{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,13]],"date-time":"2026-11-13T12:38:59Z","timestamp":1794573539377,"version":"4.9.1"},"reference-count":39,"publisher":"Elsevier BV","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T00:00:00Z","timestamp":1779840000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["cell.com","clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Cell Reports Medicine"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.xcrm.2026.102883","type":"journal-article","created":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T14:39:00Z","timestamp":1782398340000},"page":"102883","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":5,"title":["A S.C.O.R.E. framework for evaluating open-ended responses from large language models in healthcare"],"prefix":"10.1016","volume":"7","author":[{"given":"Ting Fang","family":"Tan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kabilan","family":"Elangovan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jasmine","family":"Ong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhe","family":"Ke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aaron","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nigam","family":"Shah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joseph","family":"Sung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tien Yin","family":"Wong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lan","family":"Xue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haibo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang Fu","family":"Kuo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simon","family":"Chesterman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zee Kin","family":"Yeong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2264-7174","authenticated-orcid":false,"given":"Daniel S.W.","family":"Ting","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.xcrm.2026.102883_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.xcrm.2026.102883_bib2","doi-asserted-by":"crossref","DOI":"10.1016\/j.xops.2023.100394","article-title":"Generative artificial intelligence through ChatGPT and other large language models in ophthalmology: clinical applications and challenges","volume":"3","author":"Tan","year":"2023","journal-title":"Ophthalmol. Sci."},{"key":"10.1016\/j.xcrm.2026.102883_bib3","doi-asserted-by":"crossref","first-page":"866","DOI":"10.1001\/jama.2023.14217","article-title":"Creation and Adoption of Large Language Models in Medicine","volume":"330","author":"Shah","year":"2023","journal-title":"JAMA"},{"key":"10.1016\/j.xcrm.2026.102883_bib4","article-title":"Pubmedqa: A Dataset for Biomedical Research Question Answering","author":"Jin","year":"2019","journal-title":"arXiv"},{"key":"10.1016\/j.xcrm.2026.102883_bib5","series-title":"Conference on Health, Inference, and Learning","first-page":"248","article-title":"Medmcqa: A large-scale multi-subject multi-choice dataset for medical domain question answering","author":"Pal","year":"2022"},{"key":"10.1016\/j.xcrm.2026.102883_bib6","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.xcrm.2026.102883_bib7","unstructured":"Hendrycks, D. et al. Measuring Massive Multitask Language Understanding. Preprint at arXiv. (2020)."},{"key":"10.1016\/j.xcrm.2026.102883_bib8","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1186\/s12911-024-02459-6","article-title":"Assessing the research landscape and clinical utility of large language models: a scoping review","volume":"24","author":"Park","year":"2024","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"10.1016\/j.xcrm.2026.102883_bib9","doi-asserted-by":"crossref","DOI":"10.1016\/j.imu.2023.101304","article-title":"Evaluating large language models for use in healthcare: A framework for translational value assessment","volume":"41","author":"Reddy","year":"2023","journal-title":"Inform. Med. Unlocked"},{"key":"10.1016\/j.xcrm.2026.102883_bib10","article-title":"A Comprehensive Survey on Evaluating Large Language Model Applications in the Medical Industry","author":"Huang","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.xcrm.2026.102883_bib11","unstructured":"J\u00f3zefowicz R, Vinyals O, Schuster M, Shazeer NM, Wu Y. Exploring the Limits of Language Modeling. Preprint at arXiv. https:\/\/doi.org\/10.48550\/arXiv.1602.02410."},{"key":"10.1016\/j.xcrm.2026.102883_bib12","series-title":"Proceedings of the 40th annual meeting on association for computational linguistics","first-page":"311","article-title":"BLEU: a method for automatic evaluation of machine translation","author":"Papineni","year":"2002"},{"key":"10.1016\/j.xcrm.2026.102883_bib13","series-title":"Annual meeting of the association for computational linguistics","article-title":"Rouge: A Package for Automatic Evaluation of Summaries. 2004","author":"Lin","year":"2004"},{"key":"10.1016\/j.xcrm.2026.102883_bib14","article-title":"Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation","author":"Powers","year":"2011","journal-title":"arXiv"},{"key":"10.1016\/j.xcrm.2026.102883_bib15","article-title":"Bertscore: Evaluating Text Generation with Bert.","author":"Zhang","year":"2019","journal-title":"arXiv"},{"key":"10.1016\/j.xcrm.2026.102883_bib16","series-title":"Proc. ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization 65\u201372","article-title":"METEOR: an automatic metric for MT evaluation with improved correlation with human judgments","author":"Banerjee","year":"2005"},{"key":"10.1016\/j.xcrm.2026.102883_bib17","article-title":"EYE-Llama, an in-domain large language model for ophthalmology","author":"Haghighi","year":"2024","journal-title":"bioRxiv"},{"key":"10.1016\/j.xcrm.2026.102883_bib18","article-title":"Language Enhanced Model for Eye (LEME): An Open-Source Ophthalmology-Specific Large Language Model","author":"Gilson","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.xcrm.2026.102883_bib19","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1001\/jama.2024.21700","article-title":"Testing and Evaluation of Health Care Applications of Large Language Models: A Systematic Review","volume":"333","author":"Bedi","year":"2025","journal-title":"JAMA"},{"key":"10.1016\/j.xcrm.2026.102883_bib20","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1186\/s12911-024-02757-z","article-title":"Qualitative metrics from the biomedical literature for evaluating large language models in clinical decision-making: a narrative review","volume":"24","author":"Ho","year":"2024","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"10.1016\/j.xcrm.2026.102883_bib21","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"},{"key":"10.1016\/j.xcrm.2026.102883_bib22","article-title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","author":"Liu","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.xcrm.2026.102883_bib23","article-title":"Reporting guidelines for chatbot health advice studies: explanation and elaboration for the Chatbot Assessment Reporting Tool (CHART)","volume":"390","year":"2025","journal-title":"BMJ"},{"key":"10.1016\/j.xcrm.2026.102883_bib24","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1038\/s41591-024-03425-5","article-title":"The TRIPOD-LLM reporting guideline for studies using large language models","volume":"31","author":"Gallifant","year":"2025","journal-title":"Nat. Med."},{"key":"10.1016\/j.xcrm.2026.102883_bib25","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1038\/s41591-024-03328-5","article-title":"An evaluation framework for clinical use of large language models in patient interaction tasks","volume":"31","author":"Johri","year":"2025","journal-title":"Nat. Med."},{"key":"10.1016\/j.xcrm.2026.102883_bib26","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."},{"key":"10.1016\/j.xcrm.2026.102883_bib27","doi-asserted-by":"crossref","first-page":"3270","DOI":"10.1038\/s41591-025-03983-2","article-title":"Generative artificial intelligence in medicine","volume":"31","author":"Teo","year":"2025","journal-title":"Nat. Med."},{"key":"10.1016\/j.xcrm.2026.102883_bib28","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-024-79531-8","article-title":"Testing AI on language comprehension tasks reveals insensitivity to underlying meaning","volume":"14","author":"Dentella","year":"2024","journal-title":"Sci. Rep."},{"key":"10.1016\/j.xcrm.2026.102883_bib29","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1038\/s41746-025-01519-z","article-title":"Retrieval augmented generation for 10 large language models and its generalizability in assessing medical fitness","volume":"8","author":"Ke","year":"2025","journal-title":"npj Digit. Med."},{"key":"10.1016\/j.xcrm.2026.102883_bib31","article-title":"Fine-Tuning Large Language Model (LLM) Artificial Intelligence Chatbots in Ophthalmology and LLM-Based Evaluation Using GPT-4","author":"Tan","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.xcrm.2026.102883_bib32","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pdig.0000961","article-title":"Development and evaluation of a lightweight large language model chatbot for medication enquiry","volume":"4","author":"Elangovan","year":"2025","journal-title":"PLOS Digit Health"},{"key":"10.1016\/j.xcrm.2026.102883_bib33","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1007\/s13735-024-00334-8","article-title":"Adversarial attacks and defenses for large language models (LLMs): methods, frameworks & challenges","volume":"13","author":"Kumar","year":"2024","journal-title":"Int. J. Multimed. Inf. Retr."},{"key":"10.1016\/j.xcrm.2026.102883_bib34","article-title":"Towards Safe and Aligned Large Language Models for Medicine","author":"Han","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.xcrm.2026.102883_bib35","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1093\/jamia\/ocz192","article-title":"A governance model for the application of AI in health care","volume":"27","author":"Reddy","year":"2020","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"10.1016\/j.xcrm.2026.102883_bib36","series-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","first-page":"681","article-title":"USR: An unsupervised and reference free evaluation metric for dialog generation","author":"Mehri","year":"2020"},{"key":"10.1016\/j.xcrm.2026.102883_bib37","article-title":"Gpteval: Nlg Evaluation Using Gpt-4 with Better Human Alignment","author":"Liu","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.xcrm.2026.102883_bib38","article-title":"Llm-eval: Unified Multi-Dimensional Automatic Evaluation for Open-Domain Conversations with Large Language Models","author":"Lin","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.xcrm.2026.102883_bib39","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3641289","article-title":"A survey on evaluation of large language models","volume":"15","author":"Chang","year":"2024","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"10.1016\/j.xcrm.2026.102883_bib40","article-title":"Clinical Validation of Medical-Based Large Language Model Chatbots on Ophthalmic Patient Queries with LLM-Based Evaluation","author":"Tan","year":"2026","journal-title":"arXiv"}],"container-title":["Cell Reports Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2666379126003009?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2666379126003009?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T15:08:07Z","timestamp":1784646487000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2666379126003009"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":39,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["S2666379126003009"],"URL":"https:\/\/doi.org\/10.1016\/j.xcrm.2026.102883","relation":{},"ISSN":["2666-3791"],"issn-type":[{"value":"2666-3791","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A S.C.O.R.E. framework for evaluating open-ended responses from large language models in healthcare","name":"articletitle","label":"Article Title"},{"value":"Cell Reports Medicine","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.xcrm.2026.102883","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"102883"}}