{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T13:05:12Z","timestamp":1785503112106,"version":"3.56.0"},"reference-count":34,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T00:00:00Z","timestamp":1785283200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Urologia"],"abstract":"<jats:p>Artificial intelligence (AI) is increasingly applied in clinical practice to enhance prediction of postoperative outcomes. This systematic review evaluated the performance and clinical relevance of AI-based prognostic models for patients undergoing percutaneous nephrolithotomy (PCNL). A comprehensive search of PubMed, Embase, Scopus, Web of Science, and Google Scholar was conducted on 7 August 2025 to identify original studies that used AI to predict outcomes such as stone-free status. Risk of bias was assessed using the Prediction model Risk of Bias Assessment Tool\u2014Artificial Intelligence extension. A narrative synthesis of study characteristics, and reported performance metrics of AI models was conducted. Twenty-one studies involving 24,087 patients met the inclusion criteria. Tree-based, support vector, discriminant, and regression models achieved the highest median AUCs (0.79\u20130.81) for predicting stone-free status, whereas neural networks showed lower performance (median 0.60). Tree-based and similarity-based models performed best for predicting the need for adjuvant therapy. Neural networks performed well for bleeding-related outcomes (median AUC 0.87), while tree-based and regression models showed more consistent performance for procedural complications and hospitalization. Infection-related outcomes were predicted most accurately by tree-based and neural network models (median AUCs 0.89\u20130.90). Temporal trends revealed a shift from early reliance on neural networks and support vector machines to increased use of tree-based approaches in recent years. Overall, AI models offer useful support for perioperative decision-making, though their reliability varies across outcomes. Model performance is highest for stone-free status and infection-related outcomes, but lower for rare or poorly-defined endpoints such as bleeding or peri-procedural complications, reflecting limitations in available features and outcome heterogeneity. Clinically, current models may inform management but are not yet sufficient to dictate care. Future research should focus on standardized outcome definitions, multi-institutional datasets, and integration of high-dimensional data such as imaging and radiomics to develop robust, externally validated predictive tools for prospective implementation in PCNL practice.<\/jats:p>","DOI":"10.1177\/03915603261467531","type":"journal-article","created":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T17:19:55Z","timestamp":1785345595000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["The use of artificial intelligence to predict postoperative outcomes following percutaneous nephrolithotomy: A systematic review of prognostic modeling studies"],"prefix":"10.1177","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4340-3961","authenticated-orcid":false,"given":"Mohammadreza","family":"Padooiy Nooshabadi","sequence":"first","affiliation":[{"name":"Urology Department, Firoozgar Hospital, School of Medicine, Iran University of Medical Sciences, Tehran, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3945-3803","authenticated-orcid":false,"given":"Behnam","family":"Shakiba","sequence":"additional","affiliation":[{"name":"Urology Department, Firoozgar Hospital, School of Medicine, Iran University of Medical Sciences, Tehran, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hossein","family":"Akbarnataj","sequence":"additional","affiliation":[{"name":"School of Medicine, Iran University of Medical Sciences, Tehran, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nadia","family":"Saniee","sequence":"additional","affiliation":[{"name":"Department of Medical Library and Information Sciences, School of Allied