{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T10:58:31Z","timestamp":1793789911723,"version":"4.6.1"},"reference-count":37,"publisher":"American Medical Association (AMA)","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JAMA Netw Open"],"abstract":"\n Importance<\/jats:title>\n Diagnostic imaging interpretation involves distilling multimodal clinical information into text form, a task well-suited to augmentation by generative artificial intelligence (AI). However, to our knowledge, impacts of AI-based draft radiological reporting remain unstudied in clinical settings.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n To prospectively evaluate the association of radiologist use of a workflow-integrated generative model capable of providing draft radiological reports for plain radiographs across a tertiary health care system with documentation efficiency, the clinical accuracy and textual quality of final radiologist reports, and the model\u2019s potential for detecting unexpected, clinically significant pneumothorax.<\/jats:p>\n <\/jats:sec>\n \n Design, Setting, and Participants<\/jats:title>\n This prospective cohort study was conducted from November 15, 2023, to April 24, 2024, at a tertiary care academic health system. The association between use of the generative model and radiologist documentation efficiency was evaluated for radiographs documented with model assistance compared with a baseline set of radiographs without model use, matched by study type (chest or nonchest). Peer review was performed on model-assisted interpretations. Flagging of pneumothorax requiring intervention was performed on radiographs prospectively.<\/jats:p>\n <\/jats:sec>\n \n Main Outcomes and Measures<\/jats:title>\n The primary outcomes were association of use of the generative model with radiologist documentation efficiency, assessed by difference in documentation time with and without model use using a linear mixed-effects model; for peer review of model-assisted reports, the difference in Likert-scale ratings using a cumulative-link mixed model; and for flagging pneumothorax requiring intervention, sensitivity and specificity.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n A total of 23\u202f960 radiographs (11\u202f980 each with and without model use) were used to analyze documentation efficiency. Interpretations with model assistance (mean [SE], 159.8 [27.0] seconds) were faster than the baseline set of those without (mean [SE], 189.2 [36.2] seconds) (\n P<\/jats:italic>\n \u2009=\u2009.02), representing a 15.5% documentation efficiency increase. Peer review of 800 studies showed no difference in clinical accuracy (\u03c7\n 2<\/jats:sup>\n \u2009=\u20090.68;\n P<\/jats:italic>\n \u2009=\u2009.41) or textual quality (\u03c7\n 2<\/jats:sup>\n \u2009=\u20093.62;\n P<\/jats:italic>\n \u2009=\u2009.06) between model-assisted interpretations and nonmodel interpretations. Moreover, the model flagged studies containing a clinically significant, unexpected pneumothorax with a sensitivity of 72.7% and specificity of 99.9% among 97\u202f651 studies screened.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions and Relevance<\/jats:title>\n In this prospective cohort study of clinical use of a generative model for draft radiological reporting, model use was associated with improved radiologist documentation efficiency while maintaining clinical quality and demonstrated potential to detect studies containing a pneumothorax requiring immediate intervention. This study suggests the potential for radiologist and generative AI collaboration to improve clinical care delivery.<\/jats:p>\n <\/jats:sec>","DOI":"10.1001\/jamanetworkopen.2025.13921","type":"journal-article","created":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T11:30:50Z","timestamp":1749123050000},"page":"e2513921","source":"Crossref","is-referenced-by-count":57,"title":["Efficiency and Quality of Generative AI\u2013Assisted Radiograph Reporting"],"prefix":"10.1001","volume":"8","author":[{"given":"Jonathan","family":"Huang","sequence":"first","affiliation":[{"name":"Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Illinois"},{"name":"Department of Biomedical Engineering, Northwestern University, Evanston, Illinois"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew T.","family":"Wittbrodt","sequence":"additional","affiliation":[{"name":"Research & Development, Northwestern Medicine Information