{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,9]],"date-time":"2026-11-09T13:24:44Z","timestamp":1794230684891,"version":"4.9.0"},"reference-count":54,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Medical Informatics"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.ijmedinf.2026.106760","type":"journal-article","created":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T23:15:43Z","timestamp":1791414943000},"page":"106760","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Trustworthy large language models for clinical diagnosis: a medical informatics review of evidence, safety, validation, and deployment readiness"],"prefix":"10.1016","volume":"223","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5567-6521","authenticated-orcid":false,"given":"Amar","family":"Singh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ajay","family":"Singh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shakti","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sahraoui","family":"Dhelim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6154-9237","authenticated-orcid":false,"given":"Chatter","family":"Singh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.ijmedinf.2026.106760_bib0005","series-title":"Improving Diagnosis in Health Care","year":"2015"},{"issue":"2","key":"10.1016\/j.ijmedinf.2026.106760_bib0010","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1136\/bmjqs-2021-014130","article-title":"Burden of serious harms from diagnostic error in the USA","volume":"33","author":"Newman-Toker","year":"2024","journal-title":"BMJ Qual. Saf."},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0015","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."},{"issue":"7956","key":"10.1016\/j.ijmedinf.2026.106760_bib0020","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1038\/s41586-023-05881-4","article-title":"Foundation models for generalist medical artificial intelligence","volume":"616","author":"Moor","year":"2023","journal-title":"Nature"},{"issue":"7972","key":"10.1016\/j.ijmedinf.2026.106760_bib0025","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","article-title":"Large language models encode clinical knowledge","volume":"620","author":"Singhal","year":"2023","journal-title":"Nature"},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0030","doi-asserted-by":"crossref","first-page":"943","DOI":"10.1038\/s41591-024-03423-7","article-title":"Toward expert-level medical question answering with large language models","volume":"31","author":"Singhal","year":"2025","journal-title":"Nat. Med."},{"issue":"7969","key":"10.1016\/j.ijmedinf.2026.106760_bib0035","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1038\/s41586-023-06160-y","article-title":"Health system-scale language models are all-purpose prediction engines","volume":"619","author":"Jiang","year":"2023","journal-title":"Nature"},{"issue":"1","key":"10.1016\/j.ijmedinf.2026.106760_bib0040","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1001\/jama.2023.8288","article-title":"Accuracy of a generative artificial intelligence model in a complex diagnostic challenge","volume":"330","author":"Kanjee","year":"2023","journal-title":"JAMA"},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0045","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1038\/s41746-025-01556-8","article-title":"Preliminary analysis of the impact of lab results on large language model generated differential diagnoses","volume":"8","author":"Bhasuran","year":"2025","journal-title":"NPJ Digit. Med."},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0050","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.ijmedinf.2026.106760_bib0055","article-title":"RareArena: a comprehensive benchmark dataset unveiling the potential of large language models in rare disease diagnosis","volume":"8","author":"Chen","year":"2026","journal-title":"Lancet Digit. Health"},{"issue":"10","key":"10.1016\/j.ijmedinf.2026.106760_bib0060","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"},{"issue":"8067","key":"10.1016\/j.ijmedinf.2026.106760_bib0065","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1038\/s41586-025-08869-4","article-title":"Towards accurate differential diagnosis with large language models","volume":"642","author":"McDuff","year":"2025","journal-title":"Nature"},{"issue":"8067","key":"10.1016\/j.ijmedinf.2026.106760_bib0070","doi-asserted-by":"crossref","first-page":"442","DOI":"10.1038\/s41586-025-08866-7","article-title":"Towards conversational diagnostic artificial intelligence","volume":"642","author":"Tu","year":"2025","journal-title":"Nature"},{"issue":"4","key":"10.1016\/j.ijmedinf.2026.106760_bib0075","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2026.4003","article-title":"Large language model performance and clinical reasoning tasks","volume":"9","author":"Rao","year":"2026","journal-title":"JAMA Netw. Open"},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0080","doi-asserted-by":"crossref","first-page":"1671","DOI":"10.1038\/s41591-026-04297-7","article-title":"ChatGPT health performance in a structured test of triage recommendations","volume":"32","author":"Ramaswamy","year":"2026","journal-title":"Nat. Med."},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0085","doi-asserted-by":"crossref","DOI":"10.1016\/j.ijmedinf.2025.106091","article-title":"Performance and improvement strategies for adapting generative large language models for electronic health record applications: a systematic review","volume":"205","author":"Du","year":"2026","journal-title":"Int. J. Med. Inform."},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0090","doi-asserted-by":"crossref","DOI":"10.1016\/j.ijmedinf.2025.106204","article-title":"Applications of artificial intelligence-based conversational agents in healthcare: a systematic umbrella review","volume":"207","author":"Huynh","year":"2026","journal-title":"Int. J. Med. Inform."