Abstract:
Childbirth delivery method is an essential determinant for the health of mother and child.
Choosing the wrong type of childbirth delivery causes different kinds of complications on
the mother and new born child.
This research work aims to design a machine learning model for prediction of childbirth
delivery method which can support the gynecologists in decision making process.
Predicting the correct delivery method has significance in reducing maternal mortality
and morbidity rate by avoiding complications associated with wrong delivery method.
KNN, RF and SVM algorithms are implemented as base learners and a Stacking Ensemble
method with ANN algorithm as super learner to develop childbirth delivery method
prediction model.
Confusion matrix and its derivatives; Accuracy, Precession, Recall and F1-score are used
to evaluate the performance of the proposed model. Execution Time is also used to
compare the time taken to execute the models.
The study result shows that the model implemented using Stacking Ensemble method with
ANN achieved the best Recall and Accuracy results of 90.9% and 95.2% respectively.