Medical Sciences, Hamedan University of Medical Sciences, Hamedan, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,7,29]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"crossref","unstructured":"Lang J Narendrula A El-Zawahry A et al. Global trends in incidence and burden of urolithiasis from 1990 to 2019: an analysis of global burden of disease study data. Eur Urol Open Sci 2022; 35: 37\u201346. https:\/\/doi.org\/10.1016\/j.euros.2021.10.008","DOI":"10.1016\/j.euros.2021.10.008"},{"key":"e_1_3_3_3_2","unstructured":"T\u00fcrk C Neisius A Petrik A et al. EAU guidelines on urolithiasis. Eur Assoc Urol 2020; 87: 34\u201338."},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.3390\/complications2010005"},{"key":"e_1_3_3_5_2","doi-asserted-by":"crossref","unstructured":"Kyriazis I Panagopoulos V Kallidonis P et al. Complications in percutaneous nephrolithotomy. World J Urol 2015; 33: 1069\u20131077. https:\/\/doi.org\/10.1007\/s00345-014-1400-8","DOI":"10.1007\/s00345-014-1400-8"},{"key":"e_1_3_3_6_2","doi-asserted-by":"crossref","unstructured":"Chichakli R Krause R Voelzke B et al. Incidence of perinephric hematoma after percutaneous nephrolithotomy. J Endourol 2008; 22: 1227\u20131232. https:\/\/doi.org\/10.1089\/end.2008.0002","DOI":"10.1089\/end.2008.0002"},{"key":"e_1_3_3_7_2","doi-asserted-by":"crossref","unstructured":"Keoghane SR Cetti RJ Rogers AE et al. Blood transfusion embolisation and nephrectomy after percutaneous nephrolithotomy (PCNL). BJU Int 2013; 111: 628\u2013632. https:\/\/doi.org\/10.1111\/j.1464-410X.2012.11394.x","DOI":"10.1111\/j.1464-410X.2012.11394.x"},{"key":"e_1_3_3_8_2","doi-asserted-by":"crossref","unstructured":"Geraghty RM Thakur A Howles S et al. Use of temporally validated machine learning models to predict outcomes of percutaneous nephrolithotomy using data from the British association of urological surgeons percutaneous nephrolithotomy audit. Eur Urol Focus 2024; 10: 290\u2013297. https:\/\/doi.org\/10.1016\/j.euf.2024.01.011","DOI":"10.1016\/j.euf.2024.01.011"},{"key":"e_1_3_3_9_2","doi-asserted-by":"crossref","unstructured":"Aminsharifi A Irani D Pooyesh S et al. Artificial neural network system to predict the postoperative outcome of percutaneous nephrolithotomy. J Endourol 2017; 31: 461\u2013467. https:\/\/doi.org\/10.1089\/end.2016.0791","DOI":"10.1089\/end.2016.0791"},{"key":"e_1_3_3_10_2","doi-asserted-by":"crossref","unstructured":"Rasyid N Atmoko W Birowo P. Artificial intelligence in the prediction of stone-free status in urinary stone disease treated with extracorporeal shockwave lithotripsy: a systematic review. F1000Res 2025; 14: 16. https:\/\/doi.org\/10.12688\/f1000research.152346.2","DOI":"10.12688\/f1000research.152346.2"},{"key":"e_1_3_3_11_2","doi-asserted-by":"crossref","unstructured":"Hameed BZ Shah M Naik N et al. The ascent of artificial intelligence in endourology: a systematic review over the last 2 decades. Curr Urol Rep 2021; 22: 53. https:\/\/doi.org\/10.1007\/s11934-021-01069-3","DOI":"10.1007\/s11934-021-01069-3"},{"key":"e_1_3_3_12_2","doi-asserted-by":"crossref","unstructured":"Altunhan A Soyturk S Guldibi F et al. Artificial intelligence in urolithiasis: a systematic review of utilization and effectiveness. World J Urol 2024; 42: 579. https:\/\/doi.org\/10.1007\/s00345-024-05268-8","DOI":"10.1007\/s00345-024-05268-8"},{"key":"e_1_3_3_13_2","doi-asserted-by":"crossref","unstructured":"Page MJ McKenzie JE Bossuyt PM et al. The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. BMJ 2021; 372: n71. https:\/\/doi.org\/10.1136\/bmj.n71","DOI":"10.1136\/bmj.n71"},{"key":"e_1_3_3_14_2","doi-asserted-by":"crossref","unstructured":"Moons KG Damen JA Kaul T et al. PROBAST+ AI: an updated quality risk of bias and applicability assessment tool for prediction models using regression or artificial intelligence methods. BMJ 2025; 388: e082505. https:\/\/doi.org\/10.1136\/bmj-2024-082505","DOI":"10.1136\/bmj-2024-082505"},{"key":"e_1_3_3_15_2","doi-asserted-by":"crossref","unstructured":"Geraghty