{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T17:59:12Z","timestamp":1791223152409,"version":"4.1.0"},"reference-count":0,"publisher":"Kare Publishing","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Hepatol Forum"],"abstract":"<jats:p>Background and Aim: Elevated liver enzymes are a common reason for hepatology referral, but etiological overlap complicates diagnosis. Most artificial intelligence applications address binary tasks, whereas routine practice requires multiclass discrimination. We developed and internally validated an explainable multiclass model to differentiate five major causes of persistent liver enzyme elevation.\r\nMaterials and Methods: This prospective proof-of-concept cohort included 280 consecutive adults with unexplained persistent aminotransferase elevation. Final diagnoses\u2014metabolic dysfunction-associated steatotic liver disease, viral hepatitis, alcohol-related liver disease, drug-induced liver injury, or autoimmune hepatitis\u2014were independently adjudicated by three hepatologists. Data were split into training (70%) and independent test (30%) sets, and four supervised algorithms were evaluated. To assess incorporation bias, a basic model using routine clinical and biochemical variables was compared with an extended model including serological markers. Interpretability was assessed using SHapley Additive exPlanations.\r\nResults: eXtreme gradient boosting achieved the best test-set performance, with an overall accuracy of 0.86 (95% CI 0.78\u20130.93) and balanced accuracy of 0.87 (95% CI 0.82\u20130.92). Class-specific AUROC values ranged from 0.92 to 0.95. Serological markers improved discrimination for autoimmune hepatitis (AUROC increase, 0.15; p<\/jats:p>","DOI":"10.14744\/hf.2026.79050","type":"journal-article","created":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T07:29:48Z","timestamp":1785396588000},"page":"249-255","source":"Crossref","is-referenced-by-count":0,"title":["Artificial intelligence-based multiclass classification of etiologies in patients with elevated liver enzymes: A prospective cohort study"],"prefix":"10.14744","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5760-3529","authenticated-orcid":false,"given":"Yavuz","family":"Ozden","sequence":"first","affiliation":[{"name":"Department of Gastroenterology, Kayseri City Hospital, University of Health Sciences, Kayseri, Turkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6083-2833","authenticated-orcid":false,"given":"Omer","family":"Yuzugulen","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology, Kayseri City Hospital, University of Health Sciences, Kayseri, Turkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1938-4377","authenticated-orcid":false,"given":"Nuh Mehmet","family":"Buyukberber","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology, Kayseri City Hospital, University of Health Sciences, Kayseri, Turkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"5966","published-online":{"date-parts":[[2026]]},"container-title":["Hepatology Forum"],"original-title":[],"link":[{"URL":"https:\/\/file.paplino.com\/hepatologyforum\/pdfs\/1785335680-en.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/hepatologyforum.org\/articles\/HF-79050\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T17:45:00Z","timestamp":1791222300000},"score":1,"resource":{"primary":{"URL":"https:\/\/hepatologyforum.org\/articles\/HF-79050"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":0,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026]]}},"URL":"https:\/\/doi.org\/10.14744\/hf.2026.79050","relation":{},"ISSN":["1307-5888","2757-7392"],"issn-type":[{"value":"1307-5888","type":"print"},{"value":"2757-7392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}