{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T21:06:46Z","timestamp":1788988006598,"version":"build-2803163510"},"reference-count":131,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Med Internet Res"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec sec-type=\"background\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Systems based on large language models (LLMs), multimodal LLMs, and vision-language foundation models are increasingly being evaluated for medical report generation in imaging and related clinical workflows. Existing reviews have summarized technical architectures, radiology applications, readability, and benchmark performance, but clinical readiness remains uncertain because safety, human oversight, and workflow outcomes are sparsely and inconsistently reported.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"objective\">\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>The aim of this study is to assess the effectiveness (expert acceptance and blinded preference), safety (clinically significant, omission, and commission errors), and workflow burden (reporting time, corrections, edit distance, and editing burden) of LLM-based medical report generation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"methods\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We searched PubMed\/MEDLINE, Embase, Web of Science Core Collection, Scopus, and the Cochrane Library for studies published from January 1, 2016, through May 15, 2026. Eligible studies evaluated LLMs, multimodal LLMs, or vision-language foundation models for image-to-report generation, impression generation from findings, report drafting, or structured reporting in imaging workflows. Two reviewers performed screening, extraction, risk-of-bias assessment, and Grading of Recommendations Assessment, Development, and Evaluation\u2013informed narrative certainty assessment. Outcomes were clinically significant error rate, omission error rate, commission error rate, reporting time, edit burden, expert acceptance, and blinded expert preference. Meta-analysis was not performed because no comparable outcome had at least 2 studies with compatible task structure and analyzable data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"results\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>A total of 101 studies were included. Chest x-ray was the largest modality group (36 studies), followed by computed tomography, magnetic resonance imaging (MRI), ultrasound, endoscopy, pathology, ophthalmic, electrocardiographic, dental, and mixed-modality contexts. No study was judged at low risk of bias; 15 were moderate, 72 high, and 14 serious. Safety and workflow evidence remained heterogeneous and largely nonpoolable. In a chest x-ray study, AI report acceptance was similar to that of radiologist reports (6047\/8580, 70.5% vs 6288\/8580, 73.3%), but false-negative findings were slightly higher (1584\/8580, 18.5% vs 1527\/8580, 17.8%). In a clinician-collaboration chest x-ray study, AI reports were equivalent or preferred in 233 of 300 (77.7%) and 170 of 303 (56.1%) cases across 2 datasets; yet, clinically significant errors persisted. In a brain MRI study, AI assistance reduced reading time from 61 to 53 seconds, whereas impression drafting increased editing time and edit distance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"conclusions\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This review shifts the synthesis from plausible report generation to clinically interpretable effectiveness, safety, and workflow effects. Expert acceptance and preference suggested assistive value in selected supervised settings, but these signals were limited by inconsistent reporting of clinically significant errors, omissions, commissions, and failed generations. Workflow effects were mixed, with some studies reporting shorter reading time or drafting support, and others reporting greater editing time or edit distance. The evidence remains too heterogeneous, biased, and sparse on case-level end points to support a pooled meta-analysis or autonomous clinical-readiness claims. Adoption should remain locally validated, clinician-supervised, and accompanied by standardized reporting of acceptance, preference, omissions, commissions, failed generations, reporting time, corrections, and editing burden.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/97007","type":"journal-article","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T20:11:57Z","timestamp":1788984717000},"page":"e97007-e97007","source":"Crossref","is-referenced-by-count":0,"title":["Effectiveness, Safety, and Workflow Burden of Large Language Model\u2013Based Medical Report Generation: Systematic Review"],"prefix":"10.2196","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7514-1885","authenticated-orcid":false,"given":"Jie-Lin","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0049-7813","authenticated-orcid":false,"given":"Ji-Qing","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4800-2369","authenticated-orcid":false,"given":"Xiao-Guang","family":"Ni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"issue":"11","key":"R1","doi-asserted-by":"publisher","first-page":"753","DOI":"10.7326\/M16-0961","article-title":"Allocation