{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,5]],"date-time":"2026-09-05T11:13:05Z","timestamp":1788606785530,"version":"build-2803163510"},"reference-count":29,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"36","license":[{"start":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T00:00:00Z","timestamp":1788480000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,9,4]]},"abstract":"<jats:sec>\n                    <jats:title\/>\n                    <jats:p>\n                      Fetal magnetic resonance imaging (MRI) plays an important role in evaluating prenatal central nervous system (CNS) abnormalities, but expert interpretation and counseling remain challenging. Large language models (LLMs) may support text-based diagnostic reasoning, yet their performance in fetal CNS MRI has not been well characterized. The study aimed to compare ChatGPT, Gemini, and DeepSeek in text-based diagnostic reasoning for fetal CNS MRI cases. This retrospective single-center study included 85 fetal MRI cases with postnatal diagnostic confirmation. Each case was converted into a standardized text summary containing MRI findings and essential clinical information, without image input. The 3 LLMs generated ranked differential diagnoses, diagnostic reasoning, management recommendations, prognostic counseling points, and clinical cautions. Anonymized outputs were independently evaluated under blinded conditions for principal diagnosis matching, diagnostic accuracy, clinical reasoning quality, clinical suggestion utility, and communication style and safety. DeepSeek achieved the highest principal diagnosis matching rate (66\/85, 77.6%), followed by Gemini (59\/85, 69.4%) and ChatGPT (52\/85, 61.2%). The overall difference was significant (Cochran\u2019s\n                      <jats:italic toggle=\"yes\">Q<\/jats:italic>\n                      \u2005=\u20056.2553,\n                      <jats:italic toggle=\"yes\">P<\/jats:italic>\n                      \u2005=\u2005.0438), although no pairwise comparison remained significant after Holm correction. DeepSeek showed the highest diagnostic accuracy and reasoning quality, whereas Gemini performed best in clinical suggestion utility and communication style and safety. Exploratory correlation analyses suggested model-specific associations among evaluation metrics. LLM performance in fetal CNS MRI text-based reasoning was multidimensional and model-dependent. These findings support further supervised evaluation of LLMs as text-based decision-support tools but do not support autonomous clinical diagnosis or counseling.\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1097\/md.0000000000050485","type":"journal-article","created":{"date-parts":[[2026,9,5]],"date-time":"2026-09-05T11:01:03Z","timestamp":1788606063000},"page":"e50485","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":0,"title":["Comparative evaluation of large language models for text-based diagnostic reasoning in fetal central nervous system MRI"],"prefix":"10.1097","volume":"105","author":[{"given":"Runze","family":"Yu","sequence":"first","affiliation":[{"name":"The Sixth Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang Province, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miao","family":"Peng","sequence":"additional","affiliation":[{"name":"The Sixth Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang Province, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huiying","family":"Li","sequence":"additional","affiliation":[{"name":"Harbin Red Cross Central Hospital, Harbin, Heilongjiang Province, China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simeng","family":"Liu","sequence":"additional","affiliation":[{"name":"The Sixth Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang Province, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tong","family":"Su","sequence":"additional","affiliation":[{"name":"The Sixth Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang Province, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanjie","family":"Guan","sequence":"additional","affiliation":[{"name":"The Sixth Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang Province, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yufeng","family":"Shen","sequence":"additional","affiliation":[{"name":"The Sixth Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang Province, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhui","family":"Deng","sequence":"additional","affiliation":[{"name":"The Sixth Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang Province, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6193-6361","authenticated-orcid":false,"given":"Deli","family":"Zhao","sequence":"additional","affiliation":[{"name":"The