{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T09:21:56Z","timestamp":1788168116327,"version":"build-2803163510"},"reference-count":29,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T00:00:00Z","timestamp":1788134400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T00:00:00Z","timestamp":1788134400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["bjui-journals.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["BJU International"],"abstract":"<jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Patients and Methods<\/jats:title>\n                    <jats:p>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\u2010based morphological descriptors. Data were split into stratified training and validation cohorts (80% and 20%, respectively). Predictor stability was assessed using repeated\u2010resampling 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\u2010tuned using GridSearch. Discrimination was assessed using macro\u2010averaged one\u2010vs\u2010rest area under the curve (AUC) and accuracy. Explainability relied on SHapley Additive exPlanations (SHAP).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Among 442 patients (median age 51\u2009years; 67% male), stone composition was COM in 41.0% (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009181), COD in 24.9% (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009110), calcium phosphate in 19.7% (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u200987), uric acid in 10.9% (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u200949), and cystine in 3.6% (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u200916). LASSO stability highlighted reproducible predictors, including age, hereditary disease type, stone density, maximal diameter, and location. Clinical\u2010only models achieved good discrimination (macro\u2010AUC up to 0.809). Adding morphological features markedly improved performance, with ensemble models achieving excellent discrimination in validation (macro\u2010AUC up to 0.983 with CatBoost). Morphological variables ranked among the strongest contributors on SHAP.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>A clinical\u2010only model can predict the major stone component and may support preoperative decision\u2010making. Performance further improved when morpho\u2010constitutional features were added, confirming Daudon's classification as the ground truth; however, this combined model relies on intra\u2010 and postoperative descriptors and is best regarded as an intra\u2010 or postoperative decision\u2010support tool rather than a preoperative one. External prospective validation is needed before clinical implementation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1111\/bju.70442","type":"journal-article","created":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T08:58:45Z","timestamp":1788166725000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Kidney stones composition prediction using artificial intelligence (\n                    <scp>KiSCAI)<\/scp>\n                    study"],"prefix":"10.1111","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-1213-8057","authenticated-orcid":false,"given":"Louise","family":"Duffaut","sequence":"first","affiliation":[{"name":"Endolase Lab GRC20\u2010Sorbonne University, PIMM\u2010Arts et M\u00e9tiers Paris Tech  Paris France"},{"name":"Service d'Urologie Tenon H\u00f4pital  Paris France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6126-9889","authenticated-orcid":false,"given":"Pietro","family":"Scilipoti","sequence":"additional","affiliation":[{"name":"Endolase Lab GRC20\u2010Sorbonne University, PIMM\u2010Arts et M\u00e9tiers Paris Tech  Paris France"},{"name":"Service d'Urologie Tenon H\u00f4pital  Paris France"},{"name":"Department of Experimental Oncology\/Unit of Urology, URI IRCCS Ospedale San Raffaele  Milan Italy"},{"name":"Vita\u2010Salute San Raffaele University  Milan Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4124-789X","authenticated-orcid":false,"given":"Zine\u2010Eddine","family":"Khene","sequence":"additional","affiliation":[{"name":"Department of Urology University of Rennes  Rennes France"},{"name":"Laboratoire Traitement du Signal et de l'Image, INSERM U1099 Universit\u00e9 de Rennes 1  Rennes France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7700-5622","authenticated-orcid":false,"given":"Steeve","family":"Doizi","sequence":"additional","affiliation":[{"name":"Endolase