of physician time in ambulatory practice: a time and motion study in 4 specialties","volume":"165","author":"Sinsky","journal-title":"Ann Intern Med"},{"key":"R2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1240","article-title":"On the automatic generation of medical imaging reports","author":"Jing","journal-title":"Proc Assoc Comput Linguist Annu Meet"},{"key":"R3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.112","article-title":"Generating radiology reports via memory-driven transformer","author":"Chen","journal-title":"Proc Conf Empir Methods Nat Lang Process"},{"issue":"3","key":"R4","doi-asserted-by":"publisher","first-page":"1050","DOI":"10.1109\/TBME.2025.3597325","article-title":"ChatRadio-Valuer: a chat large language model for generalizable radiology impression generation on multi-institution and multi-system data","volume":"73","author":"Zhong","journal-title":"IEEE Trans Biomed Eng"},{"issue":"23","key":"R5","doi-asserted-by":"publisher","DOI":"10.3390\/jcm13237092","article-title":"Auto-Rad: end-to-end report generation from lumber spine MRI using vision-language model","volume":"13","author":"Yeasin","journal-title":"J Clin Med"},{"issue":"23","key":"R6","doi-asserted-by":"publisher","DOI":"10.3390\/jcm13237057","article-title":"Comparative analysis of M4CXR, an LLM-based chest X-ray report generation model, and ChatGPT in radiological interpretation","volume":"13","author":"Lee","journal-title":"J Clin Med"},{"issue":"8","key":"R7","doi-asserted-by":"publisher","first-page":"3139","DOI":"10.1109\/TMI.2025.3559923","article-title":"Large language model with region-guided referring and grounding for CT report generation","volume":"44","author":"Chen","journal-title":"IEEE Trans Med Imaging"},{"issue":"3","key":"R8","doi-asserted-by":"publisher","DOI":"10.1111\/den.70134","article-title":"Large language model-driven analysis and report generation of endoscopy videos-A pilot study","volume":"38","author":"Massimi","journal-title":"Dig Endosc"},{"key":"R9","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2026.109737","article-title":"A fine-tuning multimodal large language model for endoscopic report generation","volume":"118","author":"Zhang","journal-title":"Biomed Signal Process Control"},{"key":"R10","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2026.109466","article-title":"A multi-modal fusion-based deep learning with finetuned LLaMA 3 for lung disease diagnosis using PACS radiology reports","volume":"117","author":"Joyson","journal-title":"Biomed Signal Process Control"},{"issue":"4","key":"R11","doi-asserted-by":"publisher","DOI":"10.1016\/j.xcrm.2025.102056","article-title":"MetaGP: a generative foundation model integrating electronic health records and multimodal imaging for addressing unmet clinical needs","volume":"6","author":"Liu","journal-title":"Cell Rep Med"},{"issue":"2","key":"R12","doi-asserted-by":"publisher","first-page":"39","DOI":"10.3390\/asi8020039","article-title":"Multimodal AI and large language models for orthopantomography radiology report generation and Q&A","volume":"8","author":"Dasanayaka","journal-title":"Appl Syst Innov"},{"issue":"1","key":"R13","doi-asserted-by":"publisher","DOI":"10.1080\/08839514.2026.2626117","article-title":"SPINE: segmentation-guided processing and integration of multimodal spinal MRI for natural-language enhanced report generation","volume":"40","author":"Helmy","journal-title":"Appl Artif Intell"},{"key":"R14","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.128555","article-title":"Ultrasound report generation with fuzzy knowledge and multi-modal large language model","volume":"292","author":"Li","journal-title":"Expert Syst Appl"},{"issue":"3","key":"R15","doi-asserted-by":"publisher","first-page":"100033","DOI":"10.1016\/j.metrad.2023.100033","article-title":"R2GenGPT: radiology report generation with frozen LLMs","volume":"1","author":"Wang","journal-title":"Meta-Radiology"},{"issue":"4","key":"R16","doi-asserted-by":"publisher","first-page":"100099","DOI":"10.1016\/j.metrad.2024.100099","article-title":"A systematic evaluation of GPT-4V\u2019s multimodal capability for chest X-ray image analysis","volume":"2","author":"Liu","journal-title":"Meta-Radiology"},{"key":"R17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3588121","article-title":"Enhancing structured pathology report generation with foundation model and modular design","volume":"13","author":"Kim","journal-title":"IEEE Access"},{"issue":"4","key":"R18","doi-asserted-by":"publisher","first-page":"568","DOI":"10.12720\/jait.16.4.568-581","article-title":"Multimodal medical image analysis: integrating LLM and RAG deep learning strategies","volume":"16","author":"Yan","journal-title":"J Adv Inf Technol"},{"issue":"2","key":"R19","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1093\/jamia\/ocw105","article-title":"Automation bias and verification complexity: a systematic review","volume":"24","author":"Lyell","journal-title":"J Am Med Inform Assoc"},{"issue":"3","key":"R20","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1136\/bmjqs-2018-008370","article-title":"Artificial