},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0095","doi-asserted-by":"crossref","DOI":"10.1016\/j.ijmedinf.2025.106227","article-title":"Vision-language models in diagnostic imaging: review of technical advances, clinical validation, and practical deployment","volume":"208","author":"Dutta","year":"2026","journal-title":"Int. J. Med. Inform."},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0100","doi-asserted-by":"crossref","DOI":"10.1016\/j.ijmedinf.2025.106231","article-title":"Advancing healthcare with large language models: a scoping review of applications and future directions","volume":"208","author":"Zhang","year":"2026","journal-title":"Int. J. Med. Inform."},{"issue":"1","key":"10.1016\/j.ijmedinf.2026.106760_bib0105","doi-asserted-by":"crossref","first-page":"e12","DOI":"10.1016\/S2589-7500(23)00225-X","article-title":"Assessing the potential of GPT-4 to perpetuate racial and gender biases in health care: a model evaluation study","volume":"6","author":"Zack","year":"2024","journal-title":"Lancet Digit. Health"},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0110","doi-asserted-by":"crossref","DOI":"10.3389\/fdgth.2025.1659134","article-title":"Large language models in real-world clinical workflows: a systematic review of applications and implementation","volume":"7","author":"Artsi","year":"2025","journal-title":"Front. Digit. Health"},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0115","doi-asserted-by":"crossref","DOI":"10.1038\/s41591-026-04601-5","article-title":"Prospective evaluation of a large language model clinical decision support system in the emergency department","author":"Leibovitch","year":"2026","journal-title":"Nat. Med."},{"issue":"5","key":"10.1016\/j.ijmedinf.2026.106760_bib0120","doi-asserted-by":"crossref","DOI":"10.1093\/jamiaopen\/ooaf119","article-title":"Grounded large language models for diagnostic prediction in real-world emergency department settings","volume":"8","author":"Niset","year":"2025","journal-title":"JAMIA Open"},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0125","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1186\/s12916-019-1426-2","article-title":"Key challenges for delivering clinical impact with artificial intelligence","volume":"17","author":"Kelly","year":"2019","journal-title":"BMC Med."},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0130","article-title":"Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims of deep learning studies","volume":"368","author":"Nagendran","year":"2020","journal-title":"BMJ"},{"issue":"6","key":"10.1016\/j.ijmedinf.2026.106760_bib0135","doi-asserted-by":"crossref","first-page":"e271","DOI":"10.1016\/S2589-7500(19)30123-2","article-title":"A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis","volume":"1","author":"Liu","year":"2019","journal-title":"Lancet Digit. Health"},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0140","article-title":"Evaluation of symptom checkers for self diagnosis and triage: audit study","volume":"351","author":"Semigran","year":"2015","journal-title":"BMJ"},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0145","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1038\/s41746-026-02428-5","article-title":"Large language models provide unsafe answers to patient-posed medical questions","volume":"9","author":"Draelos","year":"2026","journal-title":"NPJ Digit. Med."},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0150","doi-asserted-by":"crossref","first-page":"609","DOI":"10.1038\/s41591-025-04074-y","article-title":"Reliability of LLMs as medical assistants for the general public: a randomized preregistered study","volume":"32","author":"Bean","year":"2026","journal-title":"Nat. Med."},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0155","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1038\/s41746-023-00879-8","article-title":"The shaky foundations of large language models and foundation models for electronic health records","volume":"6","author":"Wornow","year":"2023","journal-title":"NPJ Digit. Med."},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0160","doi-asserted-by":"crossref","DOI":"10.1016\/j.ijmedinf.2025.106225","article-title":"De-identification of clinical data: a systematic review of free text, image and tabular data approaches","volume":"208","author":"Faustini","year":"2026","journal-title":"Int. J. Med. Inform."},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0165","doi-asserted-by":"crossref","DOI":"10.1016\/j.ijmedinf.2025.106220","article-title":"Effectiveness of computerized decision support systems linked to electronic health records: an updated systematic review with meta-analysis","volume":"207","author":"Biffi","year":"2026","journal-title":"Int. J. Med. Inform."},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0170","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1038\/s41746-020-0253-3","article-title":"Presenting machine learning model information to clinical end users with model facts labels","volume":"3","author":"Sendak","year":"2020","journal-title":"NPJ Digit. Med."},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0175","doi-asserted-by":"crossref","first-page":"2613","DOI":"10.1038\/s41591-024-03097-1","article-title":"Evaluation and mitigation of the limitations of large language models in clinical decision-making","volume":"30","author":"Hager","year":"2024","journal-title":"Nat. Med."},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0180","doi-asserted-by":"crossref","first-page":"642","DOI":"10.1038\/s41467-024-55628-6","article-title":"Large language models lack essential metacognition for reliable medical reasoning","volume":"16","author":"Griot","year":"2025","journal-title":"Nat. Commun."},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0185","doi-asserted-by":"crossref","DOI":"10.1016\/j.ijmedinf.2025.106224","article-title":"Generative artificial intelligence as a source of advice on resuscitation and first aid for laypeople: a scoping review","volume":"207","author":"Birkun","year":"2026","journal-title":"Int. J. Med. Inform."