EUVIMEDEUVIMED entdecken
Crossref

Kidney stones composition prediction using artificial intelligence ( KiSCAI) study

Louise Duffaut iD, Pietro Scilipoti iD, Zine-Eddine Khene iD, Steeve Doizi iD, Vincent Frochot, Laurent Berthe, Federico Zorzi iD, Nicola Nannola, Carlos Gonzalez Gonzalez iD, Jean Philippe Haymann, Emmanuel Letavernier iD, Michel Daudon und 3 weitere

BJU International · 2026-12 · 138 (6) · 1065-1076

DOI: 10.1111/bju.70442 ↗

Kurz gefasst

Fachartikel in der Zeitschrift BJU International, online erschienen am 31.08.2026. Verfasst von Louise Duffaut und 14 weiteren Autor:innen. Beteiligte Einrichtung: Endolase Lab, GRC20-Sorbonne University, PIMM-Arts et Métiers Paris Tech, Paris, France. Hauptthemen laut MEDLINE: Kidney Calculi, Artificial Intelligence, Machine Learning. Die Arbeit nennt 29 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

To develop and validate explainable machine learning (ML) models predicting urinary stone composition from routinely available clinical variables and standardised morphological features, and to quantify the incremental value of morphology. Patients and Methods This retrospective cohort study included consecutive patients undergoing endourological treatment or spontaneous stone expulsion, with laboratory analysis showing a major component exceeding 50% of stone composition, between 2019 and 2024. The outcome was dominant stone composition, classified into five categories: calcium oxalate monohydrate (COM), calcium oxalate dihydrate (COD), calcium phosphate, uric acid, and cystine. Predictors included demographics, comorbidities, stone metrics, procedural details, and Daudon‐based morphological descriptors. Data were split into stratified training and validation cohorts (80% and 20%, respectively). Predictor stability was assessed using repeated‐resampling multiclass Least Absolute Shrinkage and Selection Operator (LASSO). Multiple supervised classifiers (logistic regression, support vector machine, random forest, ExtraTrees, Adaptive Boosting [AdaBoost] variants, Extreme Gradient Boosting [XGBoost], Categorical Boosting [CatBoost]) were fine‐tuned using GridSearch. Discrimination was assessed using macro‐averaged one‐vs‐rest area under the curve (AUC) and accuracy. Explainability relied on SHapley Additive exPlanations (SHAP).

Results

Among 442 patients (median age 51 years; 67% male), stone composition was COM in 41.0% ( n = 181), COD in 24.9% ( n = 110), calcium phosphate in 19.7% ( n = 87), uric acid in 10.9% ( n = 49), and cystine in 3.6% ( n = 16). LASSO stability highlighted reproducible predictors, including age, hereditary disease type, stone density, maximal diameter, and location. Clinical‐only models achieved good discrimination (macro‐AUC up to 0.809). Adding morphological features markedly improved performance, with ensemble models achieving excellent discrimination in validation (macro‐AUC up to 0.983 with CatBoost). Morphological variables ranked among the strongest contributors on SHAP.

Conclusions

A clinical‐only model can predict the major stone component and may support preoperative decision‐making. Performance further improved when morpho‐constitutional features were added, confirming Daudon's classification as the ground truth; however, this combined model relies on intra‐ and postoperative descriptors and is best regarded as an intra‐ or postoperative decision‐support tool rather than a preoperative one. External prospective validation is needed before clinical implementation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Kidney CalculiArtificial IntelligenceMachine LearningHumansRetrospective StudiesCalcium PhosphatesPredictive Learning ModelsCalcium OxalateFemaleMaleUric AcidCystineMiddle AgedBoosting Machine Learning AlgorithmsAdultPrediction AlgorithmsClassification Algorithms

Stichwörter der Autor:innen

SHAPartificial intelligencemachine learningprediction modelstone compositionurinary stonesurolithiasis

Substanzen

Calcium PhosphatesCalcium Oxalatecalcium phosphateUric AcidCystine

Autor:innen und Institutionen

  • Endolase Lab, GRC20-Sorbonne University, PIMM-Arts et Métiers Paris Tech, Paris, France.
  • Service d'Urologie, Tenon Hôpital, Paris, France.
  • Department of Experimental Oncology/Unit of Urology, URI, IRCCS Ospedale San Raffaele, Milan, Italy.
  • Vita-Salute San Raffaele University, Milan, Italy.
  • Department of Urology, University of Rennes, Rennes, France.
  • Laboratoire Traitement du Signal et de l'Image, INSERM U1099, Université de Rennes 1, Rennes, France.

ORCID-Profile: Louise Duffaut, Pietro Scilipoti, Zine-Eddine Khene, Steeve Doizi, Federico Zorzi, Carlos Gonzalez Gonzalez, Emmanuel Letavernier, Olivier Traxer, Frédéric Panthier

Zitieren

APA

Duffaut, L., Scilipoti, P., Khene, Z. E., Doizi, S., Frochot, V., Berthe, L., Zorzi, F., Nannola, N., Gonzalez, C. G., Haymann, J. P., Letavernier, E., Daudon, M., Traxer, O., Chicaud, M., & Panthier, F. (2026). Kidney stones composition prediction using artificial intelligence ( KiSCAI) study. BJU International, 138(6), 1065-1076. https://doi.org/10.1111/bju.70442

Vancouver

Duffaut L, Scilipoti P, Khene ZE, Doizi S, Frochot V, Berthe L, et al. Kidney stones composition prediction using artificial intelligence ( KiSCAI) study. BJU International. 2026;138(6):1065-1076. doi:10.1111/bju.70442

BibTeX
@article{Duffaut2026,
  author = {Duffaut, Louise and Scilipoti, Pietro and Khene, Zine-Eddine and Doizi, Steeve and Frochot, Vincent and Berthe, Laurent and Zorzi, Federico and Nannola, Nicola and Gonzalez, Carlos Gonzalez and Haymann, Jean Philippe and Letavernier, Emmanuel and Daudon, Michel and Traxer, Olivier and Chicaud, Marie and Panthier, Frédéric},
  title = {Kidney stones composition prediction using artificial intelligence ( KiSCAI) study},
  journal = {BJU International},
  year = {2026},
  volume = {138},
  number = {6},
  pages = {1065--1076},
  doi = {10.1111/bju.70442}
}
Kostenlos starten →