intelligence, bias and clinical safety","volume":"28","author":"Challen","journal-title":"BMJ Qual Saf"},{"issue":"13","key":"R21","doi-asserted-by":"publisher","first-page":"1233","DOI":"10.1056\/NEJMsr2214184","article-title":"Benefits, limits, and risks of GPT-4 as an AI chatbot for medicine","volume":"388","author":"Lee","journal-title":"N Engl J Med"},{"issue":"12","key":"R22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3571730","article-title":"Survey of hallucination in natural language generation","volume":"55","author":"Ji","journal-title":"ACM Comput Surv"},{"issue":"3","key":"R23","doi-asserted-by":"publisher","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","journal-title":"Radiology"},{"issue":"1","key":"R24","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.243378","article-title":"Drafting the future: the dawn of AI report generation in radiology","volume":"316","author":"Seah","journal-title":"Radiology"},{"issue":"4","key":"R25","doi-asserted-by":"publisher","DOI":"10.1148\/rg.240073","article-title":"Optimizing large language models in radiology and mitigating pitfalls: prompt engineering and fine-tuning","volume":"45","author":"Kim","journal-title":"Radiographics"},{"issue":"4","key":"R26","doi-asserted-by":"publisher","first-page":"937","DOI":"10.1007\/s12194-025-00968-1","article-title":"Generative AI and foundation models in medical image","volume":"18","author":"Oda","journal-title":"Radiol Phys Technol"},{"issue":"4","key":"R27","doi-asserted-by":"publisher","first-page":"773","DOI":"10.1016\/j.gtc.2024.08.005","article-title":"Artificial intelligence in gastrointestinal endoscopy","volume":"53","author":"Labaki","journal-title":"Gastroenterol Clin North Am"},{"issue":"1","key":"R28","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1007\/s42058-023-00132-x","article-title":"Can ChatGPT write radiology reports?","volume":"7","author":"Biswas","journal-title":"Chin J Acad Radiol"},{"key":"R29","doi-asserted-by":"publisher","DOI":"10.1109\/RBME.2024.3408456","article-title":"Automated radiology report generation: a review of recent advances","volume":"18","author":"Sloan","journal-title":"IEEE Rev Biomed Eng"},{"issue":"5","key":"R30","doi-asserted-by":"publisher","first-page":"2589","DOI":"10.1007\/s00330-024-11107-6","article-title":"Large language models for structured reporting in radiology: past, present, and future","volume":"35","author":"Busch","journal-title":"Eur Radiol"},{"key":"R31","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2025.103220","article-title":"Medical radiology report generation: a systematic review of current deep learning methods, trends, and future directions","volume":"168","author":"Izhar","journal-title":"Artif Intell Med"},{"issue":"3","key":"R32","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1016\/j.jacr.2025.10.005","article-title":"Use of large language models on radiology reports: a scoping review","volume":"23","author":"Lee","journal-title":"J Am Coll Radiol"},{"issue":"3","key":"R33","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1016\/j.jacr.2025.09.004","article-title":"Leveraging large language models to enhance radiology report readability: a systematic review","volume":"23","author":"Patwardhan","journal-title":"J Am Coll Radiol"},{"key":"R34","doi-asserted-by":"publisher","DOI":"10.2196\/78041","article-title":"Trends and trajectories in the rise of large language models in radiology: scoping review","volume":"13","author":"Al Zaabi","journal-title":"JMIR Med Inform"},{"key":"R35","doi-asserted-by":"crossref","unstructured":"Papineni K Roukos S Ward T Zhu WJ . BLEU: a method for automatic evaluation of machine translation. In: Isabelle P Charniak E Lin D , editors. Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics; 2002:311-318. [doi: 10.3115\/1073083.1073135]","DOI":"10.3115\/1073083.1073135"},{"key":"R36","unstructured":"Lin CY . ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out: Proceedings of the ACL-04 Workshop. Association for Computational Linguistics; 2004:74-81. URL: https:\/\/aclanthology.org\/W04-1013\/ [Accessed 01-08-2026]"},{"key":"R37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087","article-title":"CIDEr: consensus-based image description evaluation","author":"Vedantam","journal-title":"Proc IEEE Comput Vis Pattern Recognit Conf (CVPR)"},{"key":"R38","unstructured":"Zhang T Kishore V Wu F Weinberger KQ Artzi Y . BERTScore: evaluating text generation with BERT. Presented at: International Conference on Learning Representations; Apr 26-30, 2020; Addis Ababa, Ethiopia. 