RM Finch W Fowler S et al. Use of internally validated machine and deep learning models to predict outcomes of percutaneous nephrolithotomy using data from the BAUS PCNL audit. medRxiv 2022: 2022.2006.2016.22276481. https:\/\/doi.org\/10.1101\/2022.06.16.22276481.","DOI":"10.1101\/2022.06.16.22276481"},{"key":"e_1_3_3_16_2","doi-asserted-by":"crossref","unstructured":"Yang Y Cao Z Wang W et al. Application of machine-learning models in predicting transfusion among complex renal stones patients receiving percutaneous nephrolithotomy: a retrospective study. Research Square 2022. https:\/\/doi.org\/10.21203\/rs.3.rs-1488309\/v2","DOI":"10.21203\/rs.3.rs-1488309\/v2"},{"key":"e_1_3_3_17_2","doi-asserted-by":"crossref","unstructured":"Zhou G Yang B Zhou Y et al. Machine learning constructs a model to predict systemic inflammatory response syndrome after percutaneous nephrolithotomy. Research Square 2024. https:\/\/doi.org\/10.21203\/rs.3.rs-4768219\/v1","DOI":"10.21203\/rs.3.rs-4768219\/v1"},{"key":"e_1_3_3_18_2","doi-asserted-by":"crossref","unstructured":"Zou X-C Yuan RM Zhou J et al. Preoperative prediction of bleeding complications in percutaneous nephrolithotomy using a machine learning model based on CT radiomics and clinical variables. Research Square 2024. https:\/\/doi.org\/10.21203\/rs.3.rs-4168137\/v1","DOI":"10.21203\/rs.3.rs-4168137\/v1"},{"key":"e_1_3_3_19_2","doi-asserted-by":"crossref","unstructured":"Liu ZR Yu ZJ Zhou J et al. Predictive value of stone-free rate after percutaneous nephroscopy based on multiple machine learning models. Front Med 2025; 12: 1559613. https:\/\/doi.org\/10.3389\/fmed.2025.1559613","DOI":"10.3389\/fmed.2025.1559613"},{"key":"e_1_3_3_20_2","doi-asserted-by":"crossref","unstructured":"Shalabayeva L Bah\u00edlo Mateu P Romeu Ferras M et al. Machine learning models for predicting postoperative complications and hospitalization after percutaneous nephrolithotomy. Algorithms 2025; 18: 558. https:\/\/doi.org\/10.3390\/a18090558","DOI":"10.3390\/a18090558"},{"key":"e_1_3_3_21_2","doi-asserted-by":"crossref","unstructured":"AlAzab R Ghammaz O Ardah N et al. Predicting the stone-free status of percutaneous nephrolithotomy with the machine learning system. Int J Nephrol Renovasc Dis 2023; 16: 197\u2013206. https:\/\/doi.org\/10.2147\/IJNRD.S427404","DOI":"10.2147\/IJNRD.S427404"},{"key":"e_1_3_3_22_2","doi-asserted-by":"crossref","unstructured":"Alghafees MA Rab SA Aljurayyad AS et al. A retrospective cohort study on the use of machine learning to predict stone-free status following percutaneous nephrolithotomy: an experience from Saudi Arabia. Ann Med Surg 2022; 84: 104957. https:\/\/doi.org\/10.1016\/j.amsu.2022.104957","DOI":"10.1016\/j.amsu.2022.104957"},{"key":"e_1_3_3_23_2","doi-asserted-by":"crossref","unstructured":"Aminsharifi A Irani D Tayebi S et al. Predicting the postoperative outcome of percutaneous nephrolithotomy with machine learning system: software validation and comparative analysis with guy\u2019s stone score and the CROES nomogram. J Endourol 2020; 34: 692\u2013699. https:\/\/doi.org\/10.1089\/end.2019.0475","DOI":"10.1089\/end.2019.0475"},{"key":"e_1_3_3_24_2","doi-asserted-by":"crossref","unstructured":"Hameed BZ Shah M Naik N et al. Application of artificial intelligence-based classifiers to predict the outcome measures and stone-free status following percutaneous nephrolithotomy for staghorn calculi: cross-validation of data and estimation of accuracy. J Endourol 2021; 35: 1307\u20131313. https:\/\/doi.org\/10.1089\/end.2020.1136","DOI":"10.1089\/end.2020.1136"},{"key":"e_1_3_3_25_2","doi-asserted-by":"crossref","unstructured":"Hou J Wen X Qu G et al. A multicenter study on the application of artificial intelligence radiological characteristics to predict prognosis after percutaneous nephrolithotomy. Front Endocrinol 2023; 14: 1184608. https:\/\/doi.org\/10.3389\/fendo.2023.1184608","DOI":"10.3389\/fendo.2023.1184608"},{"key":"e_1_3_3_26_2","doi-asserted-by":"crossref","unstructured":"Li