{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T03:20:28Z","timestamp":1793330428412,"version":"4.5.0"},"reference-count":29,"publisher":"American Medical Association (AMA)","issue":"10","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JAMA Netw Open"],"abstract":"Importance<\/jats:title>Multimodal generative artificial intelligence (AI) methodologies have the potential to optimize emergency department care by producing draft radiology reports from input images.<\/jats:p><\/jats:sec>Objective<\/jats:title>To evaluate the accuracy and quality of AI\u2013generated chest radiograph interpretations in the emergency department setting.<\/jats:p><\/jats:sec>Design, Setting, and Participants<\/jats:title>This was a retrospective diagnostic study of 500 randomly sampled emergency department encounters at a tertiary care institution including chest radiographs interpreted by both a teleradiology service and on-site attending radiologist from January 2022 to January 2023. An AI interpretation was generated for each radiograph. The 3 radiograph interpretations were each rated in duplicate by 6 emergency department physicians using a 5-point Likert scale.<\/jats:p><\/jats:sec>Main Outcomes and Measures<\/jats:title>The primary outcome was any difference in Likert scores between radiologist, AI, and teleradiology reports, using a cumulative link mixed model. Secondary analyses compared the probability of each report type containing no clinically significant discrepancy with further stratification by finding presence, using a logistic mixed-effects model. Physician comments on discrepancies were recorded.<\/jats:p><\/jats:sec>Results<\/jats:title>A total of 500 ED studies were included from 500 unique patients with a mean (SD) age of 53.3\u2009(21.6) years; 282 patients (56.4%) were female. There was a significant association of report type with ratings, with post hoc tests revealing significantly greater scores for AI (mean [SE] score, 3.22\u2009[0.34]; P<\/jats:italic>\u2009&amp;lt;\u2009.001) and radiologist (mean [SE] score, 3.34\u2009[0.34]; P<\/jats:italic>\u2009&amp;lt;\u2009.001) reports compared with teleradiology (mean [SE] score, 2.74\u2009[0.34]) reports. AI and radiologist reports were not significantly different. On secondary analysis, there was no difference in the probability of no clinically significant discrepancy between the 3 report types. Further stratification of reports by presence of cardiomegaly, pulmonary edema, pleural effusion, infiltrate, pneumothorax, and support devices also yielded no difference in the probability of containing no clinically significant discrepancy between the report types.<\/jats:p><\/jats:sec>Conclusions and Relevance<\/jats:title>In a representative sample of emergency department chest radiographs, results suggest that the generative AI model produced reports of similar clinical accuracy and textual quality to radiologist reports while providing higher textual quality than teleradiologist reports. Implementation of the model in the clinical workflow could enable timely alerts to life-threatening pathology while aiding imaging interpretation and documentation.<\/jats:p><\/jats:sec>","DOI":"10.1001\/jamanetworkopen.2023.36100","type":"journal-article","created":{"date-parts":[[2023,10,5]],"date-time":"2023-10-05T15:31:57Z","timestamp":1696519917000},"page":"e2336100","source":"Crossref","is-referenced-by-count":117,"title":["Generative Artificial Intelligence for Chest Radiograph Interpretation in the Emergency Department"],"prefix":"10.1001","volume":"6","author":[{"given":"Jonathan","family":"Huang","sequence":"first","affiliation":[{"name":"Department of Emergency Medicine, Northwestern University Feinberg School of Medicine, Chicago, Illinois"},{"name":"Department of Anesthesiology, Northwestern University Feinberg School of Medicine, Chicago, Illinois"},{"name":"Department of Biomedical Engineering, McCormick School of Engineering, Northwestern University, Evanston, Illinois"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luke","family":"Neill","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, Northwestern University Feinberg School of Medicine, Chicago, Illinois"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew","family":"Wittbrodt","sequence":"additional","affiliation":[{"name":"Research & Development, Northwestern Medicine Information Services, Chicago, Illinois"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Melnick","sequence":"additional","affiliation":[{"name":"Research & Development, Northwestern Medicine Information Services, Chicago, Illinois"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew","family":"Klug","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":"John","family":"Bailitz","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, Northwestern University Feinberg School of Medicine, Chicago, Illinois"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Timothy","family":"Loftus","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, Northwestern University Feinberg