2020.URL: https:\/\/openreview.net\/pdf?id=SkeHuCVFDr [Accessed 01-08-2026]"},{"key":"R39","doi-asserted-by":"publisher","DOI":"10.1016\/j.mlwa.2026.100851","article-title":"Trust but verify: image-aware evaluation of radiology report generators","volume":"23","author":"Gholipour Picha","journal-title":"Mach Learn Appl"},{"key":"R40","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.n71","article-title":"The PRISMA 2020 statement: an updated guideline for reporting systematic reviews","volume":"372","author":"Page","journal-title":"BMJ"},{"issue":"1","key":"R41","doi-asserted-by":"publisher","DOI":"10.1186\/s13643-020-01542-z","article-title":"PRISMA-S: an extension to the PRISMA statement for reporting literature searches in systematic reviews","volume":"10","author":"Rethlefsen","journal-title":"Syst Rev"},{"key":"R42","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.l6890","article-title":"Synthesis without meta-analysis (SWiM) in systematic reviews: reporting guideline","volume":"368","author":"Campbell","journal-title":"BMJ"},{"key":"R43","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.i4919","article-title":"ROBINS-I: a tool for assessing risk of bias in non-randomised studies of interventions","volume":"355","author":"Sterne","journal-title":"BMJ"},{"issue":"4","key":"R44","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.240300","article-title":"Checklist for artificial intelligence in medical imaging (CLAIM): 2024 update","volume":"6","author":"Tejani","journal-title":"Radiol Artif Intell"},{"issue":"7650","key":"R45","doi-asserted-by":"publisher","first-page":"924","DOI":"10.1136\/bmj.39489.470347.AD","article-title":"GRADE: an emerging consensus on rating quality of evidence and strength of recommendations","volume":"336","author":"Guyatt","journal-title":"BMJ"},{"issue":"2","key":"R46","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1109\/TMI.2025.3603416","article-title":"Activating associative disease-aware vision token memory for LLM-based X-ray report generation","volume":"45","author":"Wang","journal-title":"IEEE Trans Med Imaging"},{"issue":"1","key":"R47","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-34799-2","article-title":"Hybrid framework for lesion-aware, clinically coherent chest X-ray report generation using contrastive learning and large language models","volume":"16","author":"Noh","journal-title":"Sci Rep"},{"key":"R48","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.130082","article-title":"Dynamic feature fusion guiding and multimodal large language model refining for medical image report generation","volume":"299","author":"Han","journal-title":"Expert Syst Appl"},{"issue":"2","key":"R49","doi-asserted-by":"publisher","first-page":"393","DOI":"10.26599\/BDMA.2025.9020037","article-title":"Semantic feedback-based RAG for radiology report generation","volume":"9","author":"Jia","journal-title":"Big Data Min Anal"},{"key":"R50","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2026.3669539","article-title":"R2GenCSR: mining contextual and residual information for LLM-based radiology report generation","volume":"2026","author":"Wang","journal-title":"IEEE J Biomed Health Inform"},{"issue":"3","key":"R51","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.241476","article-title":"Diagnostic accuracy and clinical value of a domain-specific multimodal generative AI model for chest radiograph report generation","volume":"314","author":"Hong","journal-title":"Radiology"},{"issue":"2","key":"R52","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1038\/s41591-024-03302-1","article-title":"Collaboration between clinicians and vision-language models in radiology report generation","volume":"31","author":"Tanno","journal-title":"Nat Med"},{"issue":"1","key":"R53","doi-asserted-by":"publisher","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","journal-title":"NPJ Digit Med"},{"issue":"1","key":"R54","doi-asserted-by":"publisher","DOI":"10.1186\/s12880-024-01435-w","article-title":"An open-source fine-tuned large language model for radiological impression generation: a multi-reader performance study","volume":"24","author":"Serapio","journal-title":"BMC Med Imaging"},{"issue":"1","key":"R55","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-57426-0","article-title":"Towards a holistic framework for multimodal LLM in 3D brain CT radiology report generation","volume":"16","author":"Li","journal-title":"Nat Commun"},{"issue":"1","key":"R56","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-026-06692-8","article-title":"Towards automated reporting: a bronchoscopy report dataset for enhancing multimodality large language models","volume":"13","author":"Luo","journal-title":"Sci Data"},{"issue":"5","key":"R57","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1109\/MCE.2024.3522521","article-title":"MedVLM: medical vision\u2013language model for consumer devices","volume":"14","author":"Ayaz","journal-title":"IEEE Consum Electron Mag"},{"issue":"3","key":"R58","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.250714","article-title":"Fine-tuned large language model for automated radiology impression generation: a multicenter evaluation","volume":"8","author":"Li","journal-title":"Radiol Artif Intell"},{"issue":"8","key":"R59","doi-asserted-by":"publisher","first-page":"6282","DOI":"10.1007\/s00330-026-12524-5","article-title":"Reporting efficiency in diagnostic imaging: can plug-and-play general-purpose large language models outperform conventional speech recognition?","volume":"36","author":"de Margerie-Mellon","journal-title":"Eur Radiol"},{"issue":"1","key":"R60","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1038\/s41746-026-02569-7","article-title":"Domain specific multimodal