Neural Computing & Applications

, Volume 6, Issue 3, pp 158–164 | Cite as

Comparison of neural networks and statistical models to predict gestational age at birth

  • J. L. Eastaugh
  • S. W. Smye
  • S. Snowden
  • J. J. Walker
  • P. R. F. Dear
  • A. Farrin


The aim of this study was to produce models for the prediction of high risk pregnancies, with particular emphasis on pre-term delivery. Neural network and logistic regression models have been developed utilising pregnancy and delivery data spanning a period of seven years. Five input factors were used as explanatory variables: age, number of previous still births, gestational age at first clinical assessment, diabetes and a measure of socio-economic status. There was little difference between average model performance for the two techniques: optimal neural network performance was achieved with a fully connected feed forward network comprising a single hidden layer of three nodes and single output node. This produced a Receiver Operating Characteristic (ROC) curve area of 0.700. The ROC area for logistic regression models was 0.695. The performance of these models reflected weak associations within the data. However, performance is encouraging given the relatively limited number of predictive inputs.


High risk pregnancy Logistic regression Neural networks Pre-term delivery Receiver Operating Characteristic curve 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Audit commission. First class delivery: improving maternity services in England and Wales, 1997Google Scholar
  2. 2.
    Chamberlain G, Philip E, Howlett B, Masters K. British Births. 1970 volume 2, Obstetric care. William Heinmann Medical Books, 1978Google Scholar
  3. 3.
    Creasy RK, Beverly A, Gummer NZ, Graham C, Liggins MD. System for predicting spontaneous preterm birth. Obstetrics and Gynaecology 1980; 55(6): 692–695Google Scholar
  4. 4.
    Huesten WJ. Development of a Caesarean delivery risk score. Obstetrics and Gynaecology 1994; 84: 965–968Google Scholar
  5. 5.
    Martel M, Wacholder S, Lippman A, Brohan J, Hamilton E. Maternal age and primary Caesarean section rates: a multivariate analysis. Am J Obstetrics and Gynaecology 1987; 156: 30–38Google Scholar
  6. 6.
    Huesten WJ, Rudy M. Factors predicting elective repeat Caesarean delivery. Obstetrics and Gynaecology 1994; 83: 741–744Google Scholar
  7. 7.
    Knox AJ, Sadler MB, Pattison NS, Mantell CD, Mullins P. An obstetric scoring system: its development and application in obstetric management. Obstetrics and Gynaecology 1993; 81: 195–199Google Scholar
  8. 8.
    Narayanan MN, Lucas SB. A genetic algorithm to improve a neural network to predict a patients' response to warfarin. Methods of Informatics in Medicine 1993; 32: 55–58Google Scholar
  9. 9.
    Tarassenko L, Whitehouse R, Gasparini G, Harris AL. Neural network prediction of relapse in breast cancer patients. Neural Comput Applic 1996; 4(2): 105–113Google Scholar
  10. 10.
    Beksac MS, Durak B, Ozkan O, Cahar AN, Baki S, Karakas I, Leleli Y. An artificial intelligent diagnostic system with neural networks to determine genetic disorders and foetal health by using maternal serum markers. Euro J Obstetrics and Gynaecology and Reproductive Biology 1995; 59: 131–136Google Scholar
  11. 11.
    Rumellhart DE, Hinton GE, Williams RJ. Learning representations by back propagating errors. Nature 1986; 323: 533–536Google Scholar
  12. 12.
    Ripley BD. Pattern Recognition and Neural Networks. Oxford University Press, 1996Google Scholar
  13. 13.
    Department of Trace and Industry. Neural computing — learning solutions. Best practice guidelines for developing neural computing applications, 1994Google Scholar
  14. 14.
    Bishop CM. Neural networks for pattern recognition. Clarendon Press, 1995Google Scholar
  15. 15.
    Ripley BD. Neural networks and related methods for classification. JR Statist Soc 1994; 56(3): 409–456Google Scholar
  16. 16.
    Armitage P. Statistical Methods in Medical Research. Blackwell Scientific, 1971Google Scholar
  17. 17.
    Ingram D, Block R. Mathematical Methods in Medicine. Part 1: Statistical and analytical techniques. Wiley, 1994Google Scholar
  18. 18.
    Flury B, Riedwyl H. Multivariate statistics — a practical approach. Chapman & Hall, 1988Google Scholar
  19. 19.
    Spackman KA. Combining logistic regression and neural networks to create predictive models. Proc Ann Symposium on Computer Applications in Medical Care 1993; 456–459Google Scholar
  20. 20.
    Beale R and Jackson T. Neural Computing — An Introduction. Institute of Physics Publishing, 1990Google Scholar
  21. 21.
    Hornik K. Approximation capabilities of multilayer feed-forward networks. Neural Networks 1991; 4(2): 251–257Google Scholar
  22. 22.
    Kreinovich VY. Arbitrary nonlinearity is sufficient to represent all functions by neural networks: a theorem. Neural Networks 1991; 4(3); 381–383Google Scholar
  23. 23.
    Jarman B. Underprivileged areas: validation and distribution of scores. Br Medical J 1984; 289: 1585–1588Google Scholar
  24. 24.
    Hinton GE. Connectionist learning procedures. Artif Intell 1989; 40: 185–234Google Scholar
  25. 25.
    Gori M, Tesi A. On the problem of local minima in back-propagation. IEEE Trans Patt Anal Mach Int 1992; 14(1): 76–85Google Scholar
  26. 26.
    Amirikan B, Nishimura H. What size network is good for generalization of a specific task of interest? Neural Networks 1994; 7(2): 321–329Google Scholar
  27. 27.
    Wasserman PD. Neural Computing: Theory and practice. Von Nostrand Reinhold, 1989Google Scholar
  28. 28.
    SAS Institute Inc. SAS/Stat Users Guide. Volumes 1 and 2, 1994Google Scholar
  29. 29.
    Henderson AR. Assessing test accuracy and its clinical consequences: a primer for receiver operating characteristic curve analysis. Ann Clin Biochem 1993; 30: 521–539Google Scholar
  30. 30.
    Strike PW. Statistical Methods in Laboratory Medicine. Butterworth-Heinemann, 1991Google Scholar
  31. 31.
    Vining DJ, Gladish GW. Receiver operating characteristic curves: a basic understanding. Radiographics 1992; 12: 1147–1150Google Scholar

Copyright information

© Springer-Verlag London Limited 1997

Authors and Affiliations

  • J. L. Eastaugh
    • 1
  • S. W. Smye
    • 1
  • S. Snowden
    • 1
  • J. J. Walker
    • 2
  • P. R. F. Dear
    • 3
  • A. Farrin
    • 4
  1. 1.Department of Medical PhysicsSt James's University HospitalLeedsUK
  2. 2.Departments of Obstetrics and GynaecologySt James's University HospitalLeedsUK
  3. 3.Department of Neonatal UnitSt James's University HospitalLeedsUK
  4. 4.Departments of Research and DevelopmentSt James's University HospitalLeedsUK

Personalised recommendations