The approach to treating kidney stones hinges on their dimensions, composition, and placement. Smaller stones frequently navigate the urinary tract aided by heightened fluid intake and pain relief medication. Conversely, larger stones might necessitate medical procedures like lithotripsy, surgery, or alternative interventions for their elimination. The overarching process known as machine learning holds a diverse historical background, evolving through various definitions with technological progress. This paper considers kidney stone-related datasets like gravity, ph, osmo, cond, urea, calc, and target. The machine learning approaches are used to analyze and predict the dataset using linear regression, multilayer perceptron, SMOreg, M5P, random forest, and REP tree. Numerical illustrations are provided to prove the proposed results with accuracy parameters.