{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T19:04:44Z","timestamp":1782846284146,"version":"3.54.5"},"reference-count":31,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR AI"],"abstract":"\n Background<\/jats:title>\n Early-stage clinical findings often appear only as conference posters circulated on social media. Because posters rarely carry structured metadata, their citations are invisible to bibliometric and alternative metric tools, limiting real-time research discovery.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aimed to determine whether a large language model can accurately extract citation data from clinical conference poster images shared on X (formerly known as Twitter) and link those data to the Dimensions and Altmetric databases.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n Poster images associated with the 2024 American Society of Clinical Oncology conference were searched using the terms \u201c#ASCO24,\u201d \u201c#ASCO2024,\u201d and the conference name. Images \u2265100 kB that contained the word \u201cposter\u201d in the post text were retained. A prompt-engineered Gemini 2.0 Flash model classified images, summarized posters, and extracted structured citation elements (eg, authors, titles, and digital object identifiers [DOIs]) in JSON format. A hierarchical linkage algorithm matched extracted elements against Dimensions records, prioritizing persistent identifiers and then title-journal-author composites. Manual validation was performed on a random 20% sample.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n We searched within 115,714 posts and 16,574 images, of which 651 (3.9%) met the inclusion criteria, and we obtained 1117 potential citations. The algorithm linked 63.4% (708\/1117) of the citations to 616 unique research outputs (n=580, 94.2% journal articles; n=36, 5.8% clinical trial registrations). Manual review of 135 randomly sampled citations confirmed correct linkage in 124 (91.9%) cases. DOI-based matching was mostly flawless; most errors occurred where only partial bibliographic details were available. The linked dataset enabled rapid profiling of topical foci (eg, lung and breast cancer) and identification of the most frequently referenced institutions and clinical trials in shared posters.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n This study presents a novel artificial intelligence\u2013driven methodology for enhancing research discovery and attention analysis from nontraditional clinical scholarly outputs. The American Society of Clinical Oncology was used as an example, but this methodology could be used for any conference and clinical poster.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/78148","type":"journal-article","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T18:40:08Z","timestamp":1762195208000},"page":"e78148","source":"Crossref","is-referenced-by-count":0,"title":["Clinical Evidence Linkage From the American Society of Clinical Oncology 2024 Conference Poster Images Using Generative AI: Exploratory Observational Study"],"prefix":"10.2196","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4668-7069","authenticated-orcid":false,"given":"Carlos","family":"Areia","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8534-5985","authenticated-orcid":false,"given":"Michael","family":"Taylor","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,2,5]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.4108\/eetiot.5336"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2024.e38008"},{"key":"ref3","unstructured":"TiwaryKKlinghofferTYoungASomasundaramSBehariNDaveACheungBNeilsonDEPoggioTRaskarRA roadmap for generative design of visual intelligenceAn MIT Exploration of Generative AI202409182026-01-15https:\/\/mit-genai.pubpub.org\/pub\/bcfcb6lu\/release\/3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0064841"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3389\/frma.2018.00023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s00799-023-00352-7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2928294.2928306"},{"key":"ref8","unstructured":"RoessleinJTweepy: Twitter for Python!GitHub20202026-01-08https:\/\/github.com\/tweepy\/tweepy"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1200\/jco.2024.42.16_suppl.8039"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1200\/jco.2024.42.16_suppl.7567"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1200\/jco.2024.42.16_suppl.9564"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1200\/jco.2024.42.16_suppl.1619"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1200\/jco.2024.42.16_suppl.1605"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1200\/jco.2024.42.16_suppl.4601"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2024.42.16_suppl.10536"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1200\/jco.2024.42.16_suppl.4529"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2024.42.16_suppl.12058"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.annonc.2020.08.2240"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1200\/jco.2024.42.16_suppl.7555"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1200\/CCI.24.00077"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1200\/jco.2024.42.36_suppl.439572"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1200\/jco.2024.42.16_suppl.4091"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.eururo.2024.07.016"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1200\/jco.2024.42.16_suppl.11067"},{"key":"ref25","unstructured":"Testing the addition of an anti-cancer drug, M3814 (Peposertib), to the usual radiation-based treatment (Lutetium Lu 177 Dotatate) for pancreatic neuroendocrine tumorsNational Library of Medicine2025-05-29https:\/\/www.clinicaltrials.gov\/study\/NCT04750954"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1200\/jco.2024.42.16_suppl.tps3630"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1200\/jco.2024.42.17_suppl.lba5501"},{"key":"ref28","unstructured":"HuJA phase 2 study of the ketogenic diet vs standard anti-cancer diet guidance for patients with glioblastoma in combination with standard-of-care treatmentNational Library of Medicine2025-05-29https:\/\/clinicaltrials.gov\/study\/NCT05708352"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1200\/jco.2024.42.16_suppl.tps2103"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.2196\/23724"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2016.11.006"}],"container-title":["JMIR AI"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ai.jmir.org\/2026\/1\/e78148","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:10:39Z","timestamp":1782843039000},"score":1,"resource":{"primary":{"URL":"https:\/\/ai.jmir.org\/2026\/1\/e78148"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,5]]},"references-count":31,"URL":"https:\/\/doi.org\/10.2196\/78148","relation":{"has-preprint":[{"id-type":"doi","id":"10.2196\/preprints.78148","asserted-by":"object"}]},"ISSN":["2817-1705"],"issn-type":[{"value":"2817-1705","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,5]]}}}