Sixth Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang Province, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","reference":[{"key":"R1-20260905","doi-asserted-by":"crossref","first-page":"102873","DOI":"10.1016\/j.eclinm.2024.102873","article-title":"The global, regional, and national patterns of change in the burden of congenital birth defects, 1990\u20132021: an analysis of the Global Burden of Disease Study 2021 and forecast to 2040.","volume":"77","author":"Bai","year":"2024","journal-title":"EClinicalMedicine"},{"key":"R2-20260905","doi-asserted-by":"crossref","first-page":"662","DOI":"10.1002\/pd.4836","article-title":"Prenatal counselling for congenital anomalies: a systematic review.","volume":"36","author":"Marokakis","year":"2016","journal-title":"Prenat Diagn"},{"key":"R3-20260905","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1002\/uog.26129","article-title":"ISUOG Practice Guidelines (updated): performance of fetal magnetic resonance imaging.","volume":"61","author":"Prayer","year":"2023","journal-title":"Ultrasound Obstet Gynecol"},{"key":"R4-20260905","doi-asserted-by":"crossref","first-page":"388","DOI":"10.1002\/uog.13429","article-title":"Additional value of fetal magnetic resonance imaging in the prenatal diagnosis of central nervous system anomalies: a systematic review of the literature.","volume":"44","author":"Rossi","year":"2014","journal-title":"Ultrasound Obstet Gynecol"},{"key":"R5-20260905","doi-asserted-by":"crossref","first-page":"101525","DOI":"10.1016\/j.siny.2024.101525","article-title":"Fetal neuroimaging applications for diagnosis and counseling of brain anomalies: current practice and future diagnostic strategies.","volume":"29","author":"Tarui","year":"2024","journal-title":"Semin Fetal Neonatal Med"},{"key":"R6-20260905","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1002\/pd.5579","article-title":"Fetal MRI for dummies: what the fetal medicine specialist should know about acquisitions and sequences.","volume":"40","author":"Aertsen","year":"2020","journal-title":"Prenat Diagn"},{"key":"R7-20260905","doi-asserted-by":"crossref","first-page":"1675","DOI":"10.1016\/j.jacr.2021.07.026","article-title":"Pediatric radiologist workforce shortage: action steps to resolve.","volume":"18","author":"Farmakis","year":"2021","journal-title":"J Am Coll Radiol"},{"key":"R8-20260905","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1007\/s00247-023-05630-9","article-title":"A \u201cglobal village\u201d: promoting research and careers in the pediatric radiology community through diversity.","volume":"54","author":"Andronikou","year":"2024","journal-title":"Pediatr Radiol"},{"key":"R9-20260905","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":"R10-20260905","doi-asserted-by":"crossref","first-page":"100287","DOI":"10.1016\/j.ibmed.2025.100287","article-title":"Large language models in radiology reporting: a systematic review of performance, limitations, and clinical implications.","volume":"12","author":"Artsi","year":"2025","journal-title":"Intell Based Med"},{"key":"R11-20260905","doi-asserted-by":"crossref","first-page":"e232346","DOI":"10.1148\/radiol.232346","article-title":"Testing the ability and limitations of ChatGPT to generate differential diagnoses from transcribed radiologic findings.","volume":"313","author":"Sun","year":"2024","journal-title":"Radiology"},{"key":"R12-20260905","doi-asserted-by":"crossref","first-page":"728","DOI":"10.1067\/j.cpradiol.2024.07.007","article-title":"ChatGPT and assistive AI in structured radiology reporting: a systematic review.","volume":"53","author":"Sacoransky","year":"2024","journal-title":"Curr Probl Diagn Radiol"},{"key":"R13-20260905","first-page":"20211205","article-title":"Artificial intelligence applied to fetal MRI: a scoping review of current research.","volume":"96","author":"Meshaka","year":"2023","journal-title":"Br J Radiol"},{"key":"R17-20260905","doi-asserted-by":"crossref","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","year":"2025","journal-title":"JAMA"},{"key":"R18-20260905","doi-asserted-by":"crossref","first-page":"1616145","DOI":"10.3389\/frai.2025.1616145","article-title":"Medical reasoning in LLMs: an in-depth analysis of DeepSeek R1.","volume":"8","author":"Moell","year":"2025","journal-title":"Front Artif Intell"},{"key":"R19-20260905","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1038\/s41746-024-01010-1","article-title":"Diagnostic reasoning prompts reveal the potential for large language model interpretability in medicine.","volume":"7","author":"Savage","year":"2024","journal-title":"NPJ Digit Med"},{"key":"R20-20260905","doi-asserted-by":"crossref","first-page":"1659134","DOI":"10.3389\/fdgth.2025.1659134","article-title":"Large