large language model for automated endoscopy reporting with multicenter prospective validation","volume":"9","author":"Jiang","journal-title":"NPJ Digit Med"},{"key":"R61","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-026-01989-x","article-title":"Evaluating large language models for Turkish emergency CT impression drafting: quality, critical omissions, and readability","author":"Tekdemir","journal-title":"J Imaging Inform Med"},{"issue":"1","key":"R62","doi-asserted-by":"publisher","DOI":"10.1186\/s13244-026-02285-6","article-title":"Comparative evaluation of large language models for generating CAD-RADS 2.0-compliant diagnostic conclusions in cardiac CT reports","volume":"17","author":"Lorusso","journal-title":"Insights Imaging"},{"issue":"1","key":"R63","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-01889-4","article-title":"Keyword-based AI assistance in the generation of radiology reports: a pilot study","volume":"8","author":"Dong","journal-title":"NPJ Digit Med"},{"issue":"1","key":"R64","doi-asserted-by":"publisher","DOI":"10.1186\/s13244-026-02292-7","article-title":"Enhancing radiology workflows through collaborative AI-assisted chest X-ray reporting using large vision-language models: a proof-of-concept study","volume":"17","author":"Pellegrini","journal-title":"Insights Imaging"},{"key":"R65","doi-asserted-by":"publisher","DOI":"10.1007\/s00261-026-05524-y","article-title":"Large language model\u2013assisted radiology reporting in a single-radiologist implementation: a retrospective cohort study interpreted through a UTAUT lens","author":"Tan","journal-title":"Abdom Radiol"},{"issue":"1","key":"R66","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1007\/s40846-024-00849-9","article-title":"Enhancing diagnostic accuracy and efficiency with GPT-4-generated structured reports: a comprehensive study","volume":"44","author":"Wang","journal-title":"J Med Biol Eng"},{"issue":"2","key":"R67","doi-asserted-by":"publisher","DOI":"10.2214\/AJR.25.33704","article-title":"Temperature setting of a multimodal generative artificial intelligence model: association with accuracy and quality of artificial intelligence-generated chest radiograph reports","volume":"226","author":"Hong","journal-title":"AJR Am J Roentgenol"},{"issue":"1","key":"R68","doi-asserted-by":"publisher","DOI":"10.1186\/s41747-026-00682-6","article-title":"Can AI write reports like a radiologist? A blinded evaluation of large language model-generated lumbar spine MRI reports","volume":"10","author":"Zanardo","journal-title":"Eur Radiol Exp"},{"issue":"1","key":"R69","doi-asserted-by":"publisher","DOI":"10.1186\/s13244-025-01976-w","article-title":"Large language models for efficient whole-organ MRI score-based reports and categorization in knee osteoarthritis","volume":"16","author":"Xie","journal-title":"Insights Imaging"},{"issue":"4","key":"R70","doi-asserted-by":"publisher","first-page":"2018","DOI":"10.1007\/s00330-024-11074-y","article-title":"Automatic structuring of radiology reports with on-premise open-source large language models","volume":"35","author":"Wo\u017anicki","journal-title":"Eur Radiol"},{"issue":"1","key":"R71","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-01759-z","article-title":"Generative artificial intelligence for fundus fluorescein angiography interpretation and human expert evaluation","volume":"8","author":"Shao","journal-title":"NPJ Digit Med"},{"issue":"10","key":"R72","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering11101043","article-title":"GPT-driven radiology report generation with fine-tuned Llama 3","volume":"11","author":"Voinea","journal-title":"Bioengineering (Basel)"},{"key":"R73","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2026.112695","article-title":"Prospective evaluation of artificial intelligence (AI) in lumbar spine magnetic resonance imaging (MRI) workflow: from deep learning (DL)\u2013enhanced accelerated acquisition to simultaneous vision language model (VLM)\u2013based automated report generation","volume":"196","author":"Park","journal-title":"Eur J Radiol"},{"issue":"12","key":"R74","doi-asserted-by":"publisher","first-page":"4823","DOI":"10.1016\/j.acra.2024.07.020","article-title":"Practical evaluation of ChatGPT performance for radiology report generation","volume":"31","author":"Soleimani","journal-title":"Acad Radiol"},{"key":"R75","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2026.1679203","article-title":"Semiautomated breast ultrasound report generation using multimodal large language models and deep learning","volume":"13","author":"Azhar","journal-title":"Front Med (Lausanne)"},{"issue":"2","key":"R76","doi-asserted-by":"publisher","first-page":"624","DOI":"10.1016\/j.acra.2024.08.052","article-title":"The potential of Gemini and GPTs for structured report generation based on free-text F-FDG PET\/CT breast cancer reports","volume":"32","author":"Chen","journal-title":"Acad Radiol"},{"issue":"1","key":"R77","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-69981-5","article-title":"Multi-modal transformer architecture for medical image analysis and automated report generation","volume":"14","author":"Raminedi","journal-title":"Sci