Predicting Extracorporeal Shock Wave Lithotripsy Outcomes Using Machine Learning and the Triple-/Quadruple-D Scores

Mucahit Gelmis; Sina Kardas; Ali Ayten; Oguzhan Cura; Serkan Gonultas; Mustafa Gokhan Kose

doi:10.29271/jcpsp.2025.08.1007

Author(s)

Mucahit Gelmis Department of Urology, Gaziosmanpasa Training and Research Hospital,Istanbul,Turkiye

Sina Kardas Department of Urology, Gaziosmanpasa Training and Research Hospital,Istanbul,Turkiye

Ali Ayten Department of Urology, Gaziosmanpasa Training and Research Hospital,Istanbul,Turkiye

Oguzhan Cura Department of Urology, Gaziosmanpasa Training and Research Hospital,Istanbul,Turkiye

Serkan Gonultas Department of Urology, Gaziosmanpasa Training and Research Hospital,Istanbul,Turkiye

Mustafa Gokhan Kose Department of Urology, Gaziosmanpasa Training and Research Hospital,Istanbul,Turkiye

Abstract

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 in uencing 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-stonefree 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). Signi cant predictors of ESWL success were stone density, volume, SSD, and the quadruple-D score, while age and body mass index (BMI) were not signi cant. Conclusion: Integrating the quadruple-D score with ML models, particularly RF, enhances the prediction of ESWL outcomes. Combining clinical expertise with computational intelligence can re ne patient selection and optimise treatment strategies. However, prospective studies are needed to validate these ndings.

Publication Details

Page(s) 1007-1013

DOI 10.29271/jcpsp.2025.08.1007

Published Journal: Journal of the College of Physicians and Surgeons Pakistan, Volume: 35, Issue: 8, Year: 2025

Request the full text from PASTIC

Keywords

Random Forest, Machine learning, Extracorporeal shock wave lithotripsy, Quadruple-D score, Stone-free prediction

References

Shinde S,Al Balushi Y,Hossny M,Jose S,Factors S. .2018 .a ecting the outcome of extracorporeal shockwave lithotripsy in urinary stone treatment. Oman Med J, 39(3) : 209-17.

Schmidt S,Miernik A .2015 .Extracorporeal shock wave lithotripsy versus percutaneous nephrolithotomy or retrograde intrarenal surgery for kidney stones. Urologe A, 10(9) : 1283-6.

Tran TY,McGillen K,Cone EB,Pareek G .2014 .Triple D score is a reportable predictor of shockwave lithotripsy stone-free rates. J Endourol, 0212(2) : 226-30.

Ichiyanagi O,Fukuhara H,Kurokawa M,Izumi T,Suzuki H,Naito S .2019 .Reinforcement of the Triple D score with simple addition of the intrarenal location for the prediction of the stone-free rate after shockwave lithotripsy for renal stones 10 20 mm in diameter. Int Urol Nephrol, 10(2) : 239-45.

Yang SW,Hyon YK,Na HS,Jin L,Lee JG,Park JM .2020 .Machine learning prediction of stone-free success in patients with urinary stone after treatment of shock wave lithotripsy. BMC Urol, 10(1) : 020.

Shamout F,Zhu T,Clifton DA .2020 .Machine learning for clinical outcome prediction. IEEE Rev Biomed Eng, 3007816 : 116-26.

Salem H,Soria D,Lund JN,Awwad A. .2021 .A systematic review of the applications of expert systems and machine learning in clinical urology. BMC Med Inform Decis Mak, 10(1) : 223.

Shah M,Naik N,Somani BK,Hameed BMZ .2020 .Arti cial intelligence in urology current use and future directions: An iTRUE study. Turk J Urol, 20117(Suppl 1) : S27-39.

Rice P,Pugh M,Geraghty R,Hameed BZ,Shah M,Somani BK .2021 .Machine learning models for predicting stone-free status after shockwave lithotripsy: A systematic review and meta-analysis. Urology, 04 : 16-22.

Susanto AP,Lyell D,Widyantoro B,Berkovsky S,Magrabi F S .2023 .E ects of machine learning-based clinical decision support systems on decision-making, care delivery, and patient outcomes: A scoping review. J Am Med Inform Assoc, 10(12) : 2050-63.

Pareek G,Hedican SP,Lee FT .2005 .Shock wave lithotripsy success determined by skin-to-stone distance on computed tomography. Urology, 05(5) : 941-4.

Ghoneim IA,Ziada AM,Elkatib SE . .Predictive factors of lower calyceal stone clearance after extracorporeal shockwave lithotripsy: A focus on the infundibulopelvic. , : .

Sengupta S,Basu S,Ghosh K. .2022 .A prospective observational study on the predictability of Triple-D scoreversus Quadruple-D score in the success rate of extracorporeal shock wave lithotripsy of renal stones 1 2 cm in diameter. Urol Ann, 1(1) : 21-42.

Ozgor F,Tosun M,Kayali Y,Savun M,Binbay M,Tepeler A .2016 .External validation and evaluation of reliability and validity of the Triple D score to predict stone-free status after extracorporeal shockwave lithotripsy. J Endourol, 0721(2) : 169-73.

Turk C,Petrik A,Sarica K,Seitz C,Skolarikos A,Straub M .2015 .EAU guidelines on interventional treatment for urolithiasis. Eur Urol, 07(3) : 475-82.

Eksi M,Fakir AE,Evren I,Sam E,Arikan Y,Kargi T .2023 .Prediction of infective complications after retrograde intra renal surgery using machine learning. Minim Invasive Ther Allied Technol, 2186181(2) : 73-80.

Park JS,Kim DW,Lee D,Lee T,Koo KC,Han WK .2021 .Development of prediction models of spontaneous ureteral stone passage through machine learning: Comparison with conventional statistical analysis. PLoS One, 0260517(12) : .

Zhang D,Yin C,Zeng J,Yuan X .2020 .Combining structured and unstructured data for predictive models: A deep learning approach. BMC Med Inform Decis Mak, 10(1) : 280.

Topol EJ .2019 .High-performance medicine: The convergence of human and arti cial intelligence. Nat Med, 10(1) : 44-56.

Ribeiro MT,Singh S,Guestrin C .2016 .Why should I trust you? Explaining the predictions of any classi 2e2rn. d ACM SIGKDD Int Conf, 10 : 1135-44.