Caesarean section or commonly called cesarean section is laborartificial, where the fetus is born through an incision in the abdominal wall and uterine wall with the condition that the uterus is intact and the fetus weighs above 2500 grams. Cesarean section cannot be performed if there is no agreement from the patient or family members regarding the surgery. In recent years, the use of machine learning in predicting disease has increased rapidly. One classification technique used in machine learning is artificial neural networks. In this study, we used backpropagation neural networks to predict cesarean section. This study uses a dataset sourced from the UCI Machine Learning Repository. This dataset contains information about the results of the cesarean section of 80 pregnant women with essential characteristics of labor problems in the medical field. Model evaluation is performed using accuracy, sensitivity, and specificity values. The area under curves (AUC) and ROC curves are used to calculate performance evaluations. Based on experimental results, research shows that backpropagation neural networks can be used as an alternative model in determining the cesarean section.
[1]
Khadijah Ismail,et al.
Prediction of Diabetes by using Artificial Neural Network
,
2011
.
[2]
Suwarno Suwarno,et al.
Diagnosis of Diabetes using Support Vector Machines with Radial Basis Function Kernels
,
2016
.
[3]
Marion O. Adebiyi,et al.
Stock Price Prediction using Neural Network with Hybridized Market Indicators
,
2012
.
[4]
Fábio M. Soares,et al.
Neural network programming with Java : unleash the power of neural networks by implementing professional Java code
,
2016
.
[5]
Petra Perner,et al.
Data Mining - Concepts and Techniques
,
2002,
Künstliche Intell..
[6]
B. Milović,et al.
Prediction and Decision Making in Health Care using Data Mining
,
2012
.