Rep"},{"key":"R78","doi-asserted-by":"publisher","DOI":"10.3389\/fnume.2026.1723650","article-title":"Conceptual proposal for LLM-generated FDG PET\/CT follow-up reports in melanoma: a pilot study on model stability and blinded expert evaluation","volume":"6","author":"Bosbach","journal-title":"Front Nucl Med"},{"issue":"1","key":"R79","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-60014-x","article-title":"Generating dermatopathology reports from gigapixel whole slide images with HistoGPT","volume":"16","author":"Tran","journal-title":"Nat Commun"},{"key":"R80","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2026.3689568","article-title":"SpineVLM: a markdown-guided structured fine-tuning framework for spine X-ray report generation","author":"Liu","journal-title":"IEEE J Biomed Health Inform"},{"issue":"4","key":"R81","doi-asserted-by":"publisher","first-page":"1509","DOI":"10.1007\/s40123-026-01352-x","article-title":"Report generation system for slit-lamp image interpretation using vision-language models","volume":"15","author":"Ye","journal-title":"Ophthalmol Ther"},{"key":"R82","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2026.110173","article-title":"Enhancing chest X-ray report generation with pathology-guided prompts and vision-language shortcut bias mitigation","volume":"120","author":"Barzegar","journal-title":"Biomed Signal Process Control"},{"issue":"1","key":"R83","doi-asserted-by":"publisher","first-page":"55","DOI":"10.2478\/jaiscr-2026-0003","article-title":"Chestxgen: dynamic memory\u2013augmented vision-language transformer with context-aware gating for radiology report generation","volume":"16","author":"Allaberdiev","journal-title":"J Artif Intell Soft Comput Res"},{"key":"R84","doi-asserted-by":"publisher","DOI":"10.2196\/90814","article-title":"Automatic speech recognition and large language models for multilingual pathology report generation: proof-of-concept study","volume":"10","author":"Lin","journal-title":"JMIR Form Res"},{"issue":"2","key":"R85","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging12020068","article-title":"Automated radiological report generation from breast ultrasound images using vision and language transformers","volume":"12","author":"Khatoon","journal-title":"J Imaging"},{"issue":"1","key":"R86","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-026-02581-x","article-title":"A robust vision language model for molecular status prediction and radiology report generation in adult-type diffuse gliomas","volume":"9","author":"Park","journal-title":"NPJ Digit Med"},{"key":"R87","doi-asserted-by":"publisher","DOI":"10.1007\/s44174-025-00538-4","article-title":"Privacy-preserving chest X-ray report generation via multimodal federated learning with ViT and GPT2","author":"Hossain","journal-title":"Biomed Mater Devices"},{"issue":"1","key":"R88","doi-asserted-by":"publisher","DOI":"10.1093\/bjrai\/ubaf011","article-title":"M3: multimodal artificial intelligence for medical report generation and visual question answering from 3D abdominal CT scans","volume":"2","author":"Hosseini","journal-title":"BJR Artif Intell"},{"issue":"3","key":"R89","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.240885","article-title":"Constructing a large language model to generate impressions from findings in radiology reports","volume":"312","author":"Zhang","journal-title":"Radiology"},{"issue":"5","key":"R90","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.231259","article-title":"Evaluating GPT-4 on impressions generation in radiology reports","volume":"307","author":"Sun","journal-title":"Radiology"},{"issue":"10","key":"R91","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2023.36100","article-title":"Generative artificial intelligence for chest radiograph interpretation in the emergency department","volume":"6","author":"Huang","journal-title":"JAMA Netw Open"},{"issue":"2","key":"R92","doi-asserted-by":"publisher","first-page":"2096","DOI":"10.21037\/qims-23-1300","article-title":"ChatGPT in radiology structured reporting: analysis of ChatGPT-3.5 Turbo and GPT-4 in reducing word count and recalling findings","volume":"14","author":"Mallio","journal-title":"Quant Imaging Med Surg"},{"key":"R93","doi-asserted-by":"publisher","DOI":"10.2196\/60684","article-title":"AI in dental radiology improving the efficiency of reporting with ChatGPT: comparative study","volume":"26","author":"Stephan","journal-title":"J Med Internet Res"},{"issue":"4","key":"R94","doi-asserted-by":"publisher","first-page":"416","DOI":"10.4258\/hir.2025.31.4.416","article-title":"Utility of multimodal large language models in analyzing chest X-rays with incomplete contextual information","volume":"31","author":"Kim","journal-title":"Healthc Inform Res"},{"issue":"6","key":"R95","doi-asserted-by":"publisher","DOI":"10.3390\/tomography11060069","article-title":"Structured transformation of unstructured prostate MRI reports using large language models","volume":"11","author":"Di Palma","journal-title":"Tomography"},{"issue":"1","key":"R96","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1055\/s-0044-1788589","article-title":"Enhancing radiological reporting