Prediction of risk for cesarean delivery in term nulliparas: a comparison of neural network and multiple logistic regression models


      We sought to develop a neural network (NN) to predict the risk for cesarean delivery (CD) in term nulliparas.

      Study Design

      Using software (BrainMaker for Windows, Version 3.0; California Scientific Software, Nevada City, CA), we trained an NN with 225 patients obtained by chart review and included for nulliparity, singleton vertex > 36 weeks' gestation, and reassuring fetal heart rate on admission. Training inputs included several maternal and fetal clinical variables. Two logistic regression (LR) models using 225 and 600 patients (LR225 and LR600, respectively) were developed. The NN and LR models were tested for prediction of CD in a set of 100 patients not used for development.


      The NN, LR225, and LR600 correctly predicted 53%, 26%, and 32% of the patients with CD and 88%, 95%, and 95% of the patients with vaginal delivery, respectively.


      Compared with LRs, the NN was slightly better in predicting CD and was similar for predicting vaginal delivery in nulliparas with term singletons.

      Key words

      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'


      Subscribe to American Journal of Obstetrics & Gynecology
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect


        • Berghella V.
        • Baxter J.K.
        • Chauhan S.P.
        Evidence-based surgery for cesarean delivery.
        Am J Obstet Gynecol. 2005; 193: 1607-1617
        • National Institutes of Health
        State-of-the-science conference statement: cesarean delivery on maternal request March 27-29, 2006.
        Obstet Gynecol. 2006; 107: 1386-1397
        • Task Force on Cesarean Delivery Rates
        Evaluation of cesarean delivery.
        American College of Obstetricians and Gynecologists, Washington, DC2000
        • Herman A.
        • Groutzd A.
        • Bukovsky I.
        • Arieli S.
        • Sherman D.
        • Caspi E.
        A simplified preinduction scoring method for the prediction of successful vaginal delivery based on multivariate analysis of pelvic and other obstetrical factors.
        J Perinat Med. 1993; 21: 117-124
        • Smith G.C.
        • Dellens M.
        • White I.R.
        • Pell J.P.
        Combined logistic and bayesian modeling of cesarean section risk.
        Am J Obstet Gynecol. 2004; 191: 2029-2034
        • Wilkes P.T.
        • Wolf D.M.
        • Kronbach D.W.
        • Kunze M.
        • Gibbs R.S.
        Risk factors for cesarean delivery at presentation of nulliparous patients in labor.
        Obstet Gynecol. 2003; 102: 1352-1357
        • Vrouenraets F.P.
        • Roumen F.J.
        • Dehing C.J.
        • van den Akker E.S.
        • Aarts M.J.
        • Scheve E.J.
        Bishop score and risk of cesarean delivery after induction of labor in nulliparous women.
        Obstet Gynecol. 2005; 105: 690-697
        • Hendrix N.W.
        • Chauhan S.P.
        • Morrison J.C.
        • Magann E.F.
        • Martin Jr, J.N.
        • Devoe L.D.
        Bishop score: a poor diagnostic test to predict failed induction versus vaginal delivery.
        South Med J. 1998; 91: 248-252
        • Lynch C.M.
        • Sexton D.J.
        • Hession M.
        • Morrison J.J.
        Obesity and mode of delivery in primigravid and multigravid women.
        Am J Perinatol. 2008; 25: 163-167
        • Heffner L.J.
        • Elkin E.
        • Fretts R.C.
        Impact of labor induction, gestational age, and maternal age on cesarean delivery rates.
        Obstet Gynecol. 2003; 102: 287-293
        • Chi C.L.
        • Street W.N.
        • Wolberg W.H.
        Application of artificial neural network-based survival analysis on two breast cancer datasets.
        AMIA Annu Symp Proc. 2007; 11: 130-134
        • Farmer R.M.
        • Medearis A.L.
        • Hirata G.I.
        • Platt L.D.
        Prediction of fetal macrosomia.
        Am J Obstet Gynecol. 1992; 166: 1467
        • Lysikiewicz A.
        • Inglis S.
        • Bracero L.
        • Chervenak F.A.
        • Tejani N.
        Neural network predicts fetal hematocrit in fetal isoimmunization.
        J Matern Fetal Med. 1993; 2: 261-264
        • Kol S.
        • Thaler I.
        • Paz N.
        • Shmueli O.
        Assessment of nonstress test results.
        Am J Obstet Gynecol. 1995; 172: 1372
        • Keith R.D.
        • Beckley S.
        • Garibaldi J.M.
        • Westgate J.A.
        • Ifeachor E.C.
        • Greene K.R.
        A multicenter comparative study of 17 experts and an intelligent computer system for managing labor using the cardiotocogram.
        Br J Obstet Gynecol. 1995; 102: 688
        • Devoe L.D.
        • Samuel S.
        • Prescott P.
        • Work B.A.
        Predicting the duration of the first stage of spontaneous labor using a neural network.
        J Matern Fetal Med. 1996; 5: 256-261
        • Devoe L.D.
        Computerized fetal heart rate analysis and neural networks in antepartum fetal surveillance.
        Curr Opin Obstet Gynecol. 1996; 8: 119-122
        • Devoe L.D.
        • Carlton E.
        • Prescott P.
        Neural network prediction of nonstress test results: how often should we perform nonstress tests?.
        Am J Obstet Gynecol. 1995; 173: 1128-1131