P Tang Y Zeng Q et al. Diagnostic performance of machine learning in systemic infection following percutaneous nephrolithotomy and identification of associated risk factors. Heliyon 2024; 10: e30956. https:\/\/doi.org\/10.1016\/j.heliyon.2024.e30956","DOI":"10.1016\/j.heliyon.2024.e30956"},{"key":"e_1_3_3_27_2","doi-asserted-by":"crossref","unstructured":"Meng R Wang W Zhai Z et al. Machine learning algorithm to predict postoperative bleeding complications after lateral decubitus percutaneous nephrolithotomy. Medicine 2024; 103: e37050. https:\/\/doi.org\/10.1097\/MD.0000000000037050","DOI":"10.1097\/MD.0000000000037050"},{"key":"e_1_3_3_28_2","doi-asserted-by":"crossref","unstructured":"Pooyesh S Foshati S Sabeti M et al. Predicting outcomes in kidney stone endoscopic surgery by rotation forest algorithm. Comput Methods Biomech Biomed Eng Imaging Vis 2023; 11: 1397\u20131407. https:\/\/doi.org\/10.1080\/21681163.2022.2131629","DOI":"10.1080\/21681163.2022.2131629"},{"key":"e_1_3_3_29_2","doi-asserted-by":"crossref","unstructured":"Shabaniyan T Parsaei H Aminsharifi A et al. An artificial intelligence-based clinical decision support system for large kidney stone treatment. Australas Phys Eng Sci Med 2019; 42: 771\u2013779. https:\/\/doi.org\/10.1007\/s13246-019-00780-3","DOI":"10.1007\/s13246-019-00780-3"},{"key":"e_1_3_3_30_2","doi-asserted-by":"crossref","unstructured":"Shen R Ming S Qian W et al. A novel post-percutaneous nephrolithotomy sepsis prediction model using machine learning. BMC Urol 2024; 24: 27. https:\/\/doi.org\/10.1186\/s12894-024-01414-x","DOI":"10.1186\/s12894-024-01414-x"},{"key":"e_1_3_3_31_2","doi-asserted-by":"crossref","unstructured":"Zou XC Luo CW Yuan RM et al. Develop a radiomics-based machine learning model to predict the stone-free rate post-percutaneous nephrolithotomy. Urolithiasis 2024; 52: 64. https:\/\/doi.org\/10.1007\/s00240-024-01562-7","DOI":"10.1007\/s00240-024-01562-7"},{"key":"e_1_3_3_32_2","doi-asserted-by":"crossref","unstructured":"Zhang T Zhu L Wang X et al. Machine learning models to predict systemic inflammatory response syndrome after percutaneous nephrolithotomy. BMC Urol 2024; 24: 140. https:\/\/doi.org\/10.1186\/s12894-024-01529-1","DOI":"10.1186\/s12894-024-01529-1"},{"key":"e_1_3_3_33_2","doi-asserted-by":"crossref","unstructured":"Zhao H Li W Li J et al. Predicting the stone-free status of percutaneous nephrolithotomy with the machine learning system: comparative analysis with Guy\u2019s stone score and the STONE score system. Front Pharmacol 2022; 9: 880291. https:\/\/doi.org\/10.3389\/fmolb.2022.880291","DOI":"10.3389\/fmolb.2022.880291"},{"key":"e_1_3_3_34_2","doi-asserted-by":"crossref","unstructured":"Gavi F Ragonese M Fettucciari D et al. Antibiotic prophylaxis in stone surgery: a systematic review of the literature. World J Urol 2025; 43: 144. https:\/\/doi.org\/10.1007\/s00345-025-05528-1","DOI":"10.1007\/s00345-025-05528-1"},{"key":"e_1_3_3_35_2","doi-asserted-by":"crossref","unstructured":"Collins GS Moons KG Dhiman P et al. TRIPOD+ AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ 2024; 385: e078378. https:\/\/doi.org\/10.1136\/bmj-2023-078378","DOI":"10.1136\/bmj-2023-078378"}],"container-title":["Urologia Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/03915603261467531","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/03915603261467531","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/03915603261467531","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T12:18:06Z","timestamp":1785500286000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/03915603261467531"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,29]]},"references-count":34,"alternative-id":["10.1177\/03915603261467531"],"URL":"https:\/\/doi.org\/10.1177\/03915603261467531","relation":{},"ISSN":["0391-5603","1724-6075"],"issn-type":[{"value":"0391-5603","type":"print"},{"value":"1724-6075","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,29]]},"article-number":"03915603261467531"}}