{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T03:25:46Z","timestamp":1787196346231,"version":"build-2736575974"},"reference-count":20,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T00:00:00Z","timestamp":1787184000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T00:00:00Z","timestamp":1787184000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int Urogynecol J"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Introduction and Hypothesis<\/jats:title>\n                    <jats:p>Artificial intelligence (AI) tools such as ChatGPT are increasingly used by patients to seek health information, yet concerns remain regarding the accuracy and reliability of AI-generated content. Integrating evidence-based resources into these models may improve their educational effectiveness. In a previous pilot study, a retrieval-augmented ChatGPT model was found to outperform a standard ChatGPT model under controlled conditions, highlighting the need for further testing in pragmatic clinical contexts. The objective of this second pilot was to evaluate whether a retrieval-augmented AI model improves response quality and usability for patient-representative urogynecology queries, as rated by experts using validated instruments.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We developed a retrieval-augmented ChatGPT model grounded in the American Urogynecologic Society\u2019s (AUGS) patient education materials. Urogynecology specialists were recruited through professional networks and submitted patient-representative questions. Responses were assessed across six domains using the Quality Analysis of Medical Artificial Intelligence (QAMAI) tool, with usability measured by the System Usability Scale (SUS). Quantitative data were analyzed descriptively, and qualitative feedback was examined thematically.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Twenty-two questions were posed, with 11 out of 20 respondents providing complete responses. The median QAMAI score was 28 (IQR 24\u201329.8) and the mean SUS score was 81.8\u2009\u00b1\u200911.2. Respondents highlighted patient-friendly language, ease of use, and integration of AUGS links as strengths, while noting citation consistency, clinical depth, and comprehensiveness as areas for improvement.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>A retrieval-augmented ChatGPT model trained on AUGS materials generated high-quality responses with excellent usability. Though not a substitute for clinician counseling, such models may supplement provider\u2013patient communication.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s00192-026-06834-x","type":"journal-article","created":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T03:03:29Z","timestamp":1787195009000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving Pelvic Floor Disorder Education: A Second Pilot of a Retrieval-Augmented AI Chatbot Model"],"prefix":"10.1007","author":[{"given":"Madeline K.","family":"Moureau","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Berkley","family":"Davis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher X.","family":"Hong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,20]]},"reference":[{"key":"6834_CR1","unstructured":"Pew Research Center. Internet, Broadband Fact Sheet. Pew Research Center; 2024. https:\/\/www.pewresearch.org\/internet\/fact-sheet\/internet-broadband\/. Accessed 17 August 2025."},{"key":"6834_CR2","doi-asserted-by":"publisher","unstructured":"Wang X, Cohen R. Health information technology use among adults: United States, July\u2013December 2022. NCHS Data Brief, no 482. National Center for Health Statistics. 