Polycystic Ovary syndrome is a disorder that many women faces during their reproductive age, due to this they suffer from diabetes, infertility and high blood pressure. Diagnosis of this disorder is mainly done through various types of screenings like ultrasound images. Imaging is the most important factor in the diagnosis, through ultrasound images the follicles generated and cysts formed are easily affected. Although, this is the best method for diagnosis, the main concern is the symptoms shown by this disorder are many times ignored because symptoms like acne, hair loss, and weight gain can also be the causes of some other problem and this leads to the PCOS getting more severe. This paper can be said as a prevention measure or as an alert that one needs to visit hospital for screening. It will help female to recognize the symptoms at early age so that they can take required steps toward the cure. The proposed work is based on the images obtained after ultrasound and how the noises that occur in them can be removed by various methods like data mining, machine learning algorithms. This paper will provide the overview of predicting the disorder using symptoms as parameters through genetic algorithm and back propagation algorithm in neural network. Since, genetic algorithm and back propagation algorithm is known for their accuracy can produce better results
Predicting & Identifying Risk of Polycystic Ovary Syndrome (Pcos)
