, Oct. 2001.
  5. G. Y. Jung and K. Lee, "Intrauterine growth of Korean infants from 25 weeks to 44 weeks gestation," Journal of the Korean Pediatric Society, vol. 33, no. 7, pp. 887-900, Jul. 1990.
  6. J. J. Lee, C. G. Park, and K. S. Lee, "Birth weight distribution by gestational age in Korean population: using finite mixture model," Korean Journal of Pediatrics, vol. 48, no. 11, pp. 1179-1186, Nov. 2005.
  7. N. M. Talge, L. M. Mudd, A. Sikorskii, and O. Basso, "United States birth weight reference corrected for implausible gestational age estimates," Pediatrics, vol. 133, no. 5, pp. 844-853, May 2015. https://doi.org/10.1542/peds.2013-3285
  8. J. Villar, L. C. Ismail, C. G. Victora, E. O. Ohuma, E. Bertino, D. G. Altman, A. Lambert, A. T Papageorghiou, M. Carvalho, Y. A. Jaffer, M. G. Gravett, M. Purwar, I. O. Frederick, A. J. Noble, R. Pang, F. C. Barros, C. Chumlea, Z. A. Bhutta, and S. H. Kennedy, "International standards for newborn weight, length, and head circumference by gestational age and sex: the Newborn Cross-Sectional Study of the INTERGROWTH-21 st Project," The Lancet, vol. 384, no. 9946, pp. 857-868, Sep. 2014. https://doi.org/10.1016/S0140-6736(14)60932-6
  9. M. S. Kramer, R. W. Platt, S. W. Wen, K. S. Joseph, A. Allen, M. Abrahamowicz, B. Blondel, and G. Breart, "A new and improved population-based Canadian reference for birth weight for gestational age," Pediatrics, vol. 108, no. 2, pp. e35-e35, Aug. 2001. https://doi.org/10.1542/peds.108.2.e35
  10. Statistics Korea, Vital Statistics [Internet]. Available: https://mdis.kostat.go.kr/extract/extSurvSearchByDate.do?extcTypeDivCD=E&curMenuNo=UI_POR_P1070.
  11. E. Parzen, "On estimation of a probability density function and mode," The annals of mathematical statistics, vol. 33, no. 3, pp. 1065-1076, Sep. 1962. https://doi.org/10.1214/aoms/1177704472
  12. R. W. Platt, M. Abrahamowicz, M. S. Kramer, K. S. Joseph, L. Mery, B. Blondel, G. Breart, and S. W. Wen, "Detecting and eliminating erroneous gestational ages: a normal mixture model," Statistics in medicine, vol. 20, no. 23, pp. 3491-3503, Dec. 2001. https://doi.org/10.1002/sim.1095
  13. H. Oja, M. Koiranen, and P. Rantakallio, "Fitting mixture models to birth weight data: a case study," Biometrics, vol. 47, no. 3, pp. 883-897, Sep. 1991. https://doi.org/10.2307/2532646
  14. F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay, "Scikit-learn: Machine learning in Python," Journal of Machine Learning Research, vol. 12, pp. 2825-2830, Oct. 2011.