{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T12:18:59Z","timestamp":1788437939746,"version":"build-2803163510"},"reference-count":20,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"5","license":[{"start":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T00:00:00Z","timestamp":1779235200000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:title>\n                    A\n                    <jats:sc>BSTRACT<\/jats:sc>\n                  <\/jats:title>\n                  <jats:sec>\n                    <jats:title>Aims:<\/jats:title>\n                    <jats:p>To evaluate the diagnostic accuracy of ChatGPT-5 and Gemini 2.5 Pro compared with a pediatric radiologist reference standard in grading vesicoureteral reflux (VUR) on pediatric micturating cystourethrogram (MCUG) studies.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and Methods:<\/jats:title>\n                    <jats:p>This retrospective study included 125 pediatric MCUG cases, comprising 25 cases per VUR Grade (I-V) as determined by radiologists. A balanced distribution of VUR grades was employed to facilitate a comprehensive assessment of model performance across the severity spectrum. For each case, the most representative image was anonymized, and the stored Joint Photographic Experts Group images were randomly uploaded to ChatGPT-5 and Gemini 2.5 Pro with a standardized prompt requesting VUR grading. Grades assigned by the models were compared with the radiologist\u2019s consensus standard.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>VUR was present in 182\/250 (72.8%) renal units, more frequently on the left side (80%) than the right side (65.6%). Both models demonstrated the highest accuracy in identifying the absence of reflux (ChatGPT-5 = 92.6% and Gemini 2.5 Pro = 88.2%). Overall diagnostic accuracy was 52% (131\/250) for ChatGPT-5 and 46% (115\/250) for Gemini 2.5 Pro. ChatGPT-5 performed best for grades III\u2013IV (51% and 49%, respectively), whereas Gemini 2.5 Pro performed best for Grade V (54%). Agreement with radiologists was fair (ChatGPT-5 \u03ba = 0.40; Gemini 2.5 Pro \u03ba = 0.33).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion:<\/jats:title>\n                    <jats:p>ChatGPT-5 and Gemini 2.5 Pro demonstrated fair but suboptimal accuracy in grading VUR. Model performance appears to be influenced by the prompting strategy used. Multimodal large language models show potential as adjunctive tools; however, further optimization of prompting approaches and multimodal integration is required before clinical application.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.4103\/jiaps.jiaps_90_26","type":"journal-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T08:00:19Z","timestamp":1779436819000},"page":"723-731","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":0,"title":["Diagnostic Performance of Multimodal Large Language Models for Grading Pediatric Vesicoureteral Reflux on MCUG: A Preliminary Study"],"prefix":"10.4103","volume":"31","author":[{"given":"Shubham","family":"Saini","sequence":"first","affiliation":[{"name":"Department of Radiodiagnosis and Imaging, Postgraduate Institute of Medical Education and Research, Chandigarh, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anmol","family":"Bhatia","sequence":"additional","affiliation":[{"name":"Department of Radiodiagnosis and Imaging, Postgraduate Institute of Medical Education and Research, Chandigarh, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akshay Kumar","family":"Saxena","sequence":"additional","affiliation":[{"name":"Department of Radiodiagnosis and Imaging, Postgraduate Institute of Medical Education and Research, Chandigarh, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ravi Prakash","family":"Kanojia","sequence":"additional","affiliation":[{"name":"Department of Pediatric Surgery, Postgraduate Institute of Medical Education and Research, Chandigarh, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kushaljit Singh","family":"Sodhi","sequence":"additional","affiliation":[{"name":"Department of Radiodiagnosis and Imaging, Postgraduate Institute of Medical Education and Research, Chandigarh, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","published-online":{"date-parts":[[2026,5,20]]},"reference":[{"key":"R1-20260903","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1055\/s-0042-1759863","article-title":"Artificial intelligence: a primer for the radiologists","volume":"1","author":"Bhatia","year":"2022","journal-title":"Indographics"},{"key":"R2-20260903","first-page":"431","article-title":"ChatGPT: Chasing the Storm in Radiology Training and Education","volume":"33","author":"Sodhi","year":"2025","journal-title":"Indian J Radiol Imaging"},{"key":"R4-20260903","doi-asserted-by":"crossref","DOI":"10.1007\/s00247-025-06485-y","article-title":"Triage and workflow optimization with artificial intelligence in pediatric imaging","author":"Bhatia","year":"2025","journal-title":"Pediatr Radiol"},{"key":"R7-20260903","doi-asserted-by":"crossref","first-page":"877","DOI":"10.1016\/j.jacr.2023.07.007","article-title":"Exploring the clinical translation of generative models like ChatGPT: Promise and pitfalls in radiology, from patients to population health","volume":"20","author":"Doo","year":"2023","journal-title":"J