language models in real-world clinical workflows: a systematic review of applications and implementation.","volume":"7","author":"Artsi","year":"2025","journal-title":"Front Digit Health"},{"key":"R21-20260905","doi-asserted-by":"crossref","first-page":"e240528","DOI":"10.1148\/radiol.240528","article-title":"Best practices for large language models in radiology.","volume":"315","author":"Bluethgen","year":"2025","journal-title":"Radiology"},{"key":"R22-20260905","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1038\/s41746-026-02382-2","article-title":"Human-large language model collaboration in clinical medicine: a systematic review and meta-analysis.","volume":"9","author":"Wang","year":"2026","journal-title":"NPJ Digit Med"},{"key":"R23-20260905","doi-asserted-by":"crossref","first-page":"eaec8352","DOI":"10.1126\/science.aec8352","article-title":"Sycophantic AI decreases prosocial intentions and promotes dependence.","volume":"391","author":"Cheng","year":"2026","journal-title":"Science"},{"key":"R24-20260905","doi-asserted-by":"crossref","first-page":"1927","DOI":"10.1007\/s00247-025-06317-z","article-title":"Accuracy of large language models in generating differential diagnosis from clinical presentation and imaging findings in pediatric cases.","volume":"55","author":"Jung","year":"2025","journal-title":"Pediatr Radiol"},{"key":"R25-20260905","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1093\/jamia\/ocae254","article-title":"Large language model uncertainty proxies: discrimination and calibration for medical diagnosis and treatment.","volume":"32","author":"Savage","year":"2025","journal-title":"J Am Med Inform Assoc"},{"key":"R26-20260905","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1038\/s41746-026-02380-4","article-title":"Evaluation of large language models for diagnostic impression generation from brain MRI report findings: a multicenter benchmark and reader study.","volume":"9","author":"Wang","year":"2026","journal-title":"NPJ Digit Med"},{"key":"R28-20260905","doi-asserted-by":"crossref","first-page":"e2440969","DOI":"10.1001\/jamanetworkopen.2024.40969","article-title":"Large language model influence on diagnostic reasoning: a randomized clinical trial.","volume":"7","author":"Goh","year":"2024","journal-title":"JAMA Netw Open"},{"key":"R29-20260905","doi-asserted-by":"crossref","first-page":"e241516","DOI":"10.1148\/radiol.241516","article-title":"Best practices for the safe use of large language models and other generative AI in radiology.","volume":"316","author":"Yi","year":"2025","journal-title":"Radiology"},{"key":"R30-20260905","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1038\/s41746-026-02428-5","article-title":"Large language models provide unsafe answers to patient-posed medical questions.","volume":"9","author":"Draelos","year":"2026","journal-title":"NPJ Digit Med"},{"key":"R31-20260905","doi-asserted-by":"crossref","first-page":"943","DOI":"10.1038\/s41591-024-03423-7","article-title":"Toward expert-level medical question answering with large language models.","volume":"31","author":"Singhal","year":"2025","journal-title":"Nat Med"},{"key":"R32-20260905","doi-asserted-by":"crossref","first-page":"e240300","DOI":"10.1148\/ryai.240300","article-title":"Checklist for Artificial Intelligence in Medical Imaging (CLAIM): 2024 update.","volume":"6","author":"Tejani","year":"2024","journal-title":"Radiol Artif Intell"},{"key":"R33-20260905","doi-asserted-by":"crossref","first-page":"924","DOI":"10.1038\/s41591-022-01772-9","article-title":"Reporting guideline for the early-stage clinical evaluation of decision support systems driven by artificial intelligence: DECIDE-AI.","volume":"28","author":"Vasey","year":"2022","journal-title":"Nat Med"}],"container-title":["Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.ovid.com\/10.1097\/MD.0000000000050485","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,5]],"date-time":"2026-09-05T11:01:07Z","timestamp":1788606067000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ovid.com\/10.1097\/MD.0000000000050485"}},"subtitle":["A retrospective single-center diagnostic accuracy study"],"short-title":[],"issued":{"date-parts":[[2026,9,4]]},"references-count":29,"journal-issue":{"issue":"36","published-print":{"date-parts":[[2026]]}},"URL":"https:\/\/doi.org\/10.1097\/md.0000000000050485","relation":{},"ISSN":["0025-7974","1536-5964"],"issn-type":[{"value":"0025-7974","type":"print"},{"value":"1536-5964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,4]]},"assertion":[{"value":"2026-07-02","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-17","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}