PCOS DETECTION AND PREDICTION USING CNN MACHINE LEARNING ALGORITHMS
Abstract : Polycystic Ovary Syndrome (PCOS) is a medical condition which causes hormonal disorder in women in their childbearing years. The hormonal imbalance leads to a delayed or even absent menstrual cycle. Women with PCOS majorly suffer from excessive weight gain, facial hair growth, acne, hair loss, skin darkening and irregular periods leading to infertility in rare cases. The existing methodologies and treatments are insufficient for early-stage detection and prediction. To deal with this problem, we propose a system which can help in early detection and prediction of PCOS treatment from an optimal and minimal set of parameters. To detect whether a woman is suffering from PCOS, 5 different machine learning classifiers like Random Forest, SVM, Logistic Regression, Gaussian Naïve Bayes, K Neighbours have been used. Out of the 41 features from the dataset, top 30 features were identified using CHI SQUARE method and used in the feature vector. We also compared the results of each classifier and it has been observed that the accuracy of the Random Forest Classifier is the highest and the most reliable. The dataset used for training and testing is available on KAGGLE and owned by Prasoon Kottarathil.
• The existing data regarding the familiarity, characteristics, and treatment of the metabolic syndrome in women with PCOS.
• It follows Gaussian Normal Distribution which means there will not be covariance between the features, and it supports continuous data.
• KNeighbours Classifier: The KNN algorithm assumes that similar data if plotted would exist nearby.
• The existing methodologies and treatments are insufficient for early-stage detection and prediction.
• To deal with this problem, we propose a system which can help in early detection and prediction of PCOS treatment from an optimal and minimal set of parameters.
• Adolescents with PCOS experience several problems influencing their psychological health that probably lead to psychological distress and impaired emotional well-being.
• Infertility is considered as the devastating issue for the women of reproductive age group and it may be due to numerous reasons.
• These problems are often caused by atherosclerosis and occur when fat and cholesterol are built up in blood vessel (artery) walls.
• Many methods have been proposed to impute missing data, however, they do not fulfill the need for data quality especially in real datasets with different missing data patterns.
• A new generation of imputation methods are proposed that utilized the advantages of SI and MI methods using the hybridization schema.
• Several studies have been proposed to detect CVD using data miningtools such as decision trees, Support Vector Machines, Bayesian theory,and neural network.
• The strength of the proposed automated system involves the inclusion of PCOS and mental health questionnaires which have been validated by expert gynecologists and psychiatrists.
• A relationship between irregular cycles and impaired psychological performance in women suffering from PCOS.
• Obesity is an independent factor which exacerbates infertility in PCOS, reduces the efficacy of infertility treatment and provokes a greater risk of miscarriage.
• They may be used as a type of birth control and to treat symptoms of menopause, menstrual disorders, osteoporosis, and other conditions.
|