Too good to be true? AI performance in CT-based urinary stone detection and classification: EAU endourology systematic review and diagnostic accuracy meta-analysis.
Authors
Affiliations (16)
Affiliations (16)
- Department of Urology and Andrology, Genome Clinic, Astana, Kazakhstan. [email protected].
- European Association of Urology (EAU) Endourology section, Arnhem, The Netherlands. [email protected].
- Department of Urology, Sismanogleio Hospital, National and Kapodistrian University of Athens, Athens, Greece.
- European Association of Urology (EAU) Endourology section, Arnhem, The Netherlands.
- Ng Teng Fong General Hospital, Singapore, Singapore.
- Asian Institute of Nephro-Urology, Hyderabad, India.
- Department of Urology, IRCCS San Gerardo dei Tintori, Monza, Italy.
- Department of Urology, Saint-Petersburg State University Hospital, Saint Petersburg, Russia.
- Department of Urology, Russian University of Medicine, Botkin Hospital, Moscow, Russia.
- Department of Medicine and Surgery, Libera Università Mediterranea (LUM) University "Giuseppe Degennaro", Casamassima, Italy.
- Urology Unit, "F. Miulli" General Regional Hospital, Acquaviva delle Fonti, Casamassima, Italy.
- Department of Urology, Medical Faculty, Necmettin Erbakan University, Konya, Turkey.
- Department of Urology, University Medical Center Mannheim, Heidelberg University, Heidelberg, Germany.
- Department of Urology, Klinikum Sindelfingen-Boeblingen, University of Tuebingen, Tuebingen, Germany.
- Department of Urology, Faculty of Medicine, Istanbul University, Istanbul, Turkey.
- Department of Urology, University Hospital Southampton NHS Foundation Trust, Southampton, UK.
Abstract
To evaluate pooled performance of artificial intelligence (AI) in computed tomography (CT)-based urinary stone detection and classification and identify methodological factors influencing results. This review was registered in PROSPERO (CRD420261319940). A systematic search of PubMed, Cochrane Library, and Google Scholar was conducted up to March 15, 2026. Studies evaluating AI-based detection or classification of urolithiasis on CT with available validation/test cohort data (sensitivity/specificity or 2 × 2 tables) were included. A bivariate random-effects model generated pooled sensitivity, specificity, and hierarchical summary receiver operating characteristic (HSROC) curves. Meta-regression explored moderators related to dataset composition and AI pipelines. Risk of bias was assessed using QUADAS-AI. 14 studies (five detection-based, nine classification-based) were included. Overall pooled sensitivity and specificity were 0.967 and 0.979 (AUC 0.987). Classification studies demonstrated higher pooled sensitivity (0.977) and specificity (0.990) compared with detection studies (0.935 and 0.919; AUC 0.945). Significant heterogeneity was observed and influenced by training sample size, class imbalance, presence of bladder stones or other pathologies, and architectural choices. Most studies had high risk of bias, lacked external validation, and frequently used slice-level or pre-selected datasets, potentially overestimating performance. Substantial methodological heterogeneity and high risk of bias limit clinical generalizability. Detection studies better reflect real-world workflows and show lower performance. Current evidence does not support routine clinical implementation without standardized reporting and robust external validation.