{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T19:19:04Z","timestamp":1789759144733,"version":"4.0.1"},"reference-count":43,"publisher":"Elsevier BV","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T00:00:00Z","timestamp":1756166400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82270619"],"award-info":[{"award-number":["82270619"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["NSFC 82470621"],"award-info":[{"award-number":["NSFC 82470621"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012165","name":"Key Technologies Research and Development Program","doi-asserted-by":"publisher","award":["2022YFC3502101"],"award-info":[{"award-number":["2022YFC3502101"]}],"id":[{"id":"10.13039\/501100012165","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["jhep-reports.eu","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["JHEP Reports"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1016\/j.jhepr.2025.101579","type":"journal-article","created":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T16:15:32Z","timestamp":1756916132000},"page":"101579","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":10,"title":["Evaluating large language models' performance in answering common questions on drug-induced liver injury"],"prefix":"10.1016","volume":"7","author":[{"given":"Yinuo","family":"Dong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zili","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9755-7230","authenticated-orcid":false,"given":"Yang","family":"Zhi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tengyu","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lanlan","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuran","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueli","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jieting","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qinghui","family":"Niu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingyang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zuxiong","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2928-3425","authenticated-orcid":false,"given":"Yimin","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jhepr.2025.101579_bib1","doi-asserted-by":"crossref","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","article-title":"Large language models in medicine","volume":"29","author":"Thirunavukarasu","year":"2023","journal-title":"Nat Med"},{"key":"10.1016\/j.jhepr.2025.101579_bib2","doi-asserted-by":"crossref","first-page":"366","DOI":"10.1080\/0142159X.2023.2249588","article-title":"ChatGPT-4: an assessment of an upgraded artificial intelligence chatbot in the United States Medical Licensing Examination","volume":"46","author":"Mihalache","year":"2024","journal-title":"Med Teach"},{"key":"10.1016\/j.jhepr.2025.101579_bib3","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2023.36483","article-title":"Accuracy and reliability of chatbot responses to physician questions","volume":"6","author":"Goodman","year":"2023","journal-title":"JAMA Netw Open"},{"key":"10.1016\/j.jhepr.2025.101579_bib4","doi-asserted-by":"crossref","DOI":"10.1148\/radiol.232255","article-title":"Collaborative enhancement of consistency and accuracy in US diagnosis of thyroid nodules using large language models","volume":"310","author":"Wu","year":"2024","journal-title":"Radiology"},{"key":"10.1016\/j.jhepr.2025.101579_bib5","doi-asserted-by":"crossref","first-page":"1884","DOI":"10.1093\/jamia\/ocae184","article-title":"The potential and pitfalls of using a large language model such as ChatGPT, GPT-4, or LLaMA as a clinical assistant","volume":"31","author":"Zhang","year":"2024","journal-title":"J Am Med Inform Assoc"},{"key":"10.1016\/j.jhepr.2025.101579_bib6","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2024.40969","article-title":"Large language model influence on diagnostic reasoning: a randomized clinical trial","volume":"7","author":"Goh","year":"2024","journal-title":"JAMA Netw