SVM Based Predictive Model for SGA Detection

  • Haowen Mo
  • Jianqiang Li
  • Shi Chen
  • Hui Pan
  • Ji-Jiang YangEmail author
  • Qing Wang
  • Rui Mao
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9677)


The medical diagnosis process can be interpreted as a decision making process, which doctors determine whether a person is suffering from a disease based on the medical examination. This process can also be computerized in order to present medical diagnostic procedures in an accurate, objective, rational, and fast way. This paper presents a detection model for small for gestational age (SGA) based on support vector machine (SVM). For this purpose, a dataset was adopted from pregnancy eugenic investigation to train the classification model. Then empirical experiments were conducted for SGA detection. The results indicate that support vector machine is considerably effective to detect SGA to help doctors make the final diagnosis.


Small for gestational age Support vector machine Classification Healthcare 



This work is supported by Beijing Natural Science Foundation (4152007), China National Key Technology Research and Development Program project with no. 2013BAH19F01 and Guangdong Key Laboratory of Popular High Performance Computers, Shenzhen Key Laboratory of Service Computing and Applications.


  1. 1.
    Gardosi, J.O.: Prematurity and fetal growth restriction. Early Hum. Dev. 81, 43–49 (2005)CrossRefGoogle Scholar
  2. 2.
    Gardosi, J., Kady, S.M., McGeown, P., Francis, A., Tonks, A.: Classification of stillbirth by relevant condition at death (ReCoDe): population based cohort study. BMJ 331, 1113–1117 (2005)CrossRefGoogle Scholar
  3. 3.
    Basso, O., Frydenberg, M., Olsen, S.F., Olsen, J.: Two definitions of “small size at birth” as predictors of motor development at sixmonths. Epidemiology 16(5), 657–663 (2005)CrossRefGoogle Scholar
  4. 4.
    Ounsted, M., Moar, V.A., Scott, A.: Small-for-dates babies, gestationalage, and developmental ability at 7 years. Early Hum. Dev. 19(2), 77–86 (1989)CrossRefGoogle Scholar
  5. 5.
    Sommerfelt, K., Sonnander, K., Skranes, J., Andersson, H.W., Ahlsten, G., Ellertsen, B., et al.: Neuropsychologic and motor function in small-for-gestation preschoolers. Pediatr. Neurol. 26(3), 186–191 (2002)CrossRefGoogle Scholar
  6. 6.
    Lindqvist, P.G., Molin, J.: Does antenatal identification of small-for-gestational age fetuses significantly improve their outcome? Ultrasound Obstet. Gynecol. 25, 258–264 (2005)CrossRefGoogle Scholar
  7. 7.
    Li, J., Liu, C., Liu, B., Mao, R., Wang, Y., Chen, S., Pan, H., Wang, Q.: Diversity-aware retrieval of medical records. Comput. Ind. 69(1), 30–39 (2015)Google Scholar
  8. 8.
    Yang, J.J., Li, J., Mulder, J., Wang, Y., Wang, Q.: Emerging Information Technologies for Enhanced Healthcare. Comput. Ind. 69(1), 3–11 (2015)CrossRefGoogle Scholar
  9. 9.
    Hastie, S.J., Danskin, F., Neilson, J.P., Whittle, M.J.: Prediction of the small for gestational age twin fetus by doppler umbilical artery waveform analysis. Obstet. Gynecol. 5, 730–733 (1989)Google Scholar
  10. 10.
    Karagianis, G., Akolekar, R.: Prediction of small-for-gestation neonates from biophysical and biochemical markers at 11–13 weeks. Fetal Diagn. Ther. 29(2), 148–154 (2011)CrossRefGoogle Scholar
  11. 11.
    Yang, J.J., Li, J., Shen, R., Zeng, Y., Wang, Q.: Exploiting ensemble learning for automatic cataract detection and grading. Comput. Methods Program. Biomed. 124, 45–57 (2016)CrossRefGoogle Scholar
  12. 12.
    Vapnik, V.N.: The Nature of Statistical Learning Theory. Springer, New York (1995)CrossRefzbMATHGoogle Scholar
  13. 13.
    Boser, B.E., Guyon, I.M., Vapnik, V.N.: A training algorithm for optimal margin classifiers. In: Proceedings of Fifth Annual Workshop Computing Learning Theory, pp. 144–152 (1995)Google Scholar
  14. 14.
    Vapnik, V.N.: An overview of statistical learning theory. IEEE Trans. Neural Netw. 10(5), 988–999 (1999)CrossRefGoogle Scholar
  15. 15.
    Jianguo, X.: A Study on Application of Support Vector Machine in GPC with Real Test Analysis [D]. Master’s degree thesis, Zhejiang University (2006)Google Scholar
  16. 16.
    Fung, G.M., Mangasarian, O.L.: A feature selection newton method support vector machine classification. Comput. Optim. Appl. 28(2), 185–202 (2004)MathSciNetCrossRefzbMATHGoogle Scholar
  17. 17.
    Karatsiolis, S., Schizas, C.N.: Region based support vector machine algorithm for medical diagnosis on Pima Indian Diabetes dataset. In: Proceedings of the BIBE, Larnaca, Cyprus, 11–13 November 2012 (2012)Google Scholar
  18. 18.
    Elshazly, H.I., Elkorany, A.M., Hassanien, A.E.: Lymph diseases diagnosis approach based on support vector machines with different kernel functions. In: 2014 9th International Computer Engineering & Systems (ICCES), 22–23 December 2014, pp. 198–203 (2014)Google Scholar
  19. 19.
    Bentley, P.M., McDonnell, J.T.E.: Wavelet transforms: an introduction. IEEE J. Electron. Commun. Eng. 40, 175–185 (1992)Google Scholar
  20. 20.
    Liu, M., Wang, Q., et al.: Status assessment of preconception health risk exposure in Chinese reproductive women during 2010-2012. Natl. Med. J. China 95(3), 172–175 (2015)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Haowen Mo
    • 1
    • 2
  • Jianqiang Li
    • 1
    • 2
  • Shi Chen
    • 3
  • Hui Pan
    • 3
  • Ji-Jiang Yang
    • 4
    Email author
  • Qing Wang
    • 4
  • Rui Mao
    • 2
  1. 1.School of Software EngineeringBeijing University of TechnologyBeijingChina
  2. 2.Guangdong Key Laboratory of Popular High Performance Computers, Shenzhen Key Laboratory of Service Computing and ApplicationsShenzhenChina
  3. 3.Department of EndocrinologyPeking Union Medical College HospitalBeijingChina
  4. 4.Tsinghua National Laboratory for Information Science and TechnologyTsinghua UniversityBeijingChina

Personalised recommendations