Lab GRC20\u2010Sorbonne University, PIMM\u2010Arts et M\u00e9tiers Paris Tech  Paris France"},{"name":"Service d'Urologie Tenon H\u00f4pital  Paris France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vincent","family":"Frochot","sequence":"additional","affiliation":[{"name":"Laboratoire des Lithiases, Service des Explorations Fonctionnelles H\u00f4pital Tenon, APHP  Paris France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laurent","family":"Berthe","sequence":"additional","affiliation":[{"name":"Endolase Lab GRC20\u2010Sorbonne University, PIMM\u2010Arts et M\u00e9tiers Paris Tech  Paris France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5593-5995","authenticated-orcid":false,"given":"Federico","family":"Zorzi","sequence":"additional","affiliation":[{"name":"Endolase Lab GRC20\u2010Sorbonne University, PIMM\u2010Arts et M\u00e9tiers Paris Tech  Paris France"},{"name":"Service d'Urologie Tenon H\u00f4pital  Paris France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicola","family":"Nannola","sequence":"additional","affiliation":[{"name":"Endolase Lab GRC20\u2010Sorbonne University, PIMM\u2010Arts et M\u00e9tiers Paris Tech  Paris France"},{"name":"Service d'Urologie Tenon H\u00f4pital  Paris France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1744-8913","authenticated-orcid":false,"given":"Carlos Gonzalez","family":"Gonzalez","sequence":"additional","affiliation":[{"name":"Endolase Lab GRC20\u2010Sorbonne University, PIMM\u2010Arts et M\u00e9tiers Paris Tech  Paris France"},{"name":"Service d'Urologie Tenon H\u00f4pital  Paris France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jean Philippe","family":"Haymann","sequence":"additional","affiliation":[{"name":"Service d'Explorations Fonctionnelles Multidisciplinaires H\u00f4pital Tenon, Assistance Publique H\u00f4pitaux de Paris  Paris France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6053-8975","authenticated-orcid":false,"given":"Emmanuel","family":"Letavernier","sequence":"additional","affiliation":[{"name":"Unit\u00e9 Mixte de Recherche (UMR) S 1155 Institut National de la Sant\u00e9 et de la Recherche M\u00e9dicale (INSERM), Sorbonne Universit\u00e9  Paris France"},{"name":"Physiology Unit H\u00f4pital Tenon  Paris France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michel","family":"Daudon","sequence":"additional","affiliation":[{"name":"Laboratoire des Lithiases, Service des Explorations Fonctionnelles H\u00f4pital Tenon, APHP  Paris France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2459-3803","authenticated-orcid":false,"given":"Olivier","family":"Traxer","sequence":"additional","affiliation":[{"name":"Endolase Lab GRC20\u2010Sorbonne University, PIMM\u2010Arts et M\u00e9tiers Paris Tech  Paris France"},{"name":"Service d'Urologie Tenon H\u00f4pital  Paris France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marie","family":"Chicaud","sequence":"additional","affiliation":[{"name":"Endolase Lab GRC20\u2010Sorbonne University, PIMM\u2010Arts et M\u00e9tiers Paris Tech  Paris France"},{"name":"Service d'Urologie Tenon H\u00f4pital  Paris France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3055-2984","authenticated-orcid":false,"given":"Fr\u00e9d\u00e9ric","family":"Panthier","sequence":"additional","affiliation":[{"name":"Endolase Lab GRC20\u2010Sorbonne University, PIMM\u2010Arts et M\u00e9tiers Paris Tech  Paris France"},{"name":"Service d'Urologie Tenon H\u00f4pital  Paris France"},{"name":"PIMM, UMR 8006 CNRS\u2010Arts et M\u00e9tiers ParisTech  Paris France"},{"name":"Progressive Endourological Association for Research and Leading Solutions (PEARLS)  Paris France"},{"name":"Endourology Technology Section of European Association of Urology (EAU)  Arnhem The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,8,31]]},"reference":[{"key":"e_1_2_13_2_1","doi-asserted-by":"crossref","first-page":"709","DOI":"10.1016\/S0302-2838(03)00415-9","article-title":"Study on the prevalence and incidence of urolithiasis in Germany comparing the years 1979 vs. 2000","volume":"44","author":"Hesse A","year":"2003","journal-title":"Eur Urol"},{"key":"e_1_2_13_3_1","doi-asserted-by":"crossref","DOI":"10.1016\/j.eclinm.2024.102924","article-title":"The global, regional, and national burden of urolithiasis