Comparative Analysis of Predictive Models for the Likelihood of Infertility in Women Using Supervised Machine Learning Techniques
Journal Title: Computer Reviews Journal - Year 2018, Vol 1, Issue 2
Abstract
Infertility is a worldwide problem, affecting 8% – 15% of the couples in their reproductive age. WHO estimates that there are 60 - 80 million infertile couples worldwide with the highest incidence in some regions of Sub-Saharan Africa also infertility rate may reach 50% compared to 20% in Eastern Mediterranean Region and 11% in the developed world. Infertility has caused considerable social, emotional and psychological stress between couples, among families, within the individual concerned and the society at large. Historical data constituting information describing the risk factors of infertility alongside the respective infertility likelihood status of women was collected from Obafemi Awolowo University Teaching Hospital Complex (OAUTHC). The predictive model was formulated using naïve Bayes’, decision trees and multi-layer perceptron algorithm – supervised machine learning algorithms. The formulated model was simulated using the Waikato Environment for Knowledge Analysis (WEKA) environment. The results of the performance evaluation of the machine learning algorithms showed that the C4.5 decision trees and the multi-layer perceptron with an accuracy of 74.4% each outperformed the naïve Bayes’ algorithm. In addition, the decision trees algorithm recognized variables relevant to predicting infertility and a rule that can be applied on patient risk factor records for infertility likelihood prediction was deduced from the tree structure. This showed how effective machine learning algorithms can be used in predicting the likelihood of infertility in Nigerian women.
Authors and Affiliations
Jeremiah Ademola Balogun
Keywords
Related Articles
- EP ID EP477709
- DOI -
- Views 112
- Downloads 0
A Theoretical Overview of Mobile Networks Environment in Ecuador Prior To 5G
Many countries in the Latin American region experience the technology gap when new technologies are either developing or in testing scenarios. Telecommunications services provider must be encouraged, allowing universal a...
The MOUSE approach: Mapping Ontologies using UML for System Engineers
To address the problem of semantic heterogeneity, there has been a large body of research directed toward the study of semantic mapping technologies. Although various semantic mapping technologies have been investigated,...
ARMED for the Mobile Processing War
This article offers an explanation for why the ARM computer architecture won the hearts and minds of the mobile device manufacturers when incumbents like Intel and AMD had such a huge head start and such a large economic...
Enhanced AODV Protocol for Hybrid Wireless Network
Performance of algorithms in hybrid wireless network routing environments depends on end to end communication delay. Due to the fact that the end to end communication delay includes delay needed for finding the routing p...
Ransomware: A New Era of Digital Terrorism
This work entails the study of ten nasty ransomwares to reveal out the analytical similarities and differences among them, which will help in understanding the mindset of cyber crooks crawling over the dark net. It also...