{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T03:24:44Z","timestamp":1790738684777,"version":"4.1.0"},"reference-count":35,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T00:00:00Z","timestamp":1755561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>This study aimed to develop three types of machine learning (ML) models based on gradient boosting decision tree (GBDT), random forest (RF), and extreme gradient boosting (XGBoost) to explore their predictive value for the stone-free rate after percutaneous nephrolithotomy (PCNL).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Patients and methods<\/jats:title>\n                    <jats:p>A retrospective analysis was conducted on 160 patients who underwent PCNL. The patients were randomly divided into a training set and a test set in a 7:3 ratio. Clinical data were collected, and univariate analysis was performed to identify important data significantly associated with the stone-free rate after PCNL. Three ML models (GBDT, RF, and XGBoost) were developed using the training set. The predictive performance of these models was evaluated using the area under the curve (AUC) of the receiver operating characteristic (ROC) on the test set, confusion matrix, specificity, sensitivity, accuracy, and F1 score. For the top-performing prediction model, the study further employed the SHapley Additive exPlanations (SHAP) method to enhance model interpretability by elucidating the contribution of individual features to the prediction outcomes and ranking the relative importance of the predictive data. Finally, the clinical utility of the model was assessed through decision curve analysis (DCA), which quantified the net clinical benefit of applying the model across various risk thresholds.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Postoperative statistics indicated a stone-free rate of 70.6% (\n                      <jats:italic>n<\/jats:italic>\n                      =\u202f113) among the patients. The data significantly associated with the absence of residual stones included the number of stones, stone diameter, stone CT value, history of previous stone surgery, stone location, and stone shape (\n                      <jats:italic>p<\/jats:italic>\n                      &amp;lt;\u202f0.05). All three models demonstrated strong predictive effects in the validation set, with the GBDT model showing superior performance [AUC: 0.836 (95% CI: 0.785\u20130.873); accuracy: 0.854; sensitivity: 0.853; specificity: 0.857] compared to the XGBoost [AUC: 0.830 (95% CI: 0.792\u20130.868); accuracy: 0.771; sensitivity: 0.824; specificity: 0.643] and RF models [AUC: 0.803 (95% CI: 0.763\u20130.837); accuracy: 0.792; sensitivity: 0.824; specificity: 0.714]. The F1 scores for the GBDT, RF, and XGBoost models were 0.892, 0.836, and 0.849, respectively. The DCA decision curve analysis confirmed that the GBDT model offers a favorable net clinical benefit. In addition, the SHAP analysis identified the number of stones and the stone CT value as the most critical features influencing the model\u2019s predictions, contributing significantly to its overall predictive performance.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The prediction models developed based on three machine learning algorithms can accurately predict the stone-free rate after PCNL in patients with urinary tract stones. Among these, the GBDT model can effectively identify patients who are most likely to achieve successful outcomes from PCNL based on demographic and stone characteristics, thereby assisting in clinical treatment decision-making.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2025.1559613","type":"journal-article","created":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T05:19:48Z","timestamp":1755580788000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Predictive value of the stone-free rate after percutaneous nephrolithotomy based on multiple machine learning models"],"prefix":"10.3389","volume":"12","author":[{"given":"Zhao Rong","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhan Jiang","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian Biao","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,8,19]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"736","DOI":"10.1038\/s41581-020-0320-7","article-title":"Determining the true burden of kidney stone disease","volume":"16","author":"Thongprayoon","year":"2020","journal-title":"Nat Rev Nephrol"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1016\/j.advnut.2023.03.002","article-title":"Kidney stone prevention","volume":"14","author":"Peerapen","year":"2023","journal-title":"Adv Nutr"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1111\/bju.16179","article-title":"Prevalence of urolithiasis in China: a systematic review and meta-analysis","volume":"133","author":"Tan","year":"2024","journal-title":"BJU Int"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"1114","DOI":"10.3390\/jcm13041114","article-title":"Urological