Endometriosis is a chronic gynecological condition often undiagnosed due to its varied clinical presentations and lack of reliable non-invasive biomarkers. A comparative analysis is performed using machine learning models (MLm) to classify endometriosis using clinical, biomolecular indicators, and hereditary background attributes. Logistic Regression (LR), Support Vector Machines (SVM), Random Forests (RF), Naive Bayes (NB), Dense Neural Networks (DNN), and XGBoost were compared. Performance is assessed using accuracy, precision, recall, F1-score, and AUROC metrics. Ensemble approaches like Random Forest and XGBoost performed better in terms of accuracy and stability as compared to traditional linear machine learning models. Explainability is achieved using LIME by considering the parameters like pelvic pain, irregular periods, and hereditary attributes. Combining machine learning and explainable AI tools helps in better understanding of the findings and managing such chronic diseases.