2023. https:\/\/doi.org\/10.15620\/cdc:133700.","DOI":"10.15620\/cdc:133700"},{"issue":"S8","key":"6834_CR3","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1097\/01.GOX.0001063880.34367.8d","volume":"12","author":"A James","year":"2024","unstructured":"James A, Hung Y, Chaker S, Saad M, Torres-Guzman R, Orra S, et al. ChatGPT: a rapidly growing platform for medical information delivery for the lay public. Plast Reconstr Surg Glob Open. 2024;12(S8):13\u20134. https:\/\/doi.org\/10.1097\/01.GOX.0001063880.34367.8d.","journal-title":"Plast Reconstr Surg Glob Open"},{"issue":"1","key":"6834_CR4","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1038\/s41391-023-00705-y","volume":"27","author":"A Cocci","year":"2024","unstructured":"Cocci A, Pezzoli M, Lo Re M, Russo GI, Asmundo MG, Fode M, et al. Quality of information and appropriateness of ChatGPT outputs for urology patients. Prostate Cancer Prostatic Dis. 2024;27(1):103\u20138. https:\/\/doi.org\/10.1038\/s41391-023-00705-y.","journal-title":"Prostate Cancer Prostatic Dis"},{"issue":"7","key":"6834_CR5","doi-asserted-by":"publisher","first-page":"1368","DOI":"10.1038\/s41433-023-02906-0","volume":"38","author":"F Cappellani","year":"2024","unstructured":"Cappellani F, Card KR, Shields CL, Pulido JS, Haller JA. Reliability and accuracy of artificial intelligence ChatGPT in providing information on ophthalmic diseases and management to patients. Eye. 2024;38(7):1368\u201373. https:\/\/doi.org\/10.1038\/s41433-023-02906-0.","journal-title":"Eye"},{"key":"6834_CR6","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/j.urology.2023.05.040","volume":"180","author":"B Coskun","year":"2023","unstructured":"Coskun B, Ocakoglu G, Yetemen M, Kaygisiz O. Can ChatGPT, an artificial intelligence language model, provide accurate and high-quality patient information on prostate cancer? Urology. 2023;180:35\u201358. https:\/\/doi.org\/10.1016\/j.urology.2023.05.040.","journal-title":"Urology"},{"issue":"1","key":"6834_CR7","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1007\/s13187-010-0183-x","volume":"26","author":"AJ Friedman","year":"2011","unstructured":"Friedman AJ, Cosby R, Boyko S, Hatton-Bauer J, Turnbull G. Effective teaching strategies and methods of delivery for patient education: a systematic review and practice guideline recommendations. J Cancer Educ. 2011;26(1):12\u201321. https:\/\/doi.org\/10.1007\/s13187-010-0183-x.","journal-title":"J Cancer Educ"},{"key":"6834_CR8","doi-asserted-by":"publisher","DOI":"10.21037\/gpm-23-16","volume":"6","author":"A Nemirovsky","year":"2023","unstructured":"Nemirovsky A, Horowitz AM, Malik RD. Patient counseling for pelvic organ prolapse surgery: methods used for patient education. Gynecol Pelvic Med. 2023;6:20. https:\/\/doi.org\/10.21037\/gpm-23-16.","journal-title":"Gynecol Pelvic Med"},{"issue":"4","key":"6834_CR9","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1111\/hex.12487","volume":"20","author":"M Sustersic","year":"2017","unstructured":"Sustersic M, Gauchet A, Foote A, Bosson JL. How best to use and evaluate patient information leaflets given during a consultation: a systematic review of literature reviews. Health Expect. 2017;20(4):531\u201342. https:\/\/doi.org\/10.1111\/hex.12487.","journal-title":"Health Expect"},{"key":"6834_CR10","unstructured":"International Urogynecological Association. Leaflets. https:\/\/www.yourpelvicfloor.org\/leaflets\/. Accessed 12 Feb 2026."},{"key":"6834_CR11","unstructured":"Fact Sheets and Downloads. Voices for PFD. https:\/\/www.voicesforpfd.org\/resources\/fact-sheets-and-downloads\/. Accessed 17 August 2025"},{"issue":"5","key":"6834_CR12","doi-asserted-by":"publisher","first-page":"1423","DOI":"10.1007\/s00192-025-06446-x","volume":"37","author":"MK Moureau","year":"2025","unstructured":"Moureau MK, Davis B, Hong CX. Development and evaluation of an augmented artificial intelligence model for urogynecology queries. Int Urogynecol J. 2025;37(5):1423\u20138. https:\/\/doi.org\/10.1007\/s00192-025-06446-x.","journal-title":"Int Urogynecol J"},{"issue":"11","key":"6834_CR13","doi-asserted-by":"publisher","first-page":"6123","DOI":"10.1007\/s00405-024-08710-0","volume":"281","author":"LA Vaira","year":"2024","unstructured":"Vaira LA, Lechien JR, Abbate V, Allevi F, Audino G, Beltramini GA, et al. Validation of the Quality Analysis of Medical Artificial Intelligence (QAMAI) tool: a new tool to assess the quality of health information provided by AI platforms. Eur Arch Otorhinolaryngol. 