guidelines for kidney stones: overview and comprehensive update","volume":"13","author":"Akram","year":"2024","journal-title":"J Clin Med"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1016\/j.ucl.2021.08.003","article-title":"Mini percutaneous kidney stone removal: applicable technologies","volume":"49","author":"Desai","year":"2022","journal-title":"Urol Clin North Am"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1016\/j.ajur.2019.10.004","article-title":"Percutaneous nephrolithotomy for staghorn calculi: troubleshooting and managing complications","volume":"7","author":"Gadzhiev","year":"2020","journal-title":"Asian J Urol"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"422","DOI":"10.3390\/medicina58030422","article-title":"Factors affecting residual stone rate, operative duration, and complications in patients undergoing minimally invasive percutaneous nephrolithotomy","volume":"58","author":"Doykov","year":"2022","journal-title":"Medicina"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1016\/j.jinf.2023.07.006","article-title":"Artificial intelligence, machine learning and deep learning: potential resources for the infection clinician","volume":"87","author":"Theodosiou","year":"2023","journal-title":"J Infect"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"933","DOI":"10.1016\/j.rcl.2021.06.004","article-title":"Basic artificial intelligence techniques: machine learning and deep learning","volume":"59","author":"Erickson","year":"2021","journal-title":"Radiol Clin North Am"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"782","DOI":"10.1097\/MOU.0000000000000820","article-title":"Artificial intelligence in the diagnosis, treatment and prevention of urinary stones","volume":"30","author":"Yang","year":"2020","journal-title":"Curr Opin Urol"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/jcm10091864","article-title":"Artificial intelligence and its impact on urological diseases and management: a comprehensive review of the literature","volume":"10","author":"Hameed","year":"2021","journal-title":"J Clin Med"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"870","DOI":"10.1016\/j.kint.2021.05.031","article-title":"A multicenter study to develop a non-invasive radiomic model to identify urinary infection stone in vivo using machine-learning","volume":"100","author":"Zheng","year":"2021","journal-title":"Kidney Int"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"e37050","DOI":"10.1097\/MD.0000000000037050","article-title":"Machine learning algorithm to predict postoperative bleeding complications after lateral decubitus percutaneous nephrolithotomy","volume":"103","author":"Meng","year":"2024","journal-title":"Medicine"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1111\/bju.15836","article-title":"International alliance of urolithiasis guideline on retrograde intrarenal surgery","volume":"131","author":"Zeng","year":"2023","journal-title":"BJU Int"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"26","DOI":"10.3390\/medicina57010026","article-title":"Effectiveness of percutaneous nephrolithotomy, retrograde intrarenal surgery, and extracorporeal shock wave lithotripsy for treatment of renal stones: a systematic review and meta-analysis","volume":"57","author":"Kim","year":"2020","journal-title":"Medicina"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"309","DOI":"10.23736\/S2724-6051.21.04294-4","article-title":"Intraoperative and postoperative surgical complications after ureteroscopy, retrograde intrarenal surgery, and percutaneous nephrolithotomy: a systematic review","volume":"73","author":"Grosso","year":"2021","journal-title":"Minerva Urol Nephrol"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"CD007044","DOI":"10.1002\/14651858.CD007044.pub4","article-title":"Extracorporeal shock wave lithotripsy (ESWL) versus percutaneous nephrolithotomy (PCNL) or retrograde intrarenal surgery (RIRS) for kidney stones","volume":"8","author":"Setthawong","year":"2023","journal-title":"Cochrane Database Syst Rev"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"CD013445","DOI":"10.1002\/14651858.CD013445.pub2","article-title":"Percutaneous nephrolithotomy versus retrograde intrarenal surgery for treatment of renal stones in adults","volume":"11","author":"Soderberg","year":"2023","journal-title":"Cochrane Database Syst Rev"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"609","DOI":"10.1089\/end.2020.0868","article-title":"Residual stone fragments after percutaneous nephrolithotomy: shockwave lithotripsy vs retrograde intrarenal surgery","volume":"35","author":"Danilovic","year":"2021","journal-title":"J Endourol"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.ajur.2022.02.010","article-title":"Reliability of nephrolithometric nomograms in patients treated with minimally invasive percutaneous nephrolithotomy: a precision study","volume":"10","author":"Mazzon","year":"2023","journal-title":"Asian J