in head and neck cancer: converting free-text CT scan reports to structured reports using large language models","volume":"35","author":"Gupta","journal-title":"Indian J Radiol Imaging"},{"issue":"7","key":"R97","doi-asserted-by":"publisher","first-page":"4374","DOI":"10.1007\/s00330-024-11339-6","article-title":"CXR-LLaVA: a multimodal large language model for interpreting chest X-ray images","volume":"35","author":"Lee","journal-title":"Eur Radiol"},{"issue":"1","key":"R98","doi-asserted-by":"publisher","DOI":"10.1007\/s12672-025-02005-4","article-title":"A preliminary investigation into the potential, pitfalls, and limitations of large language models for mammography interpretation","volume":"16","author":"Pesapane","journal-title":"Discov Oncol"},{"issue":"1","key":"R99","doi-asserted-by":"publisher","first-page":"1005","DOI":"10.1007\/s10278-025-01510-w","article-title":"Improving radiology report conciseness and structure via local large language models","volume":"39","author":"Hartsock","journal-title":"J Imaging Inform Med"},{"issue":"4","key":"R100","doi-asserted-by":"publisher","first-page":"2303","DOI":"10.1007\/s10278-024-01328-y","article-title":"ChatGPT vs Gemini: comparative accuracy and efficiency in CAD-RADS score assignment from radiology reports","volume":"38","author":"Silbergleit","journal-title":"J Imaging Inform Med"},{"issue":"4","key":"R101","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.230725","article-title":"Leveraging GPT-4 for post hoc transformation of free-text radiology reports into structured reporting: a multilingual feasibility study","volume":"307","author":"Adams","journal-title":"Radiology"},{"key":"R102","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2024.111458","article-title":"Transforming free-text radiology reports into structured reports using ChatGPT: a study on thyroid ultrasonography","volume":"175","author":"Jiang","journal-title":"Eur J Radiol"},{"issue":"6","key":"R103","doi-asserted-by":"publisher","first-page":"3566","DOI":"10.1007\/s00330-023-10384-x","article-title":"Evaluating the performance of generative pre-trained transformer-4 (GPT-4) in standardizing radiology reports","volume":"34","author":"Hasani","journal-title":"Eur Radiol"},{"key":"R104","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3588344","article-title":"Medical report generation with knowledge distillation and multi-stage hierarchical attention in vision transformer encoder and GPT-2 decoder","volume":"13","author":"Tsaniya","journal-title":"IEEE Access"},{"key":"R105","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3578462","article-title":"Automated ultrasound diagnosis via CLIP-GPT synergy: a multimodal framework for image classification and report generation","volume":"13","author":"Yan","journal-title":"IEEE Access"},{"issue":"5","key":"R106","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1007\/s11604-024-01721-1","article-title":"Automated MRI pituitary structured reporting from free-text using a fine-tuned Llama model: a feasibility study","volume":"43","author":"L\u00f3pez-\u00dabeda","journal-title":"Jpn J Radiol"},{"issue":"9","key":"R107","doi-asserted-by":"publisher","first-page":"6869","DOI":"10.1109\/JBHI.2025.3569361","article-title":"A medical multimodal large language model for pediatric pneumonia","volume":"29","author":"Tian","journal-title":"IEEE J Biomed Health Inform"},{"key":"R108","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2026.104060","article-title":"Towards generalizable pathology reports via a multimodal LLM with the multicenter in-context learning","volume":"111","author":"Li","journal-title":"Med Image Anal"},{"issue":"1","key":"R109","doi-asserted-by":"publisher","DOI":"10.6018\/edumed.695571","article-title":"Informe radiol\u00f3gico estructurado asistido por modelos de lenguaje en residentes de Radiolog\u00eda: piloto de implementaci\u00f3n en Urgencias [Article in Spanish]","volume":"7","author":"Garc\u00eda Hidalgo","journal-title":"Rev Esp Edu Med"},{"issue":"2","key":"R110","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1016\/j.imed.2025.11.003","article-title":"From radiology findings to artificial intelligence\u2013powered impressions: a retrospective study on the comparative performance of recent large language models","volume":"6","author":"Tasneem","journal-title":"Intell Med"},{"issue":"5","key":"R111","doi-asserted-by":"publisher","first-page":"3676","DOI":"10.1007\/s00330-025-12147-2","article-title":"BI-RADS-compliant structured mammography reporting using locally deployed large language models under privacy constraints","volume":"36","author":"Sheng","journal-title":"Eur Radiol"},{"issue":"1","key":"R112","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-026-02551-3","article-title":"Teaching multimodal LLMs to comprehend 12-lead electrocardiographic images","volume":"9","author":"Liu","journal-title":"NPJ Digit Med"},{"key":"R113","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2026.104077","article-title":"Read like a radiologist: efficient vision-language model for 3D medical imaging interpretation","volume":"111","author":"Lee","journal-title":"Med Image