Open"},{"key":"10.1016\/j.jhepr.2025.101579_bib7","article-title":"Use of artificial intelligence for liver diseases: a survey from the EASL congress 2024","volume":"6","author":"\u017digutyt\u0117","year":"2024","journal-title":"JHEP Rep"},{"key":"10.1016\/j.jhepr.2025.101579_bib8","doi-asserted-by":"crossref","first-page":"914","DOI":"10.14309\/ajg.0000000000003179","article-title":"Is ChatGPT-4 a reliable tool in autoimmune hepatitis?","volume":"120","author":"Colapietro","year":"2025","journal-title":"Am J Gastroenterol"},{"key":"10.1016\/j.jhepr.2025.101579_bib9","doi-asserted-by":"crossref","first-page":"e279","DOI":"10.1016\/j.jhep.2023.11.017","article-title":"Preliminary fatty liver disease grading using general-purpose online large language models: ChatGPT-4 or Bard?","volume":"80","author":"Zhang","year":"2024","journal-title":"J Hepatol"},{"key":"10.1016\/j.jhepr.2025.101579_bib10","doi-asserted-by":"crossref","first-page":"1158","DOI":"10.1097\/HEP.0000000000000834","article-title":"Development of a liver disease-specific large language model chat interface using retrieval-augmented generation","volume":"80","author":"Ge","year":"2024","journal-title":"Hepatology"},{"key":"10.1016\/j.jhepr.2025.101579_bib11","doi-asserted-by":"crossref","first-page":"1753","DOI":"10.1097\/HEP.0000000000001115","article-title":"Evaluating the positive predictive value of code-based identification of cirrhosis and its complications utilizing GPT-4","volume":"81","author":"Far","year":"2025","journal-title":"Hepatology"},{"key":"10.1016\/j.jhepr.2025.101579_bib12","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1038\/s41572-019-0105-0","article-title":"Drug-induced liver injury","volume":"5","author":"Andrade","year":"2019","journal-title":"Nat Rev Dis Primers"},{"key":"10.1016\/j.jhepr.2025.101579_bib13","doi-asserted-by":"crossref","first-page":"1999","DOI":"10.1111\/liv.15262","article-title":"Incidence and risk factors of drug-induced liver injury","volume":"42","author":"Li","year":"2022","journal-title":"Liver Int"},{"key":"10.1016\/j.jhepr.2025.101579_bib14","doi-asserted-by":"crossref","first-page":"1154","DOI":"10.1136\/gutjnl-2016-313369","article-title":"Drug-induced liver injury: recent advances in diagnosis and risk assessment","volume":"66","author":"Kullak-Ublick","year":"2017","journal-title":"Gut"},{"key":"10.1016\/j.jhepr.2025.101579_bib15","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1016\/j.jhep.2021.01.029","article-title":"Comprehensive analysis and insights gained from long-term experience of the Spanish DILI Registry","volume":"75","author":"Stephens","year":"2021","journal-title":"J Hepatol"},{"key":"10.1016\/j.jhepr.2025.101579_bib16","doi-asserted-by":"crossref","DOI":"10.1111\/liv.70038","article-title":"Artificial intelligence: an emerging tool for studying drug-induced liver injury","volume":"45","author":"Niu","year":"2025","journal-title":"Liver Int"},{"key":"10.1016\/j.jhepr.2025.101579_bib17","doi-asserted-by":"crossref","first-page":"384","DOI":"10.1007\/s12072-023-10633-7","article-title":"Chinese guideline for the diagnosis and treatment of drug-induced liver injury: an update","volume":"18","author":"Mao","year":"2024","journal-title":"Hepatol Int"},{"key":"10.1016\/j.jhepr.2025.101579_bib18","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2024.4630","article-title":"Quality of large language model responses to radiation oncology patient care questions","volume":"7","author":"Yalamanchili","year":"2024","journal-title":"JAMA Netw Open"},{"key":"10.1016\/j.jhepr.2025.101579_bib19","article-title":"Artificial intelligence, ChatGPT, and other large language models for social determinants of health: current state and future directions","volume":"5","author":"Ong","year":"2024","journal-title":"Cell Rep Med"},{"key":"10.1016\/j.jhepr.2025.101579_bib20","doi-asserted-by":"crossref","DOI":"10.1016\/j.ebiom.2023.104770","article-title":"Benchmarking large language models' performances for myopia care: a comparative analysis of