{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T21:14:32Z","timestamp":1788556472910,"version":"build-2803163510"},"reference-count":26,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Med Internet Res"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Personalized dietary counseling is central to recurrence prevention in patients with urolithiasis, particularly after a 24-hour urine metabolic evaluation. However, translating quantitative metabolic abnormalities into patient-facing, guideline-concordant, and safe dietary recommendations can be challenging in routine clinical practice. Large language models (LLMs) may assist with this task, but unguided responses may overlook key metabolic priorities or case-specific safety constraints.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study evaluated whether a guideline-integrated, safety-aware, LLM-based clinical interaction framework (StoneAgent) could generate higher-quality, personalized dietary recommendations than a standard LLM configuration for recurrent urolithiasis. We also assessed whether any performance advantage persisted when the same clinical scenarios were presented as patient query\u2013style inputs.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n We conducted an in silico comparative study using 30 synthetic clinical vignettes representing common, mixed, and safety-relevant metabolic stone scenarios. For the primary experiment, StoneAgent and a standard LLM configuration were compared using structured vignette inputs. For the robustness experiment, each vignette was reformulated into 2 patient query\u2013style variants (query A and query B), preserving the same clinical content in more natural conversational language. A vignette-specific expert reference standard was developed from guideline-informed specialist consensus. Three independent reviewers blindly rated outputs on a 5-point Likert scale for metabolic specificity, guideline adherence, and actionability; safety was assessed as a binary outcome. For the patient query\u2013style experiment, query A and query B were aggregated at the vignette level for paired comparison.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n In the structured-input experiment, StoneAgent achieved higher performance than the standard LLM across metabolic specificity, guideline adherence, and actionability, with median case-level scores of 5.00 (IQR 5.00\u20105.00) vs 3.00 (IQR 2.75\u20103.92) for metabolic specificity, 5.00 (IQR 5.00\u20105.00) vs 3.67 (IQR 3.08\u20104.00) for guideline adherence, and 5.00 (IQR 5.00\u20105.00) vs 3.00 (IQR 2.67\u20103.33) for actionability (all\n P<\/jats:italic>\n <.001). Safety pass rates were 100% (30\/30) for StoneAgent and 83.3% (25\/30) for the standard LLM (exact McNemar\n P<\/jats:italic>\n =.06). In the patient query\u2013style robustness experiment, StoneAgent retained a directional advantage after case-level aggregation, with mean scores of 4.44 vs 3.62 for metabolic specificity, 4.51 vs 3.63 for guideline adherence, and 4.11 vs 3.40 for actionability. Safety pass rates were 100% (30\/30) for StoneAgent and 90% (27\/30) for the standard LLM (exact McNemar\n P<\/jats:italic>\n =.25). The performance gap was more conservative under patient query\u2013style inputs compared with structured inputs, but the overall pattern remained consistent across domains.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n In this in silico study, a guideline-integrated, safety-aware clinical interaction framework generated higher-quality dietary recommendations for recurrent urolithiasis than a standard LLM condition with structured vignette inputs. This advantage was retained with patient query\u2013style inputs. These findings suggest that explicit clinical framing, guideline grounding, and safety-oriented response scaffolding may improve the reliability of specialty counseling tasks involving metabolic stone prevention. Further validation is needed using real patient-authored queries and prospective clinical workflows.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/95162","type":"journal-article","created":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T20:41:15Z","timestamp":1788554475000},"page":"e95162-e95162","source":"Crossref","is-referenced-by-count":0,"title":["Evaluating a Guideline-Integrated Clinical Interaction Framework Vs a Standard Large Language Model Interaction for Dietary Recommendations in Recurrent Urolithiasis: In Silico Study"],"prefix":"10.2196","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8647-9794","authenticated-orcid":false,"given":"Xiaofeng","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8083-2000","authenticated-orcid":false,"given":"Jun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0109-9944","authenticated-orcid":false,"given":"Yudong","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3844-0324","authenticated-orcid":false,"given":"Yujie","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7966-8998","authenticated-orcid":false,"given":"Yong","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5377-2039","authenticated-orcid":false,"given":"Faming","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8372-4428","authenticated-orcid":false,"given":"Ye","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4531-2212","authenticated-orcid":false,"given":"Fan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5420-8518","authenticated-orcid":false,"given":"Jin","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,9,4]]},"reference":[{"issue":"9","key":"R1","doi-asserted-by":"publisher","first-page":"1301","DOI":"10.1007\/s00345-017-2008-6","article-title":"Epidemiology of stone disease across the world","volume":"35","author":"Sorokin","journal-title":"World J Urol"},{"issue":"2","key":"R2","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1097\/MNH.0000000000000478","article-title":"Leave no stone unturned: defining recurrence in kidney stone formers","volume":"28","author":"D\u2019Costa","journal-title":"Curr Opin Nephrol Hypertens"},{"issue":"1","key":"R3","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1016\/j.euf.2017.04.001","article-title":"Burden of urolithiasis: trends in prevalence, treatments, and costs","volume":"3","author":"Raheem","journal-title":"Eur Urol Focus"},{"issue":"5","key":"R4","doi-asserted-by":"publisher","first-page":"880","DOI":"10.1590\/S1677-5538.IBJU.2016.0649","article-title":"Quality of life and urolithiasis: the patient-reported outcomes