This study presented by Gelmis et al., aims to test the effectiveness of ML algorithms by using them to analyze quadruple-D scores (stone volume, density, skin-to-stone distance [SSD], and location) in predicting stone free rates after the use of Extracorporeal shock wave lithotripsy (ESWL). 309 patients underwent ESWL where the criteria was to be 18 or older while presenting with a stationary renal stone that is less than 20 mm. Exclusion criteria included presenting with multiple renal calculi, skeletal deformities, active UTI’s, and previous urinary tract surgeries in the last six months. Within the 309 patients, 37.9% had residual stones. Several factors between the non-residual stone group and the patients did not have significant differences, however the stone density, volume, and SSD were lower in the non-residual stone group. The quadruple-D score outperformed the preceding group after ESWL. At the optimal cut-off value of 1.5, quadruple-D achieved a high sensitivity of 84.9% but moderate specificity of 48.7% while the triple-D test had more specificity than sensitivity. The RF model achieved the highest accuracy of 82.9%, outperforming other conventional methods. After analysis, it is deemed that the quadruple-D scores are the most clinically and statistically relevant variable. This study highlights a future where clinical experience and expertise will work alongside computational intelligence to help make more advanced decisions in the field of Urology.