Prediction of Polycystic Ovary Syndrome Applying Machine Learning Techniques
Prediction of Polycystic Ovary Syndrome Applying Machine Learning Techniques
DOI:
https://doi.org/10.54167/tch.v17i2.1193Keywords:
Polycystic Ovary, Artificial Neural Network, Bayesian Network, KNN, Machine LearningAbstract
Polycystic Ovary Syndrome (PCOS) is one of the most common endocrinopathies among women of reproductive age. Studies show that this pathology affects between 3-15 % of the entire female population. This paper describes the use and comparison of some machine learning algorithms with the aim of offering a window of opportunity in the classification of data in an efficient way. We used three machine learning algorithms to perform a diagnosis of the PCOS using 18 features extracted from the “PCOS Dataset” hosted on the Kaggle.com platform. An Artificial Neural Network (ANN) with 97.5 % F1, a Bayesian algorithm with 97.6 % F1 and a K-Nearest Neighbors (KNN) algorithm with 100 % F1 were designed. The analysis performed showed that the KNN algorithm classifies the data used optimally, suggesting that it can be used to obtain diagnostics in laboratory applications to obtain a complementary evaluation.
Downloads
References
Aguayo-González, P. 2016. Sobrepeso y obesidad, factores de riesgo para desarrollar síndrome de ovario poliquístico. https://www.gob.mx/salud/prensa/sobrepeso-y-obesidad-factores-de-riesgo-para-desarrollar-sindrome-de-ovario-poliquistico
Suha, S.A. & Islam, M.N. 2022. An extended machine learning technique for polycystic ovary syndrome detection using ovary ultrasound image. Nature Scientific Reports 12: 17123. https://doi.org/10.1038/s41598-022-21724-0 *
Cañedo-Figueroa, C. E. & García-Chávez, H. 2021. Diseño de algoritmo compuesto por Machine Learning y un modelo probabilístico para la detección de diabetes. Memorias Del Congreso Nacional de Ingeniería Biomédica 8(1), 57–60. https://memoriascnib.mx/index.php/memorias/article/view/828
Carvajal, R., Herrera, G. & Porcile, J., 2010. Espectro Fenotípico Del Síndrome De Ovario Poliquístico. Rev Chil Obstet Ginecol, 75(2): 124 – 132. http://dx.doi.org/10.4067/S0717-75262010000200009
Denny, A., Raj, A., Ashok, A., Maneesh-Ram, C. & George, R. 2019. i-HOPE: Detection and Prediction System for Polycystic Ovary Syndrome (PCOS) Using Machine Learning Techniques. En: TENCON 2019 - 2019 IEEE Region 10 Conference (TENCON), Kochi, India, 2019, pp. 673-678. https://doi.org/10.1109/TENCON.2019.8929674
Guadamuz-Delgado, J., Miranda-Saavedra, M. & Mora-Miranda, N. 2022. Actualización sobre el síndrome de ovario poliquístico. Revista Médica Sinergia 7(5): e801. https://doi.org/10.31434/rms.v7i5.801
Madhumitha, J., Kalaiyarasi, M. & Ram, S. S. 2021. Automated Polycystic Ovarian Syndrome Identification with Follicle Recognition. En 2021 3rd International Conference on Signal Processing and Communication (ICPSC), 98-102. https://doi.org/10.1109/ICSPC51351.2021.9451720
Moheddine, A., 2022. PCOS_Dataset Kaggle. https://www.kaggle.com/datasets/ayamoheddine/pcos-dataset?select=PCOS_data.csv
Mubasher-Hassan, M. & Mirza, T. 2020. Comparative Analysis of Machine Learning Algorithms in Diagnosis of Polycystic Ovarian Syndrome. Int J Comput Appl, 175(17), 42-53. https://www.ijcaonline.org/archives/volume175/number17/31548-2020920688
Palomar, L. & Guerrero, J. 2017. El teorema de bayes y el diagnóstico clínico. Memorias del Congreso Internacional Sobre la Enseñanza y Aplicación de las Matemáticas, Universidad Nacional Autónoma de México, Facultad de Estudios Superiores Cuautitlán. https://bit.ly/3JBftTU
Prapty, A. S. & Shitu, T. T. 2020. An Efficient Decision Tree Establishment and Performance Analysis with Different Machine Learning Approaches on Polycystic Ovary Syndrome. En: 23rd International Conference on Computer and Information Technology (ICCIT), DHAKA, Bangladesh, 2020, pp. 1-5. https://doi.org/10.1109/ICCIT51783.2020.9392666
Uddin, S., Haque, I., Lu, H., Moni, M. A. & Gide, E. 2022. Comparative performance analysis of K-nearest neighbour (KNN) algorithm and its different variants for disease prediction. Sci Rep, 12(1): 6256. https://doi.org/10.1038/s41598-022-10358-x
Winnykamien, I., Dalibón, A. & Knoblovits, P. 2016. Síndrome de ovario poliquístico. Rev. Hosp. Ital. B. Aires 37(1): 10-20. https://pesquisa.bvsalud.org/portal/resource/pt/biblio-966680