ChatGPT-3.5, ChatGPT-4.0, and Google Bard","volume":"95","author":"Lim","year":"2023","journal-title":"EBioMedicine"},{"key":"10.1016\/j.jhepr.2025.101579_bib21","doi-asserted-by":"crossref","DOI":"10.1148\/radiol.230922","article-title":"How AI responds to common lung cancer questions: ChatGPT vs Google Bard","volume":"307","author":"Rahsepar","year":"2023","journal-title":"Radiology"},{"key":"10.1016\/j.jhepr.2025.101579_bib22","doi-asserted-by":"crossref","DOI":"10.1016\/j.jclinane.2024.111582","article-title":"The evaluation of the performance of ChatGPT in the management of labor analgesia","volume":"98","author":"Ismaiel","year":"2024","journal-title":"J Clin Anesth"},{"key":"10.1016\/j.jhepr.2025.101579_bib23","doi-asserted-by":"crossref","first-page":"1941","DOI":"10.1097\/JS9.0000000000001066","article-title":"Evaluation of large language models in breast cancer clinical scenarios: a comparative analysis based on ChatGPT-3.5, ChatGPT-4.0, and Claude2","volume":"110","author":"Deng","year":"2024","journal-title":"Int J Surg"},{"key":"10.1016\/j.jhepr.2025.101579_bib24","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1001\/jamaophthalmol.2023.6917","article-title":"Assessment of a large language model's responses to questions and cases about glaucoma and retina management","volume":"142","author":"Huang","year":"2024","journal-title":"JAMA Ophthalmol"},{"key":"10.1016\/j.jhepr.2025.101579_bib25","unstructured":"Kincaid JP, Fishburne RP, Jr, Rogers RL, et al. Derivation of New Readability Formulas (Automated Readability Index, Fog Count And Flesch Reading Ease Formula) for Navy Enlisted Personnel. Accessed https:\/\/stars.library.ucf.edu\/istlibrary\/56 [Accessed September 3, 2025]."},{"key":"10.1016\/j.jhepr.2025.101579_bib26","first-page":"639","article-title":"SMOG grading-a new readability formula","volume":"12","author":"McLaughlin","year":"1969","journal-title":"J Read"},{"key":"10.1016\/j.jhepr.2025.101579_bib27","doi-asserted-by":"crossref","first-page":"3280","DOI":"10.1038\/s41467-025-56989-2","article-title":"Benchmarking large language models for biomedical natural language processing applications and recommendations","volume":"16","author":"Chen","year":"2025","journal-title":"Nat Commun"},{"key":"10.1016\/j.jhepr.2025.101579_bib28","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1038\/s41746-025-01486-5","article-title":"Multiple large language models versus experienced physicians in diagnosing challenging cases with gastrointestinal symptoms","volume":"8","author":"Yang","year":"2025","journal-title":"NPJ Digit Med"},{"key":"10.1016\/j.jhepr.2025.101579_bib29","doi-asserted-by":"crossref","DOI":"10.2196\/67830","article-title":"Comparing artificial intelligence-generated and clinician-created personalized self-management guidance for patients with knee osteoarthritis: blinded observational study","volume":"27","author":"Du","year":"2025","journal-title":"J Med Internet Res"},{"key":"10.1016\/j.jhepr.2025.101579_bib30","doi-asserted-by":"crossref","first-page":"1323","DOI":"10.1016\/j.cgh.2023.11.008","article-title":"Accuracy of ChatGPT in common gastrointestinal diseases: impact for patients and providers","volume":"22","author":"Kerbage","year":"2024","journal-title":"Clin Gastroenterol Hepatol"},{"key":"10.1016\/j.jhepr.2025.101579_bib31","article-title":"Emerging applications of NLP and large language models in gastroenterology and hepatology: a systematic review","volume":"11","author":"Omar","year":"2024","journal-title":"Front Med"},{"key":"10.1016\/j.jhepr.2025.101579_bib32","doi-asserted-by":"crossref","DOI":"10.1148\/radiol.241073","article-title":"Open-source large language models in radiology: a review and tutorial for practical research and clinical deployment","volume":"314","author":"Savage","year":"2025","journal-title":"Radiology"},{"key":"10.1016\/j.jhepr.2025.101579_bib33","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2024.103004","article-title":"Advancing health coaching: a comparative study