Effectiveness of Contraceptive Usage among Reproductive Ages in Nigeria Using Artificial Neural Network
Loading...
Date
2018
Journal Title
Journal ISSN
Volume Title
Publisher
School of Engineering and Computing, University of the West of Scotland - Computing and Information Systems Journal, 22(1), 24 – 34
Abstract
Purpose: Contraceptive usage among women of
reproductive age is a fertile area of research for the
medical scientists, social scientists, and medical
practitioners. However, not much work has been done
in Nigeria to identify some of the contraceptive
methods used in preventing unwanted pregnancy
and sexually transmitted infection (STI) diseases,
particularly to explicitly determine which of them are
most effective. This paper tackles this task.
Methodology: In this paper, we examine different
types of contraceptive methods used by Nigeria
women to prevent unwanted pregnancy. Datasets on
contraceptive usage among 28,647 women of
reproductive age from the 2008 Nigerian Demographic
Health Survey (NDHS) were analyzed using Artificial
Neural Network (ANN) approach in the R language.
Finding/Results: The results of the analysis revealed
that approximately 1%, 3% and 9% of the study
population were using Folkloric, Traditional and
Modern methods, respectively. Additionally, 12%, 3%
and 9% of the women were found to be currently
using the methods since last birth and before last birth.
Furthermore, the ANN results through the Garson
algorithm revealed that using the modern methods
(IUD, Norplant and Female condom) and the
traditional methods prevents the unwanted pregnancy
negatively, while other modern methods (pill, male
condom, female sterilizer, periodic abstinence,
withdrawal, locational amenorrhea and foam or jelly)
were found to be effective in preventing unwanted
pregnancy positively. Interestingly, women that used
the modern methods (i.e. Pill, IUD, Injection, Male
condom, Female sterilization, Periodic abstinence,
Withdrawal and Lactational amenorrhea) were found
to be effective in preventing unwanted pregnancy.
Research Limitation: The main limitation of this
study is the inability to access the current data from
NDHS. Therefore, the conclusion of this study is only
based on the 2008 NDHS data.
Originality/Value: This research work introduces
artificial neural network (ANN) to determine and
identify the effect of contraceptive methods usage
among Nigeria women, and to determine their level of
important using Garson's algorithm variable important.
This introduction measures the nonlinear effect that
exists between the methods and response variable
(pregnant and no pregnant) which existing research
approaches do not.
Keywords: Contraceptive methods, Variable
Important, Garson Algorithm, Artificial Neural
Network (ANN) and Data mining