Services, Chicago, Illinois"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Caitlin N.","family":"Teague","sequence":"additional","affiliation":[{"name":"Research & Development, Northwestern Medicine Information Services, Chicago, Illinois"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eric","family":"Karl","sequence":"additional","affiliation":[{"name":"Research & Development, Northwestern Medicine Information Services, Chicago, Illinois"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Galal","family":"Galal","sequence":"additional","affiliation":[{"name":"Research & Development, Northwestern Medicine Information Services, Chicago, Illinois"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Thompson","sequence":"additional","affiliation":[{"name":"Research & Development, Northwestern Medicine Information Services, Chicago, Illinois"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ajay","family":"Chapa","sequence":"additional","affiliation":[{"name":"Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Illinois"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming-Lun","family":"Chiu","sequence":"additional","affiliation":[{"name":"Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Illinois"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bradley","family":"Herynk","sequence":"additional","affiliation":[{"name":"Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Illinois"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richard","family":"Linchangco","sequence":"additional","affiliation":[{"name":"Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Illinois"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Serhal","sequence":"additional","affiliation":[{"name":"Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Illinois"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J. Alex","family":"Heller","sequence":"additional","affiliation":[{"name":"Research & Development, Northwestern Medicine Information Services, Chicago, Illinois"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samir F.","family":"Abboud","sequence":"additional","affiliation":[{"name":"Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Illinois"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mozziyar","family":"Etemadi","sequence":"additional","affiliation":[{"name":"Research & Development, Northwestern Medicine Information Services, Chicago, Illinois"},{"name":"Department of Biomedical Engineering, Northwestern University, Evanston, Illinois"},{"name":"Department of Anesthesiology, Northwestern University Feinberg School of Medicine, Chicago, Illinois"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10","published-online":{"date-parts":[[2025,6,5]]},"reference":[{"issue":"8","key":"zoi250461r1","doi-asserted-by":"publisher","first-page":"500","DOI":"10.1038\/s41568-018-0016-5","article-title":"Artificial intelligence in radiology.","volume":"18","author":"Hosny","year":"2018","journal-title":"Nat Rev Cancer"},{"issue":"4","key":"zoi250461r2","doi-asserted-by":"publisher","first-page":"1134","DOI":"10.1038\/s41591-024-02855-5","article-title":"Adapted large language models can outperform medical experts in clinical text summarization.","volume":"30","author":"Van Veen","year":"2024","journal-title":"Nat Med"},{"issue":"21","key":"zoi250461r3","doi-asserted-by":"publisher","first-page":"1981","DOI":"10.1056\/NEJMra2301725","article-title":"The current and future state of AI interpretation of medical images.","volume":"388","author":"Rajpurkar","year":"2023","journal-title":"N Engl J Med"},{"issue":"9","key":"zoi250461r4","doi-asserted-by":"publisher","first-page":"843","DOI":"10.1001\/jama.2019.11456","article-title":"Trends in use of medical imaging in US health care systems and in Ontario, Canada, 2000-2016.","volume":"322","author":"Smith-Bindman","year":"2019","journal-title":"JAMA"},{"issue":"10315","key":"zoi250461r5","doi-asserted-by":"publisher","first-page":"1997","DOI":"10.1016\/S0140-6736(21)00673-5","article-title":"The Lancet Commission on Diagnostics: transforming access to diagnostics.","volume":"398","author":"Fleming","year":"2021","journal-title":"Lancet"},{"issue":"2","key":"zoi250461r9","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","year":"2025","journal-title":"Nat Med"},{"issue":"10","key":"zoi250461r11","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","year":"2023","journal-title":"JAMA Netw