Genetic Clustering for Polycystic Ovary Syndrome Detection in Women of Reproductive Age
Anuradha D. Thakare1, Priyanka R. Lel2
1Anuradha D. Thakare*, Department of Computer Engineering, Pimpri Chinchwad College of Engineering, Pune, India.
2Priyanka R. Lele, Department of Computer Engineering, Pimpri Chinchwad College of Engineering, Pune, India.
Manuscript received on February 06, 2020. | Revised Manuscript received on February 10, 2020. | Manuscript published on February 30, 2020. | PP: 1356-1361 | Volume-9 Issue-3, February, 2020. | Retrieval Number: C5457029320/2020©BEIESP | DOI: 10.35940/ijeat.C5457.029320
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Now a days, hormonal disorder causing Polycystic Ovary Syndrome (PCOS) is been observed in most of the women of reproductive age. PCOS causes enlarged ovaries with small cysts on the outer edges. Women with PCOS may have irregularity in menstrual periods or excess male hormone (androgen) levels. The ovaries may develop numerous small collections of follicles (cysts) and fail to regularly release eggs. Symptoms of PCOS include irregular periods, excess androgen, polycystic ovaries, abnormal Body Mass Index, disturbed levels of hormones (Luteinizing Hormone, Follicle-stimulating Hormone, Dehydroepiandrosterone), poor insulin resistance. There is a need to design and develop an optimized system to analyze the sonogram in correlation with the physical symptoms for detection of PCOS at early stage which may result in proper treatment and reduced health loss. This article presents work-in-progress of our proposed research on Intelligent System to detect PCOS. The performance analysis of various Machine learning algorithms like Artificial Neural Network, K- nearest Neighbor and Linear Regression to detect PCOS is presented. Whereas, optimized Genetic Clustering for optimization of classification results is proposed. Basic Genetic Algorithm (GA) and other hybrid GA’s will be used for comparing the optimal results. The classification results are optimized with 89% accuracy.
Keywords: Classification, Genetic Clustering, Machine Learning, Polycystic Ovary Syndrome, statistical measures, Sonography.