Computational intelligence for early detection of infertility in women

Abstract

Polycystic Ovary Syndrome (PCOS) is a major cause of female infertility. Early detection and treatment are critical in improving patients' prognoses. The current fertility conditions in India are sceptic, with women being more vulnerable. PCOS is one of the leading causes of infertility, affecting up to 20% of women in India. This necessitates an accurate and timely diagnosis, which can be accomplished by developing automated diagnosing models. Given that the data to be dealt with includes both clinical and non-clinical inputs, the effective information must be considered alone for the diagnosis. This necessitates a careful selection of features prior to diagnosing. The objective of this work is to identify prominent features in the dataset to develop a reliable yet simple diagnostic model to detect PCOS. To develop such a model, swarm intelligence (SI) is used for feature selection and machine learning (ML) is used for classification. Initially, optimal features are chosen using statistical methods such as correlation and Chi Square tests, as well as an exhaustive search procedure based on recursive elimination. Additionally, the SI algorithms, Particle Swarm Optimization (PSO), and Flashing Firefly (FF) algorithms are used to determine the optimal number and feasible combination of features. In the ML model, Random Forest (RF) and XGBoost classifiers were used for classification. The Synthetic Minority Oversampling Technique for Nominal and Continuous Features (SMOTENC) was employed to create a balanced dataset because the original dataset was unbalanced and all of the investigations were carried out for original and balanced datasets. Based on the metrics accuracy of training and testing, precision, recall, F1-score, AUC-ROC, and Matthew's Correlation Coefficient (MCC), a comparative analysis of the results is discussed and validated. The findings show that ML models with various feature selection algorithms perform best for various feature dimensions, with the model with RF classifier and features selected by PSO performed best with highest accuracy. A user interface module was developed with minimum features to diagnose PCOS. The performance of the model was also compared with the state of the art deep learning techniques.