School of Medicine, Chicago, Illinois"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanjeev","family":"Malik","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, Northwestern University Feinberg School of Medicine, Chicago, Illinois"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amit","family":"Phull","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, Northwestern University Feinberg School of Medicine, Chicago, Illinois"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Victoria","family":"Weston","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, 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":"Mozziyar","family":"Etemadi","sequence":"additional","affiliation":[{"name":"Research & Development, Northwestern Medicine Information Services, Chicago, Illinois"},{"name":"Department of Anesthesiology, Northwestern University Feinberg School of Medicine, Chicago, Illinois"},{"name":"Department of Biomedical Engineering, McCormick School of Engineering, Northwestern University, Evanston, Illinois"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10","published-online":{"date-parts":[[2023,10,5]]},"reference":[{"issue":"1","key":"zoi231039r1","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1016\/j.ajem.2009.07.011","article-title":"Accuracy of radiographic readings in the emergency department.","volume":"29","author":"Petinaux","year":"2011","journal-title":"Am J Emerg Med"},{"issue":"4","key":"zoi231039r2","doi-asserted-by":"publisher","first-page":"626","DOI":"10.5811\/westjem","article-title":"Radiograph interpretation discrepancies in a community hospital emergency department.","volume":"20","author":"Tranovich","year":"2019","journal-title":"West J Emerg Med"},{"issue":"1021","key":"zoi231039r3","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20120112","article-title":"The impact of immediate reporting on interpretive discrepancies and patient referral pathways within the emergency department: a randomised controlled trial.","volume":"86","author":"Hardy","year":"2013","journal-title":"Br J Radiol"},{"issue":"4","key":"zoi231039r4","doi-asserted-by":"publisher","first-page":"W180","DOI":"10.2214\/AJR.19.21386","article-title":"The increasing use of emergency department imaging in the US: is it appropriate?","volume":"213","author":"Selvarajan","year":"2019","journal-title":"AJR Am J Roentgenol"},{"issue":"5","key":"zoi231039r5","doi-asserted-by":"publisher","first-page":"993","DOI":"10.1007\/s10140-021-01935-0","article-title":"Update on establishing and managing an overnight emergency radiology division.","volume":"28","author":"Scheinfeld","year":"2021","journal-title":"Emerg Radiol"},{"issue":"2","key":"zoi231039r6","doi-asserted-by":"publisher","DOI":"10.1177\/2058460121989319","article-title":"Discrepancy rates of preliminary and final reports for after-hours pediatric teleradiology interpretations.","volume":"10","author":"Pfeifer","year":"2021","journal-title":"Acta Radiol Open"},{"issue":"1","key":"zoi231039r7","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1007\/s10140-010-0899-2","article-title":"Systematic survey of discrepancy rates in an international teleradiology service.","volume":"18","author":"Agrawal","year":"2011","journal-title":"Emerg Radiol"},{"issue":"5","key":"zoi231039r9","doi-asserted-by":"publisher","first-page":"4019","DOI":"10.1007\/s10462-022-10270-w","article-title":"Automatic captioning for medical imaging (MIC): a rapid review of literature.","volume":"56","author":"Beddiar","year":"2023","journal-title":"Artif Intell Rev"},{"key":"zoi231039r10","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1162\/tacl_a_00536","article-title":"Locally Typical Sampling.","volume":"11","author":"Meister","year":"2023","journal-title":"Trans Assoc Comput Linguist"},{"issue":"12","key":"zoi231039r12","doi-asserted-by":"publisher","first-page":"1399","DOI":"10.1038\/s41551-022-00936-9","article-title":"Expert-level detection of pathologies from unannotated chest x-ray images via self-supervised learning.","volume":"6","author":"Tiu","year":"2022","journal-title":"Nat Biomed Eng"},{"issue":"8","key":"zoi231039r13","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":"3","key":"zoi231039r14","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.222268","article-title":"Autonomous chest radiograph reporting using AI: estimation of clinical impact.","volume":"307","author":"Plesner","year":"2023","journal-title":"Radiology"},{"issue":"4","key":"zoi231039r15","doi-asserted-by":"publisher","first-page":"584","DOI":"10.3390\/diagnostics13040584","article-title":"Artificial Intelligence-assisted chest x-ray for the diagnosis of COVID-19: a systematic review and meta-analysis.","volume":"13","author":"Tzeng","year":"2023","journal-title":"Diagnostics (Basel)"},{"issue":"1","key":"zoi231039r16","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1186\/1471-2334-12-31","article-title":"Interrater agreement in the assessment of abnormal chest x-ray findings for tuberculosis between 2 Asian