{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T12:09:49Z","timestamp":1784117389951,"version":"3.55.0"},"reference-count":43,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100004731","name":"Zhejiang Province Natural Science Foundation","doi-asserted-by":"publisher","award":["LHZSZ25H090002"],"award-info":[{"award-number":["LHZSZ25H090002"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Biomedical Informatics"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.jbi.2026.105072","type":"journal-article","created":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T16:36:08Z","timestamp":1782146168000},"page":"105072","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Beyond Accuracy: Safety-Centered guidelines for the evaluation of LLM-based therapy recommendation systems for chronic multimorbidity patients"],"prefix":"10.1016","volume":"180","author":[{"given":"Yicong","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Irit","family":"Hochberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhoujian","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruth","family":"Edry","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengxing","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5612-768X","authenticated-orcid":false,"given":"Mor","family":"Peleg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.jbi.2026.105072_b0005","doi-asserted-by":"crossref","first-page":"e35","DOI":"10.1016\/S2589-7500(24)00246-2","article-title":"The potential of Generative Pre-trained Transformer 4 (GPT-4) to analyse medical notes in three different languages: a retrospective model-evaluation study","volume":"7","author":"Menezes","year":"2025","journal-title":"Lancet Digit. Heal."},{"issue":"8","key":"10.1016\/j.jbi.2026.105072_b0010","doi-asserted-by":"crossref","first-page":"2550","DOI":"10.1038\/s41591-025-03726-3","article-title":"Comparative benchmarking of the DeepSeek large language model on medical tasks and clinical reasoning","volume":"31","author":"Tordjman","year":"2025","journal-title":"Nat. Med."},{"key":"10.1016\/j.jbi.2026.105072_b0015","article-title":"A scoping review on generative AI and large language models in mitigating medication related harm. npj Digit","volume":"8(1):182","author":"Ong","year":"2025","journal-title":"Med"},{"issue":"1","key":"10.1016\/j.jbi.2026.105072_b0020","article-title":"Assuring the safety of AI-based clinical decision support systems: a case study of the AI Clinician for sepsis treatment","volume":"29","author":"Festor","year":"2022","journal-title":"BMJ Heal. Care Inf."},{"key":"10.1016\/j.jbi.2026.105072_b0025","doi-asserted-by":"crossref","DOI":"10.2196\/56121","article-title":"Quality and Accountability of ChatGPT in Health Care in Low- and Middle-Income Countries: simulated Patient Study","volume":"26","author":"Si","year":"2024","journal-title":"J. Med. Internet Res."},{"issue":"1","key":"10.1016\/j.jbi.2026.105072_b0030","doi-asserted-by":"crossref","first-page":"9377","DOI":"10.1038\/s41467-025-64430-x","article-title":"AgentMD: Empowering Language Agents for Risk Prediction with Large-Scale Clinical Tool Learning","volume":"16","author":"Jin","year":"2025","journal-title":"Nat. Commun."},{"key":"10.1016\/j.jbi.2026.105072_b0035","first-page":"19","article-title":"LLMs-based Few-Shot Disease predictions using EHR: a Novel Approach Combining Predictive Agent reasoning and critical Agent Instruction","author":"Cui","year":"2024","journal-title":"AMIA Annu. Symp. Proc."},{"key":"10.1016\/j.jbi.2026.105072_b0040","series-title":"In: Proceedings of the 31st International Conference on Computational Linguistics","first-page":"10183","article-title":"AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator","author":"Fan","year":"2025"},{"key":"10.1016\/j.jbi.2026.105072_b0045","article-title":"Enhancing diagnostic capability with multi-agents conversational large language models","volume":"8(1):159","author":"Chen","year":"2025","journal-title":"Npj Digit Med."},{"key":"10.1016\/j.jbi.2026.105072_b0050","series-title":"In: Proceedings of the ACM on Web Conference","first-page":"2250","article-title":"Enhancing Electronic Health Record Modeling through Large Language Model-Driven Multi-Agent Collaboration","author":"Wang","year":"2025"},{"key":"10.1016\/j.jbi.2026.105072_b0055","article-title":"A community-of-practice-based evaluation methodology for knowledge intensive computational methods and its application to multimorbidity decision support","volume":"142","author":"Van","year":"2023","journal-title":"J. Biomed. Inform."},{"key":"10.1016\/j.jbi.2026.105072_b0060","doi-asserted-by":"crossref","first-page":"989","DOI":"10.1093\/gerona\/glv013","article-title":"Polypharmacy among adults aged 65 years and older in the United States: 1988\u20132010","volume":"70","author":"Charlesworth","year":"2015","journal-title":"J. Gerontol. A Biol. Sci. Med. Sci."