Open"},{"key":"zoi250461r13","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2023.102633","article-title":"Improving chest X-ray report generation by leveraging warm starting.","volume":"144","author":"Nicolson","year":"2023","journal-title":"Artif Intell Med"},{"issue":"9","key":"zoi250461r15","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2023.100802","article-title":"Evaluating progress in automatic chest X-ray radiology report generation.","volume":"4","author":"Yu","year":"2023","journal-title":"Patterns (N Y)"},{"issue":"8056","key":"zoi250461r16","doi-asserted-by":"publisher","first-page":"888","DOI":"10.1038\/s41586-025-08675-y","article-title":"Multimodal generative AI for medical image interpretation.","volume":"639","author":"Rao","year":"2025","journal-title":"Nature"},{"issue":"3","key":"zoi250461r17","doi-asserted-by":"publisher","first-page":"802","DOI":"10.1148\/radiol.11101396","article-title":"Impact of a 4-year quality improvement initiative to improve communication of critical imaging test results.","volume":"259","author":"Anthony","year":"2011","journal-title":"Radiology"},{"issue":"12","key":"zoi250461r18","doi-asserted-by":"publisher","first-page":"868","DOI":"10.1056\/NEJM200003233421207","article-title":"Spontaneous pneumothorax.","volume":"342","author":"Sahn","year":"2000","journal-title":"N Engl J Med"},{"issue":"12","key":"zoi250461r19","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2022.47172","article-title":"Evaluation of an artificial intelligence model for detection of pneumothorax and tension pneumothorax in chest radiographs.","volume":"5","author":"Hillis","year":"2022","journal-title":"JAMA Netw Open"},{"issue":"4","key":"zoi250461r21","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","year":"2024","journal-title":"Radiol Artif Intell"},{"issue":"10","key":"zoi250461r23","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1016\/j.jacr.2011.04.015","article-title":"Addenda to the radiology report: what are we trying to convey?","volume":"8","author":"Hussain","year":"2011","journal-title":"J Am Coll Radiol"},{"issue":"8","key":"zoi250461r24","doi-asserted-by":"publisher","first-page":"926","DOI":"10.1177\/0284185113508178","article-title":"Quality of chest radiograph reports.","volume":"55","author":"Hirvonen-Kari","year":"2014","journal-title":"Acta Radiol"},{"issue":"4","key":"zoi250461r25","doi-asserted-by":"publisher","first-page":"526","DOI":"10.1016\/j.acra.2018.07.001","article-title":"Addressing burnout in radiologists.","volume":"26","author":"Chetlen","year":"2019","journal-title":"Acad Radiol"},{"issue":"1","key":"zoi250461r26","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1038\/s41746-020-0221-y","article-title":"An overview of clinical decision support systems: benefits, risks, and strategies for success.","volume":"3","author":"Sutton","year":"2020","journal-title":"NPJ Digit Med"},{"issue":"8","key":"zoi250461r27","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2022.29289","article-title":"Association of artificial intelligence-aided chest radiograph interpretation with reader performance and efficiency.","volume":"5","author":"Ahn","year":"2022","journal-title":"JAMA Netw Open"},{"issue":"1","key":"zoi250461r28","doi-asserted-by":"publisher","first-page":"1383","DOI":"10.1038\/s41598-023-28633-w","article-title":"Non-task expert physicians benefit from correct explainable AI advice when reviewing X-rays.","volume":"13","author":"Gaube","year":"2023","journal-title":"Sci Rep"},{"issue":"8","key":"zoi250461r29","doi-asserted-by":"publisher","first-page":"e496","DOI":"10.1016\/S2589-7500(21)00106-0","article-title":"Effect of a comprehensive deep-learning model on the accuracy of chest x-ray interpretation by radiologists: a retrospective, multireader multicase study.","volume":"3","author":"Seah","year":"2021","journal-title":"Lancet Digit Health"},{"issue":"12","key":"zoi250461r30","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2021-052902","article-title":"Assessment of the effect of a comprehensive chest radiograph deep learning model on radiologist reports and patient outcomes: a real-world observational study.","volume":"11","author":"Jones","year":"2021","journal-title":"BMJ Open"},{"issue":"3","key":"zoi250461r31","doi-asserted-by":"publisher","first-page":"837","DOI":"10.1038\/s41591-024-02850-w","article-title":"Heterogeneity and predictors of the effects of AI assistance on