TY - JOUR
T1 - Prediction of risk for cesarean delivery in term nulliparas
T2 - a comparison of neural network and multiple logistic regression models
AU - Al Housseini, Ali
AU - Newman, Tondra
AU - Cox, Alan
AU - Devoe, Lawrence D
PY - 2009/1/1
Y1 - 2009/1/1
N2 - Objective: 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. Results: 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. Conclusion: Compared with LRs, the NN was slightly better in predicting CD and was similar for predicting vaginal delivery in nulliparas with term singletons.
AB - Objective: 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. Results: 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. Conclusion: Compared with LRs, the NN was slightly better in predicting CD and was similar for predicting vaginal delivery in nulliparas with term singletons.
KW - cesarean
KW - neural network
KW - prediction
KW - vaginal
UR - http://www.scopus.com/inward/record.url?scp=67649321281&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=67649321281&partnerID=8YFLogxK
U2 - 10.1016/j.ajog.2009.05.001
DO - 10.1016/j.ajog.2009.05.001
M3 - Article
C2 - 19576377
AN - SCOPUS:67649321281
SN - 0002-9378
VL - 201
SP - 113.e1-113.e6
JO - American Journal of Obstetrics and Gynecology
JF - American Journal of Obstetrics and Gynecology
IS - 1
ER -