PCOS Diagnosis With Commonly Known Diseases Using Hybrid Machine Learning Algorithms

The Polycystic ovarian syndrome (PCOS) is the most widespread health concern currently affecting women in the world. The defining characteristics of PCOS are cysts in the ovaries and a hormonal imbalance. One in every five women in India is affected by PCOS because of the lack of awareness in women. The late identification of PCOS can also lead to high risk diseases including hypertension, diabetes, cardiovascular disease and obesity etc. Thus, the main objective of the paper is to examine how some features like heart diseases, obesity, diabetes, and high blood pressure can be used for diagnosing PCOS through hybrid and classification algorithms. In order to determine the best performing algorithm in this scenario, the comparison is made among the six simple classification algorithms based on the performance metrics. The algorithm which gives the highest accuracy is further used in conjunction to create hybrid algorithms. The performance metrics and time taken is compared among all simple classification and hybrid algorithms. The most efficient algorithm is then can be further used for PCOS diagnosis which in turn saves time and cost.