2024;281(11):6123\u201331. https:\/\/doi.org\/10.1007\/s00405-024-08710-0.","journal-title":"Eur Arch Otorhinolaryngol"},{"key":"6834_CR14","unstructured":"Brooke J. SUS: A quick and dirty usability scale. Usability Eval Ind. 1995;189."},{"key":"6834_CR15","unstructured":"Sauro J. Measuring usability with the System Usability Scale (SUS). 2011. https:\/\/measuringu.com\/sus\/. Accessed 17 August 2025"},{"issue":"3","key":"6834_CR16","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1016\/j.ero.2025.08.001","volume":"1","author":"A Madrid-Garc\u00eda","year":"2025","unstructured":"Madrid-Garc\u00eda A, Benavent D, Plasencia-Rodr\u00edguez C, Rosales-Rosado Z, Merino-Barbancho B, Freites-N\u00fa\u00f1ez D. Optimising the clinical application of rheumatology guidelines using large language models: a retrieval-augmented generation framework integrating EULAR and ACR recommendations. EULAR Rheumatol Open. 2025;1(3):228\u201336. https:\/\/doi.org\/10.1016\/j.ero.2025.08.001.","journal-title":"EULAR Rheumatol Open"},{"key":"6834_CR17","doi-asserted-by":"publisher","first-page":"1790","DOI":"10.3233\/shti251216","volume":"329","author":"S Guan","year":"2025","unstructured":"Guan S, Ho CM, Mok PK, Hui V. Development of a neurosurgery chatbot using large language models with retrieval-augmented generation. Stud Health Technol Inform. 2025;329:1790\u20131. https:\/\/doi.org\/10.3233\/shti251216.","journal-title":"Stud Health Technol Inform"},{"key":"6834_CR18","doi-asserted-by":"publisher","DOI":"10.1007\/s00417-025-06877-8","author":"K Reddy","year":"2025","unstructured":"Reddy K, Paulus YM. Leveraging retrieval-augmented large language models for patient education in ophthalmology. Graefes Arch Clin Exp Ophthalmol. 2025. https:\/\/doi.org\/10.1007\/s00417-025-06877-8.","journal-title":"Graefes Arch Clin Exp Ophthalmol"},{"key":"6834_CR19","doi-asserted-by":"publisher","first-page":"890","DOI":"10.3233\/shti250494","volume":"327","author":"S McInerney","year":"2025","unstructured":"McInerney S, Nash T, Lee R, Falis M, Gruber F, Casey A. AI chatbot for cancer patient support: development and evaluation using Llama 3.1, Mistral 7B, and PHI 3B. Stud Health Technol Inform. 2025;327:890\u20131. https:\/\/doi.org\/10.3233\/shti250494.","journal-title":"Stud Health Technol Inform"},{"issue":"7","key":"6834_CR20","doi-asserted-by":"publisher","first-page":"735","DOI":"10.1093\/asj\/sjaf038","volume":"45","author":"A Genovese","year":"2025","unstructured":"Genovese A, Prabha S, Borna S, Gomez-Cabello CA, Haider SA, Trabilsy M, et al. Artificial intelligence for patient support: assessing retrieval-augmented generation for answering postoperative rhinoplasty questions. Aesthet Surg J. 2025;45(7):735\u201344. https:\/\/doi.org\/10.1093\/asj\/sjaf038.","journal-title":"Aesthet Surg J"}],"container-title":["International Urogynecology Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00192-026-06834-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00192-026-06834-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00192-026-06834-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T03:03:34Z","timestamp":1787195014000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00192-026-06834-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,20]]},"references-count":20,"alternative-id":["6834"],"URL":"https:\/\/doi.org\/10.1007\/s00192-026-06834-x","relation":{},"ISSN":["0937-3462","1433-3023"],"issn-type":[{"value":"0937-3462","type":"print"},{"value":"1433-3023","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,20]]},"assertion":[{"value":"13 April 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 August 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This study was determined to be \u201cNot Regulated\u201d because the University of Michigan was not considered \u201cengaged\u201d in the research. Therefore, study activities did not require oversight from the University of Michigan Institutional Review Board.","order":1,"name":"Ethics","label":"Ethical\/Institutional Review Board Approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"None.","order":2,"name":"Ethics","label":"Conflicts of interest","group":{"name":"EthicsHeading","label":"Declarations"}}]}}