Anal"},{"key":"R114","author":"Alkhaldi","journal-title":"Trans Mach Learn Res"},{"issue":"3","key":"R115","doi-asserted-by":"publisher","DOI":"10.1016\/j.identj.2025.109404","article-title":"MedFusionT5: cross-modal attention boosts semantic quality and reduces hallucinations in dental AI","volume":"76","author":"Abdaoui","journal-title":"Int Dent J"},{"issue":"5","key":"R116","doi-asserted-by":"publisher","first-page":"150107","DOI":"10.1007\/s11432-025-4818-7","article-title":"CT-Agent: a multimodal-LLM agent for 3D CT radiology question answering","volume":"69","author":"Mao","journal-title":"Sci China Inf Sci"},{"issue":"7","key":"R117","doi-asserted-by":"publisher","first-page":"1303","DOI":"10.1093\/jamia\/ocag070","article-title":"The detectability paradox: bilingual medical report generation with open-weight models and the limits of human oversight","volume":"33","author":"Rouhizadeh","journal-title":"J Am Med Inform Assoc"},{"issue":"4","key":"R118","doi-asserted-by":"publisher","first-page":"100103","DOI":"10.1016\/j.metrad.2024.100103","article-title":"Potential of multimodal large language models for data mining of medical images and free-text reports","volume":"2","author":"Zhang","journal-title":"Meta-Radiology"},{"issue":"1","key":"R119","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1067\/j.cpradiol.2023.04.001","article-title":"Ability of ChatGPT to generate competent radiology reports for distal radius fracture by use of RSNA template items and integrated AO classifier","volume":"53","author":"Bosbach","journal-title":"Curr Probl Diagn Radiol"},{"key":"R120","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2025.107562","article-title":"Automated generation of chest X-ray imaging diagnostic reports by multimodal and multi granularity features fusion","volume":"105","author":"Fang","journal-title":"Biomed Signal Process Control"},{"key":"R121","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3606961","article-title":"Chest X-ray report generation using abnormality guided vision language model","volume":"13","author":"Edirisinghe","journal-title":"IEEE Access"},{"key":"R122","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112913","article-title":"Context-enhanced framework for medical image report generation using multimodal contexts","volume":"310","author":"Li","journal-title":"Knowl Based Syst"},{"key":"R123","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.129884","article-title":"DC-RRG: diagnosis-centered cascaded radiology report generation","volume":"299","author":"Lin","journal-title":"Expert Syst Appl"},{"issue":"1","key":"R124","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-025-10404-6","article-title":"Engaging preference optimization alignment in large language model for continual radiology report generation: a hybrid approach","volume":"17","author":"Izhar","journal-title":"Cogn Comput"},{"key":"R125","doi-asserted-by":"publisher","DOI":"10.1007\/s13748-024-00358-5","article-title":"Enhancing radiology report generation through pre-trained language models","author":"Leonardi","journal-title":"Prog Artif Intell"},{"issue":"1","key":"R126","doi-asserted-by":"publisher","first-page":"409","DOI":"10.18280\/ts.420135","article-title":"Generative artificial intelligence for the automated generation of medical reports: a modified poor and rich optimization (MPRO)\u2013based approach","volume":"42","author":"Aslam","journal-title":"Traitement du Signal"},{"key":"R127","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2025.108416","article-title":"Grounded knowledge\u2013enhanced medical vision\u2013language pre-training for chest X-ray","volume":"112","author":"Deng","journal-title":"Biomed Signal Process Control"},{"issue":"4","key":"R128","doi-asserted-by":"publisher","first-page":"100171","DOI":"10.1016\/j.metrad.2025.100171","article-title":"S-RRG-Bench: structured radiology report generation with fine-grained evaluation framework","volume":"3","author":"Li","journal-title":"Meta-Radiology"},{"issue":"14","key":"R129","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics15141805","article-title":"Turkish chest X-ray report generation model using the Swin enhanced yield transformer (Model-SEY) framework","volume":"15","author":"Ucan","journal-title":"Diagnostics (Basel)"},{"issue":"6","key":"R130","doi-asserted-by":"publisher","DOI":"10.1002\/eng2.70220","article-title":"Vision-language models for automated chest X-ray interpretation: leveraging ViT and GPT-2","volume":"7","author":"Rakibul Islam","journal-title":"Eng Rep"},{"issue":"5","key":"R131","doi-asserted-by":"publisher","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","journal-title":"Nat Med"}],"container-title":["Journal of Medical Internet Research"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T20:11:59Z","timestamp":1788984719000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jmir.org\/2026\/1\/e97007"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,9]]},"references-count":131,"URL":"https:\/\/doi.org\/10.2196\/97007","relation":{},"ISSN":["1438-8871"],"issn-type":[{"value":"1438-8871","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,9]]},"article-number":"v28i11e97007"}}