countries.","volume":"12","author":"Sakurada","year":"2012","journal-title":"BMC Infect Dis"},{"issue":"3","key":"zoi231039r17","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1016\/j.jmir.2021.04.002","article-title":"Interrater reliability in quality assurance (QA) of pediatric chest x-rays.","volume":"52","author":"Hlabangana","year":"2021","journal-title":"J Med Imaging Radiat Sci"},{"issue":"1","key":"zoi231039r18","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1186\/s13054-017-1606-4","article-title":"Does training improve diagnostic accuracy and interrater agreement in applying the Berlin radiographic definition of acute respiratory distress syndrome\u2014a multicenter prospective study.","volume":"21","author":"Peng","year":"2017","journal-title":"Crit Care"},{"issue":"3","key":"zoi231039r19","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1007\/s13244-018-0599-0","article-title":"Added value of double reading in diagnostic radiology: a systematic review.","volume":"9","author":"Geijer","year":"2018","journal-title":"Insights Imaging"},{"issue":"5","key":"zoi231039r20","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1111\/j.1525-1497.2006.00427.x","article-title":"Competency in chest radiography\u2014a comparison of medical students, residents, and fellows.","volume":"21","author":"Eisen","year":"2006","journal-title":"J Gen Intern Med"},{"issue":"4","key":"zoi231039r21","doi-asserted-by":"publisher","first-page":"349","DOI":"10.7861\/clinmedicine.13-4-349","article-title":"Assessing the accuracy and certainty in interpreting chest x-rays in the medical division.","volume":"13","author":"Satia","year":"2013","journal-title":"Clin Med (Lond)"},{"issue":"3","key":"zoi231039r22","doi-asserted-by":"publisher","first-page":"650","DOI":"10.1016\/j.chest.2022.10.039","article-title":"Commonly missed findings on chest radiographs: causes and consequences.","volume":"163","author":"Gefter","year":"2023","journal-title":"Chest"},{"issue":"4","key":"zoi231039r23","doi-asserted-by":"publisher","DOI":"10.1056\/CAT.21.0469","article-title":"Preventing delayed and missed care by applying artificial intelligence to trigger radiology imaging follow-up.","volume":"3","author":"Domingo","year":"2022","journal-title":"NEJM Catal Innov Care Deliv"},{"issue":"1","key":"zoi231039r24","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1186\/s12911-021-01623-6","article-title":"Automatic detection of actionable radiology reports using bidirectional encoder representations from transformers.","volume":"21","author":"Nakamura","year":"2021","journal-title":"BMC Med Inform Decis Mak"},{"key":"zoi231039r8","unstructured":"Cao? Y, Li? S, Liu? Y, . A comprehensive survey of AI-generated content (AIGC): a history of generative AI from GAN to ChatGPT. arXiv. Preprint posted online March 7, 2023. doi:10.48550\/arXiv.2303.04226"},{"key":"zoi231039r11","doi-asserted-by":"crossref","unstructured":"Yu? F, Endo? M, Krishnan? R, . Evaluating progress in automatic chest X-ray radiology report generation. medRxiv. Preprint posted online August 31, 2022. doi:10.1016\/j.patter.2023.100802","DOI":"10.1016\/j.patter.2023.100802"},{"key":"zoi231039r25","unstructured":"Hendrycks? D, Burns? C, Kadavath? S, . Measuring mathematical problem solving with the MATH data set. arXiv. Preprint posted online March 5, 2021. doi:10.48550\/arXiv.2103.03874"},{"key":"zoi231039r26","unstructured":"Cobbe? K, Kosaraju? V, Bavarian? M, . Training verifiers to solve math word problems. arXiv. Preprint posted online October 27, 2021. doi:10.48550\/arXiv.2110.14168"},{"key":"zoi231039r27","unstructured":"Lewkowycz? A, Andreassen? A, Dohan? D, . Solving quantitative reasoning problems with language models. arXiv. Preprint posted online June 29, 2022. doi:10.48550\/arXiv.2206.14858"},{"key":"zoi231039r28","unstructured":"Bai? Y, Jones? A, Ndousse? K, . Training a helpful and harmless assistant with reinforcement learning from human feedback. arXiv. Preprint posted online April 12, 2022. doi:10.48550\/arXiv.2204.05862"},{"key":"zoi231039r29","unstructured":"Hinton? G. On radiology. Paper presented at: Machine Learning and The Market for Intelligence 2016; November 24, 2016; Toronto, Ontario, Canada. Accessed May 16, 2023. https:\/\/www.youtube.com\/watch?v=2HMPRXstSvQ"}],"container-title":["JAMA Network Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/jamanetwork.com\/journals\/jamanetworkopen\/articlepdf\/2810195\/huang_2023_oi_231039_1695747117.56418.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,5]],"date-time":"2023-10-05T15:32:07Z","timestamp":1696519927000},"score":1,"resource":{"primary":{"URL":"https:\/\/jamanetwork.com\/journals\/jamanetworkopen\/fullarticle\/2810195"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,5]]},"references-count":29,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2023,10,2]]}},"URL":"https:\/\/doi.org\/10.1001\/jamanetworkopen.2023.36100","relation":{},"ISSN":["2574-3805"],"issn-type":[{"value":"2574-3805","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,5]]}}}