Gelmis M. et al., 2025: Predicting Extracorporeal Shock Wave Lithotripsy Outcomes Using Machine Learning and the Triple-/Quadruple-D Scores.
Mucahit Gelmis 1, Sina Kardas 1, Ali Ayten 1, Oguzhan Cura 1, Serkan Gonultas 1, Mustafa Gokhan Kose 1
1Department of Urology, Gaziosmanpasa Training and Research Hospital, Istanbul, Turkiye.
Abstract
Objective: To evaluate the predictive performance of the triple-D and quadruple-D scores integrated with machine learning (ML) models in determining stone-free outcomes after extracorporeal shock wave lithotripsy (ESWL), and to compare ML model performance and identify its key predictors influencing ESWL success.
Study design: An observational study. Place and Duration of the Study: Department of Urology, Gaziosmanpasa Training and Research Hospital, Istanbul, Turkiye, from October 2020 to November 2024.
Methodology: A total of 309 patients who underwent ESWL were analysed. The patients were categorised into stone-free and non-stone- free groups based on post-treatment imaging. Clinical parameters, including quadruple-D score (stone volume, density, skin-to-stone distance [SSD], and location), were recorded. Three ML models‒random forest (RF), logistic regression (LR), and neural network (NN)‒were trained on 80% of the dataset and tested on 20%. Model performance was assessed using accuracy, area under the curve (AUC), precision, recall, and F1 score.
Results: The quadruple-D score (AUC: 0.724) demonstrated superior predictive power compared to the Triple-D score (AUC: 0.700). Among ML models, RF achieved the highest accuracy (82.9%, AUC: 0.91), followed by NN (80.9%, AUC: 0.87) and LR (79.6%, AUC: 0.85). Significant predictors of ESWL success were stone density, volume, SSD, and the quadruple-D score, while age and body mass index (BMI) were not significant.
Conclusion: Integrating the quadruple-D score with ML models, particularly RF, enhances the prediction of ESWL outcomes. Combining clinical expertise with computational intelligence can refine patient selection and optimise treatment strategies. However, prospective studies are needed to validate these findings.
J Coll Physicians Surg Pak. 2025 Aug;35(8):1007-1013. doi: 10.29271/jcpsp.2025.08.1007.
PMID: 40843568
Comments 1
The authors used machine learning to compare Triple-D score and Quadruple-D score as predictors of SWL-success. As in many other studies successful SWL was considered when the kidney was completely stone free or had minor residuals variable in Quadruple-D score is explained by difficulties to clear the lower calyces, particularly in cases referred to as “unfavorable anatomy”. For the latter factor the infundibulo-pelvic angle, the length and width of the lower calyx are of outstanding importance.
The machine learning calculations presented in the article are in my opinion only an application of a modern computer technique to predict what equally effective might have been obtained by manual calculations.
The authors finally concluded that this machine learning model must be further applied in “multicenter studies”. Although such an approach certainly will add further strength to the calculation, it seems much more interesting to use computer analysis of the kidney and stone images to derive data on the geometry of the stone containing lower calyx. That would refine the information of the location variable in Quadruple-D score. In that way it would be possible to improve the analysis by applying modern technology and machine learning to get data that not easily can be obtained by only briefly looking at the images.
Hans-Göran Tiselius