},{"key":"10.1016\/j.jbi.2026.105072_b0065","first-page":"i66","article-title":"Modeling polypharmacy side effects with graph convolutional networks","volume":"34","author":"Zitnik","year":"2018","journal-title":"Bioinformatics. Bioinformatics."},{"issue":"1","key":"10.1016\/j.jbi.2026.105072_b0070","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1197\/jamia.M1135","article-title":"Comparing Computer-Interpretable Guideline Models: a Case-Study Approach","volume":"10","author":"Peleg","year":"2003","journal-title":"J Am Med Inf. Assoc."},{"key":"10.1016\/j.jbi.2026.105072_b0075","series-title":"In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","first-page":"1315","article-title":"Learning to prescribe effective and safe treatment combinations for multimorbidity","author":"Zhang","year":"2017"},{"key":"10.1016\/j.jbi.2026.105072_b0080","series-title":"In: Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","first-page":"3735","article-title":"Dual Molecular Graph Encoders for Recommending Effective and Safe Drug Combinations","author":"Yang","year":"2021"},{"key":"10.1016\/j.jbi.2026.105072_b0085","doi-asserted-by":"crossref","DOI":"10.1016\/j.bdr.2020.100174","article-title":"SMR: Medical Knowledge Graph Embedding for Safe Medicine Recommendation","volume":"23","author":"Gong","year":"2021","journal-title":"Big Data Res."},{"key":"10.1016\/j.jbi.2026.105072_b0090","series-title":"In: Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence","first-page":"1126","article-title":"GAMENet: graph augmented memory networks for recommending medication combination","author":"Shang","year":"2011"},{"key":"10.1016\/j.jbi.2026.105072_b0095","article-title":"MGRN: toward robust drug recommendation via multi-view gating retrieval network","volume":"40(10):btae572","author":"Meng","year":"2024","journal-title":"Bioinformatics"},{"key":"10.1016\/j.jbi.2026.105072_b0100","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2023.104301","article-title":"DGCL: Distance-wise and Graph Contrastive Learning for medication recommendation","volume":"139","author":"Li","year":"2023","journal-title":"J Biomed Inf."},{"issue":"6","key":"10.1016\/j.jbi.2026.105072_b0105","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1109\/MIS.2018.2886697","article-title":"GLARE-SSCPM\u00a0: an Intelligent System to support the Treatment of Comorbid GLARE-SSCPM\u00a0: an Intelligent System to support the Treatment of Comorbid patients","volume":"33","author":"Piovesan","year":"2018","journal-title":"IEEE Intell. Syst."},{"key":"10.1016\/j.jbi.2026.105072_b0110","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2021.102127","article-title":"Decision support for comorbid conditions via execution-time integration of clinical guidelines using transaction-based semantics and temporal planning","volume":"118","author":"Van Woensel","year":"2021","journal-title":"Artif. Intell. Med."},{"issue":"September","key":"10.1016\/j.jbi.2026.105072_b0115","article-title":"Towards a goal-oriented methodology for clinical-guideline-based management recommendations for patients with multimorbidity: GoCom and its preliminary evaluation","volume":"112","author":"Kogan","year":"2020","journal-title":"J. Biomed. Inform."},{"key":"10.1016\/j.jbi.2026.105072_b0120","first-page":"291","article-title":"Ontological approach for safe and effective polypharmacy prescription","author":"Grando","year":"2012","journal-title":"AMIA Annu. Symp. Proc."},{"key":"10.1016\/j.jbi.2026.105072_b0125","doi-asserted-by":"crossref","unstructured":"Litchfield I, Turner A, PALMER R, Filho JBF, Weber P. Automated conflict resolution between multiple clinical pathways: a technology report. J Innov Heal. Inform. 2018;25(3):142\u20138.","DOI":"10.14236\/jhi.v25i3.986"},{"issue":"13","key":"10.1016\/j.jbi.2026.105072_b0130","doi-asserted-by":"crossref","first-page":"1598","DOI":"10.3390\/healthcare13131598","article-title":"ChatGPT Performance Deteriorated in patients with Comorbidities when Providing Cardiological Therapeutic Consultations","volume":"13","author":"Hao","year":"2025","journal-title":"Healthcare"},{"issue":"1","key":"10.1016\/j.jbi.2026.105072_b0135","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1007\/s10916-024-02058-y","article-title":"Proactive Polypharmacy Management using Large Language Models: Opportunities to Enhance Geriatric Care","volume":"48","author":"Rao","year":"2024","journal-title":"J. Med. Syst."},{"issue":"10","key":"10.1016\/j.jbi.2026.105072_b0140","article-title":"Large language model as clinical decision support system augments medication safety in 16 clinical specialties","volume":"6","author":"Ong","year":"2025","journal-title":"Cell Rep. Med."},{"issue":"1","key":"10.1016\/j.jbi.2026.105072_b0145","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1186\/s12911-025-03181-7","article-title":"Evaluating the performance of ChatGPT in clinical multidisciplinary treatment: a retrospective study","volume":"25","author":"Wang","year":"2025","journal-title":"BMC Med Inf. Decis Mak."