},{"issue":"6464","key":"10.1016\/j.ijmedinf.2026.106760_bib0190","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1126\/science.aax2342","article-title":"Dissecting racial bias in an algorithm used to Manage the health of populations","volume":"366","author":"Obermeyer","year":"2019","journal-title":"Science"},{"issue":"6","key":"10.1016\/j.ijmedinf.2026.106760_bib0195","doi-asserted-by":"crossref","first-page":"e406","DOI":"10.1016\/S2589-7500(22)00063-2","article-title":"AI recognition of patient race in medical imaging: a modelling study","volume":"4","author":"Gichoya","year":"2022","journal-title":"Lancet Digit. Health"},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0200","doi-asserted-by":"crossref","DOI":"10.1016\/j.ijmedinf.2025.106173","article-title":"Digital health disparities: a review of barriers and solutions for racially diverse groups","volume":"206","author":"Teke","year":"2026","journal-title":"Int. J. Med. Inform."},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0205","article-title":"Large language models and global health equity: a roadmap for equitable adoption in LMICs","volume":"63","author":"Chen","year":"2025","journal-title":"Lancet Reg. Health \u2013 West. Pac."},{"issue":"Suppl 3","key":"10.1016\/j.ijmedinf.2026.106760_bib0210","doi-asserted-by":"crossref","first-page":"i68","DOI":"10.1136\/qshc.2010.042085","article-title":"A new sociotechnical model for studying health information technology in complex adaptive healthcare systems","volume":"19","author":"Sittig","year":"2010","journal-title":"Qual. Saf. Health Care"},{"issue":"5","key":"10.1016\/j.ijmedinf.2026.106760_bib0215","first-page":"418","article-title":"The SAFER guides: empowering organizations to improve the safety and effectiveness of electronic health records","volume":"20","author":"Sittig","year":"2014","journal-title":"Am. J. Manag. Care"},{"issue":"4","key":"10.1016\/j.ijmedinf.2026.106760_bib0220","doi-asserted-by":"crossref","first-page":"755","DOI":"10.1093\/jamia\/ocaf018","article-title":"Revisions to the safety assurance factors for electronic health record resilience (SAFER) guides to update national recommendations for safe use of electronic health records","volume":"32","author":"Sittig","year":"2025","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0260","series-title":"Ethics and Governance of Artificial Intelligence for Health: Guidance on Large Multi-Modal Models","year":"2024"},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0265","series-title":"Artificial Intelligence Risk Management Framework (AI RMF 1.0)","year":"2023"},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0285","doi-asserted-by":"crossref","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","year":"2024","journal-title":"BMJ"},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0290","doi-asserted-by":"crossref","DOI":"10.1136\/bmj-2024-082505","article-title":"PROBAST+AI: an updated quality, risk of bias, and applicability assessment tool for prediction models using regression or artificial intelligence methods","volume":"388","author":"Moons","year":"2025","journal-title":"BMJ"},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0295","doi-asserted-by":"crossref","first-page":"3283","DOI":"10.1038\/s41591-025-03953-8","article-title":"The STARD-AI reporting guideline for diagnostic accuracy studies using artificial intelligence","volume":"31","author":"Sounderajah","year":"2025","journal-title":"Nat. Med."},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0300","doi-asserted-by":"crossref","first-page":"1364","DOI":"10.1038\/s41591-020-1034-x","article-title":"Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI extension","volume":"26","author":"Liu","year":"2020","journal-title":"Nat. Med."},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0305","doi-asserted-by":"crossref","first-page":"1351","DOI":"10.1038\/s41591-020-1037-7","article-title":"Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI extension","volume":"26","author":"Rivera","year":"2020","journal-title":"Nat. Med."},{"issue":"5","key":"10.1016\/j.ijmedinf.2026.106760_bib0310","doi-asserted-by":"crossref","first-page":"924","DOI":"10.1038\/s41591-022-01772-9","article-title":"Reporting guideline for the early-stage clinical evaluation of decision support systems driven by artificial intelligence: DECIDE-AI","volume":"28","author":"Vasey","year":"2022","journal-title":"Nat. Med."},{"issue":"4","key":"10.1016\/j.ijmedinf.2026.106760_bib0315","doi-asserted-by":"crossref","DOI":"10.1148\/ryai.240300","article-title":"Checklist for artificial intelligence in medical imaging (CLAIM): 2024 update","volume":"6","author":"Tejani","year":"2024","journal-title":"Radiol. Artif. Intell."},{"key":"10.1016\/j.ijmedinf.2026.106760_bib0320","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1186\/s12916-025-04274-w","article-title":"Reporting guideline for chatbot health advice studies: the CHART statement","volume":"23","author":"Huo","year":"2025","journal-title":"BMC Med."}],"container-title":["International Journal of Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1386505626005009?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1386505626005009?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,11,9]],"date-time":"2026-11-09T12:29:38Z","timestamp":1794227378000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1386505626005009"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":54,"alternative-id":["S1386505626005009"],"URL":"https:\/\/doi.org\/10.1016\/j.ijmedinf.2026.106760","relation":{},"ISSN":["1386-5056"],"issn-type":[{"value":"1386-5056","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Trustworthy large language models for clinical diagnosis: a medical informatics review of evidence, safety, validation, and deployment readiness","name":"articletitle","label":"Article Title"},{"value":"International Journal of Medical Informatics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ijmedinf.2026.106760","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"106760"}}