Gallstone disease is a prevalent medical condition and its diagnosis remains complex due to the influence of multiple clinical and demographic factors. This project aims to develop predictive machine learning models that can accurately classify the presence of gallstones based on a dataset of 319 patients containing various clinical predictors. A comprehensive range of modelling tech- niques was explored to compare the effectiveness of traditional, probabilistic, gradient-boosting and deep learning approaches in this classification task. These include TabTransformer, Denoising Autoencoder (DAE), XGBoost, Linear Discriminant Analysis (LDA) and Gaussian Process Classifier (GPC). Each model was trained and tested to assess predictive accuracy, robustness and overall classification performance. The primary goal of this study is to benchmark the relative strengths of these models for gallstone prediction and to identify potential directions for improving predictive performance in future work.