A Novel Approach for Polycystic Ovary Syndrome Prediction Using Machine Learning in Bioinformatics

Abstract

Polycystic ovary syndrome (PCOS) is a critical disorder in women during their reproduction phase. The PCOS disorder is commonly caused by excess male hormone and androgen levels. The follicles are the collections of fluid developed by ovaries and may fail to release eggs regularly. The PCOS results in miscarriage, infertility issues, and complications during pregnancy. According to a recent report, PCOS is diagnosed in 31.3% of women from Asia. Studies show that 69% to 70% of women did not avail of a detecting cure for PCOS. A research study is needed to save women from critical complications by identifying PCOS early. The main aim of our research is to predict PCOS using advanced machine learning techniques. The dataset based on clinical and physical parameters of women is utilized for building study models. A novel feature selection approach is proposed based on the optimized chi-squared (CS-PCOS) mechanism. The ten hyper-parametrized machine learning models are applied in comparison. Using the novel CS-PCOS approach, the gaussian naive bayes (GNB) outperformed machine learning models and state-of-the-art studies. The GNB achieved 100% accuracy, precision, recall, and f1-scores with minimal time computations of 0.002 seconds. The k-fold cross-validation of GNB achieved a 100% accuracy score. The proposed GNB model achieved accurate results for critical PCOS prediction. Our study reveals that the dataset features prolactin (PRL), blood pressure systolic, blood pressure diastolic, thyroid stimulating hormone (TSH), relative risk (RR-breaths), and pregnancy are the prominent factors having high involvement in PCOS prediction. Our research study helps the medical community overcome the miscarriage rate and provide a cure to women through the early detection of PCOS.

Exploring the dominant features and data-driven detection of polycystic ovary syndrome through modified stacking ensemble machine learning technique

“…For example, to categorize between PCOS and non-PCOS criteria, Danaei et al [29] employed Extra Tree, Adaptive Boosting (AdaBoost), Bagging Ensemble with Random Forest and Multi-Layer Perceptron (MLP) classification models which were then evaluated through performance parameters using the reduced subgroups of features obtained by filter, embedded, and wrapper feature extraction techniques. For feature selection, Nasim et al [30] presented an improved chi-squared (CS-PCOS) mechanism and they then conducted a performance comparison analysis of ten hyper-parametrized machine learning models for PCOS prediction. Another work in this domain had been proposed by Agrawal et al [31] , where the top 30 features from the data were determined using the Chi-square technique, and the underlying state of PCOS was predicted using Random Forest, SVM, Logistic Regression, Gaussian Naive Bayes, and K Neighbors utilizing this reduced feature vector.…”

An Integrated Approach for Diabetes Detection Using Fisher Score Feature Selection and Capsule Network

“…Cluster analysis, K-means, the Apriori algorithm, etc., are some of the most popular ways to learn without being watched [15]- [17]. Some of deep learning algorithms were also applied for diabetes detection [18], [19]. Several challenges in healthcare, including the detection of diabetes, have been overcome via machine learning.…”

Heart Disease Prediction Using Outlier Removal based Max Voting Ensemble Method

“…Studies have demonstrated that identifying and addressing heart failure promptly can enhance life quality and extend survival rates. (Qadri, et al, 2023) It is difficult to predict cardiac disease since it calls for both extensive expertise and cutting-edge information. (Khan, 2020) The severity of the heart disease problem is categorized using a variety of techniques, including the K-Nearest Neighbor Algorithm (KNN), Naive Bayes (NB), Decision Tree (DT), Support Vector Machine (SVM), Random Forest (RF), and Genetic Algorithm (GA).…”