},{"issue":"4","key":"10.1016\/j.jbi.2026.105072_b0150","doi-asserted-by":"crossref","first-page":"1142","DOI":"10.1002\/cpt.3585","article-title":"ChatGPT vs. Clinical Decision support Systems in the Analysis of Drug-Drug Interactions","volume":"117","author":"Bischof","year":"2025","journal-title":"Clin. Pharmacol. Ther."},{"key":"10.1016\/j.jbi.2026.105072_b0155","doi-asserted-by":"crossref","DOI":"10.2196\/69504","article-title":"Identifying Deprescribing Opportunities with Large Language Models in older adults: Retrospective Cohort Study","volume":"8","author":"Socrates","year":"2025","journal-title":"JMIR Aging."},{"key":"10.1016\/j.jbi.2026.105072_b0160","doi-asserted-by":"crossref","first-page":"8236","DOI":"10.1038\/s41467-024-52415-1","article-title":"Evaluating the use of large language models to provide clinical recommendations in the Emergency Department","volume":"15","author":"Williams","year":"2024","journal-title":"Nat. Commun."},{"key":"10.1016\/j.jbi.2026.105072_b0165","first-page":"1","article-title":"A collaborative large language model for drug analysis","author":"Zhou","year":"2025","journal-title":"Nat. Biomed. Eng."},{"issue":"1","key":"10.1016\/j.jbi.2026.105072_b0170","doi-asserted-by":"crossref","first-page":"154","DOI":"10.3390\/electronics14010154","article-title":"KELLM: Knowledge-Enhanced Label-Wise Large Language Model for Safe and Interpretable Drug Recommendation","volume":"14","author":"Xu","year":"2025","journal-title":"Electronics"},{"key":"10.1016\/j.jbi.2026.105072_b0175","first-page":"920","article-title":"Towards a framework for comparing functionalities of multimorbidity clinical decision support: a literature-based feature set and bench","author":"O\u2019Sullivan","year":"2021","journal-title":"In: AMIA Annual Symposium Proceedings. American Medical Informatics Association"},{"issue":"9","key":"10.1016\/j.jbi.2026.105072_b0180","doi-asserted-by":"crossref","first-page":"1477","DOI":"10.1093\/jamia\/ocaf110","article-title":"Human-centered explainability evaluation in clinical decision-making: a critical review of the literature","volume":"32","author":"Bauer","year":"2025","journal-title":"J. Am. Med. Informatics Assoc."},{"issue":"194","key":"10.1016\/j.jbi.2026.105072_b0185","first-page":"4","article-title":"SUS-A quick and dirty usability scale","volume":"189","author":"Brooke","year":"1996","journal-title":"Usability Eval. Ind."},{"issue":"3","key":"10.1016\/j.jbi.2026.105072_b0190","doi-asserted-by":"crossref","first-page":"319","DOI":"10.2307\/249008","article-title":"Perceived usefulness, perceived ease of use, and user acceptance of information technology","volume":"13","author":"Davis","year":"1989","journal-title":"MIS Q."},{"issue":"4","key":"10.1016\/j.jbi.2026.105072_b0195","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1016\/j.ijmedinf.2015.01.004","article-title":"A multiple-scenario assessment of the effect of a continuous-care, guideline-based decision support system on clinicians\u2019 compliance to clinical guidelines","volume":"84","author":"Shalom","year":"2015","journal-title":"Int. J. Med. Informatics, Press."},{"issue":"1","key":"10.1016\/j.jbi.2026.105072_b0200","article-title":"Advancing clinical chatbot validation using ai-powered evaluation with a new 3-bot evaluation system: Instrument validation study","volume":"8","author":"Choo","year":"2025","journal-title":"JMIR Nurs."},{"issue":"1","key":"10.1016\/j.jbi.2026.105072_b0205","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.jbi.2026.105072_b0210","article-title":"Rapidly benchmarking large language models for diagnosing comorbid patients: comparative study leveraging the LLM-as-a-judge method","volume":"6","author":"Sarvari","year":"2025","journal-title":"Jmirx Med."},{"key":"10.1016\/j.jbi.2026.105072_b0215","article-title":"Autonomous medical evaluation for guideline adherence of large language models 2024. npj Digit","volume":"7(1):358","author":"Fast","year":"2024","journal-title":"Med"}],"container-title":["Journal of Biomedical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1532046426000961?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1532046426000961?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T11:26:05Z","timestamp":1784114765000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1532046426000961"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":43,"alternative-id":["S1532046426000961"],"URL":"https:\/\/doi.org\/10.1016\/j.jbi.2026.105072","relation":{},"ISSN":["1532-0464"],"issn-type":[{"value":"1532-0464","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Beyond Accuracy: Safety-Centered guidelines for the evaluation of LLM-based therapy recommendation systems for chronic multimorbidity patients","name":"articletitle","label":"Article Title"},{"value":"Journal of Biomedical Informatics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jbi.2026.105072","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"105072"}}