{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T08:06:06Z","timestamp":1785139566146,"version":"3.55.0"},"reference-count":23,"publisher":"Wiley","issue":"7","license":[{"start":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T00:00:00Z","timestamp":1784678400000},"content-version":"vor","delay-in-days":21,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["JGH Open"],"published-print":{"date-parts":[[2026,7]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Aims<\/jats:title>\n                    <jats:p>Gastroesophageal reflux disease can progress to reflux esophagitis and Barrett's esophagus (BE), making accurate endoscopic diagnosis important. Artificial intelligence tools like ChatGPT\u20105 may assist image interpretation, though data on newer large language models remains limited. This study evaluated ChatGPT\u20105 for BE detection and LA esophagitis severity classification.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods and Results<\/jats:title>\n                    <jats:p>\n                      Endoscopic images from the HyperKvasir dataset were analyzed, including BE, esophagitis A, esophagitis B\u2013D, and normal Z\u2010line images. Four standardized prompts were assessed: (1) BE versus normal, (2) esophagitis versus normal, (3) LA\u2010grade severity (A vs. B\u2013D), and (4) BE versus severe esophagitis. ChatGPT\u20105 was evaluated in auto mode. Two investigators analyzed 640 unique images, yielding 1280 evaluations. Sensitivity, specificity, positive\/negative predictive values (PPV\/NPV), F1 scores, and accuracy were calculated. In binary tasks, sensitivity was highest for severe esophagitis (B\u2013D) (0.774). Binary accuracy was similar across tasks (~0.64), with the highest for severe esophagitis (0.655). In three\u2010class analyses, severe esophagitis performed best (sensitivity 0.506, specificity 0.761, accuracy 0.438), with performance improving alongside disease severity. PPV trended higher for severe esophagitis compared with normal mucosa (\n                      <jats:italic>p<\/jats:italic>\n                      \u2009~\u20090.03), though significance was not retained after multiple\u2010comparison correction. In the BE\u2010severe esophagitis\u2010normal comparison, severe esophagitis achieved the highest sensitivity (0.590), specificity (0.790), and accuracy (0.521). PPV trended higher for severe esophagitis versus normal mucosa (\n                      <jats:italic>p<\/jats:italic>\n                      \u2009~\u20090.05), though significance was not maintained after multiplicity adjustment. NPVs exceeded PPVs across all paradigms.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>ChatGPT\u20105 demonstrated moderate performance for esophageal image interpretation, performing best for severe esophagitis and worst for mild esophagitis\/BE. Binary prompting outperformed multiclass formats, and the model functioned better as a rule\u2010out tool.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/jgh3.70452","type":"journal-article","created":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T04:53:14Z","timestamp":1784782394000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluating\n                    <scp>ChatGPT<\/scp>\n                    \u20105 for Detection of Barrett's Esophagus and Grading of Esophagitis: A Multiclass Endoscopic Image Analysis"],"prefix":"10.1002","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8408-5381","authenticated-orcid":false,"given":"Hamza R.","family":"Khan","sequence":"first","affiliation":[{"name":"Division of Gastroenterology &amp; Advanced Endoscopy Rutgers New Jersey Medical School  Newark New Jersey USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ibraheem","family":"Mirza","sequence":"additional","affiliation":[{"name":"Division of Gastroenterology &amp; Advanced Endoscopy Rutgers New Jersey Medical School  Newark New Jersey USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5132-3956","authenticated-orcid":false,"given":"Owais M.","family":"Aftab","sequence":"additional","affiliation":[{"name":"Department of Medicine SUNY Downstate Health Sciences  Brooklyn New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yash","family":"Shah","sequence":"additional","affiliation":[{"name":"Division of Gastroenterology &amp; Advanced Endoscopy Rutgers New Jersey Medical School  Newark New Jersey USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5428-9848","authenticated-orcid":false,"given":"Ahmed H.","family":"Al\u2010Khazraji","sequence":"additional","affiliation":[{"name":"Division of Gastroenterology &amp; Advanced Endoscopy Rutgers New Jersey Medical School  Newark New Jersey USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,7,22]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12876-024-03143-9"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.5056\/jnm18140"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cgh.2023.10.006"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mayocp.2023.07.014"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.5946\/ce.2022.247"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1159\/000547635"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12913-025-13832-0"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.2196\/63430"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-020-00622-y"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.2147\/OPTH.S517238"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11604-024-01606-3"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.2196\/67551"},{"issue":"5","key":"e_1_2_10_14_1","article-title":"Optimizing Diagnostic Performance of ChatGPT: The Impact of Prompt Engineering on Thoracic Radiology Cases","volume":"16","author":"Cesur T.","year":"2024","journal-title":"Cureus"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01029-4"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12909-025-07752-0"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1053\/j.gastro.2021.11.040"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(23)00199-1"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1063\/5.0208691"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.3390\/jcm14020572"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.2196\/58801"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1177\/1932296820985567"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajoint.2025.100111"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.1002\/hsr2.71219"}],"container-title":["JGH Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jgh3.70452","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/jgh3.70452","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jgh3.70452","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T07:53:16Z","timestamp":1785138796000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/jgh3.70452"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":23,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["10.1002\/jgh3.70452"],"URL":"https:\/\/doi.org\/10.1002\/jgh3.70452","archive":["Portico"],"relation":{},"ISSN":["2397-9070","2397-9070"],"issn-type":[{"value":"2397-9070","type":"print"},{"value":"2397-9070","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"2026-05-07","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-15","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70452"}}