Gynecological Disease Diagnosis Expert System GDDES Based on Machine Learning Algorithm and Natural Language Processing

This project presents the development of the Gynaecological Disease Diagnosis Expert System (GDDES) leveraging machine learning algorithms and natural language processing (NLP) to accurately diagnose common gynaecological disorders, specifically Urinary Tract Infection (UTI) and Polycystic Ovary Syndrome (PCOS). The existing system employs classical machine learning techniques including Decision Tree, Random Forest Classifier, Support Vector Classifier (SVC), Naïve Bayes, and K-Nearest Neighbor for classification tasks. The proposed system enhances diagnostic accuracy and efficiency by integrating advanced algorithms such as Logistic Regression and Gradient Boosting Models. The system utilizes NLP to analyze patient records and symptoms, facilitating a robust, automated diagnostic process. This approach aims to improve diagnostic precision and reduce the time required for disease identification, providing a reliable tool for healthcare professionals.

Keywords: Gynaecological Disease Diagnosis, Machine Learning, Decision Tree, Logistic Regression, Gradient Boosting Models.