measurement information system (PROMIS)","volume":"43","author":"Patel","journal-title":"Int Braz J Urol"},{"key":"R5","doi-asserted-by":"publisher","DOI":"10.2147\/MDER.S384823","article-title":"Incremental healthcare cost implications of retreatment following ureteroscopy or percutaneous nephrolithotomy for upper urinary tract stones: a population-based study of commercially-insured US adults","volume":"15","author":"Johnston","journal-title":"Med Devices (Auckl)"},{"issue":"4","key":"R6","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1016\/j.eururo.2024.05.029","article-title":"Metabolic evaluation and recurrence prevention for urinary stone patients: an EAU guidelines update","volume":"86","author":"Skolarikos","journal-title":"Eur Urol"},{"issue":"6","key":"R7","doi-asserted-by":"publisher","first-page":"175","DOI":"10.5489\/cuaj.7872","article-title":"UPDATE\u2014Canadian Urological Association guideline: evaluation and medical management of kidney stones","volume":"16","author":"Bhojani","journal-title":"Can Urol Assoc J"},{"issue":"1","key":"R8","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1016\/j.ucl.2012.09.007","article-title":"Metabolic evaluation of first-time and recurrent stone formers","volume":"40","author":"Goldfarb","journal-title":"Urol Clin North Am"},{"issue":"2","key":"R9","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1053\/j.ajkd.2024.02.010","article-title":"24-hour urinary chemistries and kidney stone risk","volume":"84","author":"Ferraro","journal-title":"Am J Kidney Dis"},{"issue":"4","key":"R10","doi-asserted-by":"publisher","first-page":"1084","DOI":"10.1016\/j.juro.2016.10.052","article-title":"The role of the 24-hour urine collection in the prevention of kidney stone recurrence","volume":"197","author":"Hsi","journal-title":"J Urol"},{"issue":"2","key":"R11","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1016\/j.juro.2013.08.080","article-title":"Prevalence of 24-hour urine collection in high risk stone formers","volume":"191","author":"Milose","journal-title":"J Urol"},{"issue":"8","key":"R12","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","article-title":"Large language models in medicine","volume":"29","author":"Thirunavukarasu","journal-title":"Nat Med"},{"key":"R13","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2024.1477898","article-title":"Large language models in patient education: a scoping review of applications in medicine","volume":"11","author":"Aydin","journal-title":"Front Med (Lausanne)"},{"issue":"4","key":"R14","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1001\/jama.2024.21700","article-title":"Testing and evaluation of health care applications of large language models: a systematic review","volume":"333","author":"Bedi","journal-title":"JAMA"},{"issue":"1","key":"R15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.euo.2023.07.017","article-title":"Defining the role of large language models in urologic care and research","volume":"7","author":"Gupta","journal-title":"Eur Urol Oncol"},{"issue":"4","key":"R16","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1097\/JU.0000000000003615","article-title":"Evaluating the effectiveness of artificial intelligence-powered large language models application in disseminating appropriate and readable health information in urology","volume":"210","author":"Davis","journal-title":"J Urol"},{"issue":"4","key":"R17","doi-asserted-by":"publisher","first-page":"750","DOI":"10.1016\/j.eururo.2014.10.029","article-title":"Metabolic evaluation and recurrence prevention for urinary stone patients: EAU guidelines","volume":"67","author":"Skolarikos","journal-title":"Eur Urol"},{"issue":"2","key":"R18","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1016\/j.jcm.2016.02.012","article-title":"A guideline of selecting and reporting intraclass correlation coefficients for reliability research","volume":"15","author":"Koo","journal-title":"J Chiropr Med"},{"issue":"6","key":"R19","doi-asserted-by":"publisher","DOI":"10.3390\/nu13061917","article-title":"Nutrition and kidney stone disease","volume":"13","author":"Siener","journal-title":"Nutrients"},{"issue":"3","key":"R20","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1016\/j.advnut.2023.03.002","article-title":"Kidney stone prevention","volume":"14","author":"Peerapen","journal-title":"Adv Nutr"},{"issue":"5","key":"R21","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1097\/UPJ.0000000000000428","article-title":"Bridging the gap between urological research and patient understanding: the role of large language models in automated generation of layperson's summaries","volume":"10","author":"Eppler","journal-title":"Urol Pract"},{"issue":"11","key":"R22","doi-asserted-by":"publisher","first-page":"2717","DOI":"10.1007\/s11255-023-03729-4","article-title":"The utility of the ChatGPT artificial intelligence tool for patient education and enquiry in robotic radical prostatectomy","volume":"55","author":"Gabriel","journal-title":"Int Urol Nephrol"},{"issue":"1","key":"R23","doi-asserted-by":"publisher","DOI":"10.1007\/s00345-024-05146-3","article-title":"Using artificial intelligence to generate medical literature for urology patients: a comparison of three different large language models","volume":"42","author":"Pompili","journal-title":"World J Urol"},{"issue":"12","key":"R24","doi-asserted-by":"publisher","first-page":"775","DOI":"10.4111\/kju.2014.55.12.775","article-title":"Medical and dietary therapy for kidney stone prevention","volume":"55","author":"Gul","journal-title":"Korean J Urol"},{"issue":"11","key":"R25","first-page":"1234","volume":"84","author":"Frassetto","journal-title":"Am Fam Physician"},{"issue":"2","key":"R26","doi-asserted-by":"publisher","first-page":"105","DOI":"10.4081\/aiua.2015.2.105","article-title":"Dietary treatment of urinary risk factors for renal stone formation. A review of CLU Working Group","volume":"87","author":"Prezioso","journal-title":"Arch Ital Urol Androl"}],"container-title":["Journal of Medical Internet Research"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T20:41:22Z","timestamp":1788554482000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jmir.org\/2026\/1\/e95162"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,4]]},"references-count":26,"URL":"https:\/\/doi.org\/10.2196\/95162","relation":{},"ISSN":["1438-8871"],"issn-type":[{"value":"1438-8871","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,4]]},"article-number":"v28i9e95162"}}