in 204 countries and territories, 2000\u20132021: a systematic analysis for the global burden of disease study 2021","volume":"78","author":"GBD 2021 Urolithiasis Collaborators","year":"2024","journal-title":"EClinicalMedicine"},{"key":"e_1_2_13_4_1","doi-asserted-by":"crossref","first-page":"1301","DOI":"10.1007\/s00345-017-2008-6","article-title":"Epidemiology of stone disease across the world","volume":"35","author":"Sorokin I","year":"2017","journal-title":"World J Urol"},{"key":"e_1_2_13_5_1","doi-asserted-by":"crossref","first-page":"802","DOI":"10.1016\/j.purol.2008.09.029","article-title":"\u00c9pid\u00e9miologie des lithiases urinaires","volume":"18","author":"Daudon M","year":"2008","journal-title":"Prog Urol"},{"key":"e_1_2_13_6_1","first-page":"815","article-title":"Lithogenesis","volume":"18","author":"Daudon M","year":"2008","journal-title":"Prog Urol"},{"key":"e_1_2_13_7_1","doi-asserted-by":"crossref","first-page":"459","DOI":"10.1007\/s00240-018-1043-0","article-title":"Recurrence rates of urinary calculi according to stone composition and morphology","volume":"46","author":"Daudon M","year":"2018","journal-title":"Urolithiasis"},{"key":"e_1_2_13_8_1","doi-asserted-by":"crossref","first-page":"1797","DOI":"10.1016\/S0140-6736(98)01295-1","article-title":"Kidney stones","volume":"351","author":"Pak CYC","year":"1998","journal-title":"Lancet"},{"key":"e_1_2_13_9_1","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1007\/s00345-014-1444-9","article-title":"Kidney stone analysis: \u201cgive me your stone, I will tell you who you are!\u201d","volume":"33","author":"Cloutier J","year":"2015","journal-title":"World J Urol"},{"key":"e_1_2_13_10_1","first-page":"1081","article-title":"Urinary calculi: review of classification methods and correlations with etiology","volume":"7","author":"Daudon M","year":"1993","journal-title":"Scanning Microsc"},{"key":"e_1_2_13_11_1","doi-asserted-by":"crossref","first-page":"1470","DOI":"10.1016\/j.crci.2016.05.008","article-title":"Comprehensive morpho\u2010constitutional analysis of urinary stones improves etiological diagnosis and therapeutic strategy of nephrolithiasis","volume":"19","author":"Daudon M","year":"2016","journal-title":"C R Chim"},{"key":"e_1_2_13_12_1","doi-asserted-by":"crossref","first-page":"32","DOI":"10.4111\/icu.2018.59.1.32","article-title":"Fourier transform infrared spectroscopy for analysis of kidney stones","volume":"59","author":"Khan AH","year":"2018","journal-title":"Investig Clin Urol"},{"key":"e_1_2_13_13_1","doi-asserted-by":"crossref","DOI":"10.1155\/2014\/176165","article-title":"FT\u2010IR analysis of urinary stones: a helpful tool for clinician comparison with the chemical spot test","volume":"2014","author":"Primiano A","year":"2014","journal-title":"Dis Markers"},{"key":"e_1_2_13_14_1","doi-asserted-by":"crossref","DOI":"10.3390\/jcm10132888","article-title":"Endoscopic papillary abnormalities and stone recognition (EPSR) during flexible ureteroscopy: a comprehensive review","volume":"10","author":"Almeras C","year":"2021","journal-title":"J Clin Med"},{"key":"e_1_2_13_15_1","first-page":"1389","article-title":"Management of adult's renal and ureteral stones. Update of the lithiasis Committee of the French Association of urology (CLAFU). General considerations","volume":"23","author":"Chabannes \u00c9","year":"2013","journal-title":"Prog Urol"},{"key":"e_1_2_13_16_1","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/j.eururo.2025.03.011","article-title":"European Association of Urology guidelines on the diagnosis and treatment of urolithiasis","volume":"88","author":"Skolarikos A","year":"2025","journal-title":"Eur Urol"},{"key":"e_1_2_13_17_1","doi-asserted-by":"crossref","DOI":"10.1016\/j.sipas.2025.100322","article-title":"The role of artificial intelligence in advancing urologic care: from diagnostics to therapeutics","volume":"24","author":"Samenezhad S","year":"2025","journal-title":"Surg Pract Sci"},{"key":"e_1_2_13_18_1","doi-asserted-by":"crossref","first-page":"786","DOI":"10.1111\/bju.15767","article-title":"Evaluation and understanding of automated urinary stone recognition methods","volume":"130","author":"El Beze J","year":"2022","journal-title":"BJU Int"},{"key":"e_1_2_13_19_1","article-title":"Construction and validation of a urinary stone composition prediction model based on machine