of large language model and health coaches","volume":"157","author":"Ong","year":"2024","journal-title":"Artif Intell Med"},{"key":"10.1016\/j.jhepr.2025.101579_bib34","doi-asserted-by":"crossref","DOI":"10.2196\/52597","article-title":"Large language models and empathy: systematic review","volume":"26","author":"Sorin","year":"2024","journal-title":"J Med Internet Res"},{"key":"10.1016\/j.jhepr.2025.101579_bib35","doi-asserted-by":"crossref","DOI":"10.1016\/j.ijmedinf.2024.105562","article-title":"Assessing the response quality and readability of chatbots in cardiovascular health, oncology, and psoriasis: a comparative study","volume":"190","author":"Olszewski","year":"2024","journal-title":"Int J Med Inform"},{"key":"10.1016\/j.jhepr.2025.101579_bib36","doi-asserted-by":"crossref","first-page":"544","DOI":"10.1038\/s41562-023-01783-7","article-title":"Driving and suppressing the human language network using large language models","volume":"8","author":"Tuckute","year":"2024","journal-title":"Nat Hum Behav"},{"key":"10.1016\/j.jhepr.2025.101579_bib37","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2024.22399","article-title":"Large language model-based responses to patients' in-basket messages","volume":"7","author":"Small","year":"2024","journal-title":"JAMA Netw Open"},{"key":"10.1016\/j.jhepr.2025.101579_bib38","doi-asserted-by":"crossref","DOI":"10.2196\/54985","article-title":"The diagnostic ability of GPT-3.5 and GPT-4.0 in surgery: comparative analysis","volume":"26","author":"Liu","year":"2024","journal-title":"J Med Internet Res"},{"key":"10.1016\/j.jhepr.2025.101579_bib39","article-title":"GPT-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv:2303.08774"},{"key":"10.1016\/j.jhepr.2025.101579_bib40","series-title":"Proceedings of the 2022 ACM Conference on fairness, accountability, and transparency","first-page":"214","article-title":"Taxonomy of risks posed by language models","author":"Weidinger","year":"2022"},{"key":"10.1016\/j.jhepr.2025.101579_bib41","doi-asserted-by":"crossref","DOI":"10.2196\/53164","article-title":"Hallucination rates and reference accuracy of ChatGPT and Bard for systematic reviews: comparative analysis","volume":"26","author":"Chelli","year":"2024","journal-title":"J Med Internet Res"},{"key":"10.1016\/j.jhepr.2025.101579_bib42","doi-asserted-by":"crossref","first-page":"1036","DOI":"10.1002\/hep.32689","article-title":"AASLD practice guidance on drug, herbal, and dietary supplement-induced liver injury","volume":"77","author":"Fontana","year":"2023","journal-title":"Hepatology"},{"key":"10.1016\/j.jhepr.2025.101579_bib43","doi-asserted-by":"crossref","first-page":"1222","DOI":"10.1016\/j.jhep.2019.02.014","article-title":"EASL Clinical Practice Guidelines: drug-induced liver injury","volume":"70","year":"2019","journal-title":"J Hepatol"}],"container-title":["JHEP Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2589555925002617?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2589555925002617?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T06:35:32Z","timestamp":1773038132000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2589555925002617"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":43,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["S2589555925002617"],"URL":"https:\/\/doi.org\/10.1016\/j.jhepr.2025.101579","relation":{},"ISSN":["2589-5559"],"issn-type":[{"value":"2589-5559","type":"print"}],"subject":[],"published":{"date-parts":[[2025,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Evaluating large language models' performance in answering common questions on drug-induced liver injury","name":"articletitle","label":"Article Title"},{"value":"JHEP Reports","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jhepr.2025.101579","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Author(s). Published by Elsevier B.V. on behalf of European Association for the Study of the Liver (EASL).","name":"copyright","label":"Copyright"}],"article-number":"101579"}}