Am Coll Radiol"},{"key":"R8-20260903","doi-asserted-by":"crossref","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","article-title":"Large language models in medicine","volume":"29","author":"Thirunavukarasu","year":"2023","journal-title":"Nat Med"},{"key":"R9-20260903","doi-asserted-by":"crossref","first-page":"866","DOI":"10.1001\/jama.2023.14217","article-title":"Creation and adoption of large language models in medicine","volume":"330","author":"Shah","year":"2023","journal-title":"JAMA"},{"key":"R10-20260903","doi-asserted-by":"crossref","first-page":"e232756","DOI":"10.1148\/radiol.232756","article-title":"Chatbots and large language models in radiology: A practical primer for clinical and research applications","volume":"310","author":"Bhayana","year":"2024","journal-title":"Radiology"},{"key":"R11-20260903","doi-asserted-by":"crossref","first-page":"e2431076","DOI":"10.2214\/AJR.24.31076","article-title":"Applications of artificial intelligence for pediatric cancer imaging","volume":"223","author":"Singh","year":"2024","journal-title":"Am J Roentgenol"},{"key":"R12-20260903","doi-asserted-by":"crossref","first-page":"e2329741","DOI":"10.2214\/AJR.23.29741","article-title":"Imaging of vesicoureteral reflux: AJR expert panel narrative review","volume":"222","author":"Cajigas-Loyola","year":"2024","journal-title":"Am J Roentgenol"},{"key":"R13-20260903","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1016\/S0022-5347(17)59492-6","article-title":"Intrarenal reflux and its relationship to renal scarring","volume":"113","author":"Rose","year":"1975","journal-title":"J Urol"},{"key":"R15-20260903","doi-asserted-by":"crossref","first-page":"587","DOI":"10.1007\/s002470000263","article-title":"What is the normal prevalence of vesicoureteral reflux?","volume":"30","author":"Sargent","year":"2000","journal-title":"Pediatr Radiol"},{"key":"R16-20260903","doi-asserted-by":"crossref","first-page":"1535","DOI":"10.1016\/j.juro.2009.06.053","article-title":"Nomograms for predicting annual resolution rate of primary vesicoureteral reflux: Results from 2,462 children","volume":"182","author":"Estrada","year":"2009","journal-title":"J Urol"},{"key":"R17-20260903","doi-asserted-by":"crossref","first-page":"440","DOI":"10.1111\/iju.13915","article-title":"New trends in voiding cystourethrography and vesicoureteral reflux: Who, when and how?","volume":"26","author":"Arlen","year":"2019","journal-title":"Int J Urol"},{"key":"R18-20260903","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1007\/s004670050316","article-title":"Variation in the diagnosis of vesicoureteric reflux using micturating cystourethrography","volume":"11","author":"Craig","year":"1997","journal-title":"Pediatr Nephrol"},{"key":"R19-20260903","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1016\/j.jpurol.2013.06.014","article-title":"Reliability of voiding cystourethrogram for the grading of vesicoureteral reflux","volume":"10","author":"O'Neil","year":"2014","journal-title":"J Pediatr Urol"},{"key":"R20-20260903","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1016\/j.jpurol.2016.06.020","article-title":"Reliability of grading of vesicoureteral reflux and other findings on voiding cystourethrography","volume":"13","author":"Schaeffer","year":"2017","journal-title":"J Pediatr Urol"},{"key":"R21-20260903","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/j.diii.2024.04.003","article-title":"ChatGPT in radiology: A systematic review of performance, pitfalls, and future perspectives","volume":"105","author":"Keshavarz","year":"2024","journal-title":"Diagn Interv Imaging"},{"key":"R22-20260903","first-page":"e70897","article-title":"Comparative accuracy of ChatGPT 4.0 and Google Gemini in answering pediatric radiology text-based questions","volume":"16","author":"Abdul Sami","year":"2024","journal-title":"Cureus"},{"key":"R23-20260903","doi-asserted-by":"crossref","first-page":"1729","DOI":"10.1007\/s00247-024-06025-0","article-title":"Capability of multimodal large language models to interpret pediatric radiological images","volume":"54","author":"Reith","year":"2024","journal-title":"Pediatr Radiol"},{"key":"R24-20260903","doi-asserted-by":"crossref","DOI":"10.4274\/dir.2025.253460","article-title":"Diagnostic accuracy and consistency of ChatGPT-4o in radiology: influence of image, clinical data, and answer options on performance","author":"Atak\u0131r","year":"2025","journal-title":"Diagn Interv Radiol"}],"container-title":["Journal of Indian Association of Pediatric Surgeons"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.ovid.com\/10.4103\/jiaps.jiaps_90_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T12:03:49Z","timestamp":1788437029000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ovid.com\/10.4103\/jiaps.jiaps_90_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,20]]},"references-count":20,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026]]}},"URL":"https:\/\/doi.org\/10.4103\/jiaps.jiaps_90_26","relation":{},"ISSN":["0971-9261","1998-3891"],"issn-type":[{"value":"0971-9261","type":"print"},{"value":"1998-3891","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,20]]},"assertion":[{"value":"2026-02-26","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-10","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}