Urol"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"4327","DOI":"10.1038\/s41598-025-88704-y","article-title":"Constructing a machine learning model for systemic infection after kidney stone surgery based on CT values","volume":"15","author":"Li","year":"2025","journal-title":"Sci Rep"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"674","DOI":"10.3390\/metabo14120674","article-title":"Machine learning models decoding the association between urinary stone diseases and metabolic urinary profiles","volume":"14","author":"Ma","year":"2024","journal-title":"Metabolites"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"579","DOI":"10.1007\/s00345-024-05268-8","article-title":"Artificial intelligence in urolithiasis: a systematic review of utilization and effectiveness","volume":"42","author":"Altunhan","year":"2024","journal-title":"World J Urol"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1089\/end.2021.0211","article-title":"Machine learning prediction of kidney stone composition using electronic health record-derived features","volume":"36","author":"Abraham","year":"2022","journal-title":"J Endourol"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"643","DOI":"10.3390\/jpm13040643","article-title":"Personalized prediction of patient radiation exposure for therapy of urolithiasis: an application and comparison of six machine learning algorithms","volume":"13","author":"Huettenbrink","year":"2023","journal-title":"J Pers Med"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"104569","DOI":"10.1016\/j.compbiomed.2021.104569","article-title":"Deep learning model for automated kidney stone detection using coronal CT images","volume":"135","author":"Yildirim","year":"2021","journal-title":"Comput Biol Med"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1007\/s00240-024-01593-0","article-title":"CT-based radiomics of machine-learning to screen high-risk individuals with kidney stones","volume":"52","author":"Zhu","year":"2024","journal-title":"Urolithiasis"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/s00240-023-01506-7","article-title":"AI prediction of extracorporeal shock wave lithotripsy outcomes for ureteral stones by machine learning-based analysis with a variety of stone and patient characteristics","volume":"52","author":"Nakamae","year":"2023","journal-title":"Urolithiasis"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"809","DOI":"10.1089\/end.2023.0457","article-title":"A novel machine-learning algorithm to predict stone recurrence with 24-hour urine data","volume":"38","author":"Shee","year":"2024","journal-title":"J Endourol"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1186\/s12894-024-01529-1","article-title":"Machine learning models to predict systemic inflammatory response syndrome after percutaneous nephrolithotomy","volume":"24","author":"Zhang","year":"2024","journal-title":"BMC Urol"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"712","DOI":"10.1089\/end.2023.0702","article-title":"Artificial intelligence in urology: application of a machine learning model to predict the risk of urolithiasis in a general population","volume":"38","author":"S\u00e1nchez","year":"2024","journal-title":"J Endourol"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1016\/j.urology.2022.07.008","article-title":"Machine learning models to predict 24 hour urinary abnormalities for kidney stone disease","volume":"169","author":"Kavoussi","year":"2022","journal-title":"Urology"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"17562872231196676","DOI":"10.1177\/17562872231196676","article-title":"The role of \u2018artificial intelligence, machine learning, virtual reality, and radiomics\u2019 in PCNL: a review of publication trends over the last 30\u202fyears","volume":"15","author":"Nedbal","year":"2023","journal-title":"Ther Adv Urol"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"2331","DOI":"10.1007\/s00345-022-04091-3","article-title":"Urologists are optimistic surgeons: prevalence and predictors of discordance between intraoperative stone-free rate and cross-sectional imaging evaluation after vacuum-assisted mini-percutaneous nephrolithotomy","volume":"40","author":"Jannello","year":"2022","journal-title":"World J Urol"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1007\/s00240-023-01495-7","article-title":"Comparison of endoscopic versus CT assessment of stone-free status after percutaneous nephrolithotomy (PCNL)","volume":"51","author":"Hartung","year":"2023","journal-title":"Urolithiasis"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1559613\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T05:19:49Z","timestamp":1755580789000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1559613\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,19]]},"references-count":35,"alternative-id":["10.3389\/fmed.2025.1559613"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2025.1559613","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,19]]},"article-number":"1559613"}}