learning","volume":"53","author":"Guo J","year":"2025","journal-title":"Urolithiasis (New York, NY)"},{"key":"e_1_2_13_20_1","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1186\/s12894-023-01396-2","article-title":"Predicting stone composition via machine\u2010learning models trained on intra\u2010operative endoscopic digital images","volume":"24","author":"Zhu G","year":"2024","journal-title":"BMC Urol"},{"key":"e_1_2_13_21_1","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1038\/nmeth.4642","article-title":"Statistics versus machine learning","volume":"15","author":"Bzdok D","year":"2018","journal-title":"Nat Methods"},{"key":"e_1_2_13_22_1","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1159\/000049776","article-title":"Methods for measuring crystallization in urolithiasis research: why, how and when?","volume":"40","author":"Hess B","year":"2001","journal-title":"Eur Urol"},{"key":"e_1_2_13_23_1","doi-asserted-by":"crossref","DOI":"10.1016\/j.cmpb.2021.106584","article-title":"Explanation of machine learning models using shapley additive explanation and application for real data in hospital","volume":"214","author":"Nohara Y","year":"2022","journal-title":"Comput Methods Prog Biomed"},{"key":"e_1_2_13_24_1","doi-asserted-by":"crossref","first-page":"791","DOI":"10.1016\/j.purol.2023.08.018","article-title":"2022 recommendations of the AFU lithiasis committee: management of symptomatic urinary stones","volume":"33","author":"Meria P","year":"2023","journal-title":"Prog Urol"},{"key":"e_1_2_13_25_1","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.euf.2020.11.004","article-title":"Classification of stones according to Michel Daudon: a narrative review","volume":"7","author":"Corrales M","year":"2021","journal-title":"Eur Urol Focus"},{"key":"e_1_2_13_26_1","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1111\/bju.15312","article-title":"Toward improved endoscopic examination of urinary stones: a concordance study between endoscopic digital pictures vs microscopy","volume":"128","author":"Estrade V","year":"2021","journal-title":"BJU Int"},{"key":"e_1_2_13_27_1","doi-asserted-by":"crossref","first-page":"1468","DOI":"10.1089\/end.2022.0244","article-title":"Thulium fiber Laser's dust for stone composition analysis: is it enough? A pilot study","volume":"36","author":"Sierra A","year":"2022","journal-title":"J Endourol"},{"key":"e_1_2_13_28_1","doi-asserted-by":"crossref","first-page":"441","DOI":"10.4111\/icu.20220062","article-title":"Prediction of the composition of urinary stones using deep learning","volume":"63","author":"Kim US","year":"2022","journal-title":"Investig Clin Urol"},{"key":"e_1_2_13_29_1","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1111\/bju.15718","article-title":"Fabrication and application of a wireless high\u2010definition endoscopic system in urological surgeries","volume":"131","author":"Niu D","year":"2023","journal-title":"BJU Int"},{"key":"e_1_2_13_30_1","doi-asserted-by":"crossref","first-page":"13038","DOI":"10.1038\/s41598-026-43507-7","article-title":"Transparent AI for mathematics: transformer\u2010based large language models for mathematical entity relationship extraction with XAI","volume":"16","author":"Aurpa TT","year":"2026","journal-title":"Sci Rep"}],"container-title":["BJU International"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/bjui-journals.onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/bju.70442","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/bjui-journals.onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/bju.70442","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/bjui-journals.onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/bju.70442","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T08:58:50Z","timestamp":1788166730000},"score":1,"resource":{"primary":{"URL":"https:\/\/bjui-journals.onlinelibrary.wiley.com\/doi\/10.1111\/bju.70442"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,31]]},"references-count":29,"alternative-id":["10.1111\/bju.70442"],"URL":"https:\/\/doi.org\/10.1111\/bju.70442","archive":["Portico"],"relation":{},"ISSN":["1464-4096","1464-410X"],"issn-type":[{"value":"1464-4096","type":"print"},{"value":"1464-410X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,31]]},"assertion":[{"value":"2026-08-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"bju.70442"}}