radiologists.","volume":"30","author":"Yu","year":"2024","journal-title":"Nat Med"},{"issue":"1","key":"zoi250461r32","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1038\/s41597-019-0322-0","article-title":"MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports.","volume":"6","author":"Johnson","year":"2019","journal-title":"Sci Data"},{"issue":"3","key":"zoi250461r33","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.231236","article-title":"Commercially available chest radiograph AI tools for detecting airspace disease, pneumothorax, and pleural effusion.","volume":"308","author":"Lind Plesner","year":"2023","journal-title":"Radiology"},{"issue":"3","key":"zoi250461r34","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1177\/08465371231220885","article-title":"Deep learning for pneumothorax detection on chest radiograph: a diagnostic test accuracy systematic review and meta analysis.","volume":"75","author":"Katzman","year":"2024","journal-title":"Can Assoc Radiol J"},{"issue":"1","key":"zoi250461r36","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1038\/s41597-023-02432-4","article-title":"FracAtlas: a dataset for fracture classification, localization and segmentation of musculoskeletal radiographs.","volume":"10","author":"Abedeen","year":"2023","journal-title":"Sci Data"},{"key":"zoi250461r35","author":"Rajpurkar","year":"2018"},{"key":"zoi250461r6","doi-asserted-by":"crossref","unstructured":"Xiong? Y, Liu? J, Zaripova? K, Sharifzadeh? S, Keicher? M, Navab? N. Prior-RadGraphFormer: a prior-knowledge-enhanced transformer for generating radiology graphs from x-rays.? arXiv. Preprint posted online March 24, 2023. doi:10.48550\/arXiv.2303.13818","DOI":"10.1007\/978-3-031-55088-1_5"},{"key":"zoi250461r7","unstructured":"Hyland? SL, Bannur? S, Bouzid? K, . MAIRA-1: A specialised large multimodal model for radiology report generation.? arXiv. Preprint posted online November 22, 2023. doi:10.48550\/arXiv.2311.13668"},{"key":"zoi250461r8","unstructured":"Moutakanni? T, Bojanowski? P, Chassagnon? G, . Advancing human-centric AI for robust X-ray analysis through holistic self-supervised learning.? arXiv. Preprint posted online May 2, 2024. doi:10.48550\/arXiv.2405.01469"},{"key":"zoi250461r10","doi-asserted-by":"crossref","unstructured":"Bannur? S, Hyland? SL, Liu? Q, . Learning to exploit temporal structure for biomedical vision-language processing.? arXiv. Preprint posted online January 11, 2023. doi:10.48550\/arXiv.2301.04558","DOI":"10.1109\/CVPR52729.2023.01442"},{"key":"zoi250461r12","unstructured":"Jeong? J, Tian? K, Li? A, . Multimodal image-text matching improves retrieval-based chest x-ray report generation.? arXiv. Preprint posted online March 29, 2023. doi:10.48550\/arXiv.2303.17579"},{"key":"zoi250461r14","unstructured":"Bannur? S, Bouzid? K, Castro? DC, . MAIRA-2: grounded radiology report generation.? arXiv. Preprint posted online June 6, 2024. doi:10.48550\/arXiv.2406.04449"},{"key":"zoi250461r20","unstructured":"Dosovitskiy? A, Beyer? L, Kolesnikov? A, . An image is worth 16\u00d716 words: transformers for image recognition at scale.? arXiv. Preprint posted online October 22, 2020. doi:10.48550\/arXiv.2010.11929"},{"key":"zoi250461r22","unstructured":"Jain? S, Agrawal? A, Saporta? A, . RadGraph: extracting clinical entities and relations from radiology reports.? arXiv. Preprint posted online June 28, 2021. doi:10.48550\/arXiv.2106.14463"},{"key":"zoi250461r37","doi-asserted-by":"crossref","unstructured":"Nguyen? HT, Pham? HH, Nguyen? NT, . VinDr-SpineXR: a deep learning framework for spinal lesions detection and classification from radiographs.? arXiv. Preprint posted online June 24, 2021. doi:10.48550\/arXiv.2106.12930","DOI":"10.1007\/978-3-030-87240-3_28"}],"container-title":["JAMA Network Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/jamanetwork.com\/journals\/jamanetworkopen\/articlepdf\/2834943\/huang_2025_oi_250461_1748448325.30901.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T11:30:52Z","timestamp":1749123052000},"score":1,"resource":{"primary":{"URL":"https:\/\/jamanetwork.com\/journals\/jamanetworkopen\/fullarticle\/2834943"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,5]]},"references-count":37,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,6,2]]}},"URL":"https:\/\/doi.org\/10.1001\/jamanetworkopen.2025.13921","relation":{},"ISSN":["2574-3805"],"issn-type":[{"value":"2574-3805","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,5]]}}}