Performance Comparison of Neural Network-Based Models in the Classification of Polycystic Ovary Syndrome Disease
- 1 January 2023
- journal article
- Published by Ordu University in Black Sea Journal of Health Science
- Vol. 6 (1), 20-25
- https://doi.org/10.19127/bshealthscience.1144271
Abstract
In this study, it was aimed to compare the performances of the above mentioned ANN, MLP and deep learning methods to determine polycystic ovary syndrome (PCOS) risk factors and predict PCOS diagnosis. In this study, the data set “Polycystic ovary syndrome” was used to determine PCOS risk factors and to compare the performances of ANN, MLP and deep learning methods for PCOS diagnosis prediction. The performance of the models was evaluated with accuracy, sensitivity, specificity, positive/negative predictive values. Factors associated with PCOS were estimated from the deep learning model that has the best performance. Accuracy, sensitivity, specificity, positive predictive value and negative predictive value obtained from the MLP method were 87.25%, 79.66%, 90.93%, 81.03%, and 90.19%. Accuracy, sensitivity, specificity, positive predictive value and negative predictive value obtained from the Neural Network method were 87.80%, 79.10%, 92.03%, 82.84%, and 90.05%. Accuracy, sensitivity, specificity, positive predictive value and negative predictive value obtained from the Deep Learning method were 89.09%, 81.92%, 92.58%, 84.30%, and 91.33%. According to the findings obtained from this study, the best classification result according to the performance metrics obtained from the artificial neural networks, MLP and deep learning methods used for the PCOS data set used in the study belongs to the deep learning method. As a result, PCOS was successfully classified in the light of the findings obtained from the study, and clinical findings were tried to be revealed by giving the risk factors associated with PCOS.Keywords
This publication has 16 references indexed in Scilit:
- A guide to deep learning in healthcareNature Medicine, 2019
- Development of a novel risk prediction and risk stratification score for polycystic ovary syndromeClinical Endocrinology, 2018
- Derin Öğrenme ve Sağlık Alanındaki UygulamalarıJournal of Turkish Studies, 2018
- Neural Networks and Deep LearningPublished by Springer Science and Business Media LLC ,2018
- Improving the Diagnosis of Liver Disease Using Multilayer Perceptron Neural Network and Boosted Decision TreesJournal of Medical and Biological Engineering, 2017
- New insights into the genetics of polycystic ovary syndromeNature Reviews Endocrinology, 2016
- Yapay sinir ağları ve klinik araştırmalarda kullanımıGenel Tip Dergisi, 2015
- Deep learningNature, 2015
- Deep learning in neural networks: An overviewNeural Networks, 2015
- Discretization approach to EEG signal classification using Multilayer Perceptron Neural Network modelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010