[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3085":3,"related-3085":58},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":18,"tags":20,"primary_topic":9,"secondary_topics":21,"classification":22,"search_phrases":37,"slug":38,"view_count":39,"doi":40,"paper":41,"created_at":57},3085,"Large language models in healthcare: applications, evaluation frameworks, and governance pathways — a scoping review and multidimensional framework","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffdgth.2026.1865568","Background Large language models (LLMs) are increasingly evaluated for healthcare applications spanning clinical documentation, decision support, patient communication, research assistance, and operational workflows. Despite rapid adoption interest, evidence remains heterogeneous and standardised approaches for evaluation and governance are not yet consistently applied. Objective To map healthcare applications of LLMs, synthesise reported outcomes and risks, and propose a multidimensional evaluation and governance framework oriented toward digital-health implementation. Methods A scoping review was conducted following the methodological guidance of Arksey and O'Malley, Levac et al., and the Joanna Briggs Institute, with reporting aligned to the PRISMA-ScR checklist. The protocol was prospectively registered on the Open Science Framework https:\u002F\u002Fdoi.org\u002F10.17605\u002FOSF.IO\u002FSWP78 ). Searches were performed in PubMed\u002FMEDLINE, Embase, Scopus, Web of Science, IEEE Xplore, ACM Digital Library, and the ACL Anthology, supplemented by medRxiv\u002FbioRxiv preprint searches and grey-literature scanning of WHO, FDA, and EU AI-Office guidance, covering 1 January 2019–30 April 2026. Title\u002Fabstract and full-text screening were carried out in duplicate; inter-rater agreement was Cohen's κ = 0.78. Data were extracted in duplicate using a piloted form. Synthesis followed Braun and Clarke's six-phase reflexive thematic analysis. The complete list of 78 included studies is provided in Supplementary File S4. Results Seventy-eight studies met inclusion criteria; 68% were published between 2023 and 2025. Five application domains were identified: (1) clinical documentation and summarisation; (2) clinical decision support and reasoning assistance; (3) patient communication and health-literacy support; (4) biomedical research and knowledge synthesis; and (5) administrative and operational use cases. The evidence base was dominated by benchmark and simulated-workflow studies (89%), with limited prospective workflow-embedded evaluations (11%). Reported benefits concentrated on documentation efficiency, text quality, and knowledge synthesis; safety-relevant risks included hallucinated content, omission of clinically critical information, demographic bias, privacy vulnerabilities, limited explainability, and automation bias. Studies were geographically concentrated in North America and East Asia, with limited representation from Sub-Saharan Africa, South Asia, and Latin America. Conclusions Current evidence supports cautious deployment of LLMs in selected healthcare tasks under structured oversight. Translational progress depends on prospective evaluation, standardised reporting, equity-focused audits, and lifecycle governance with continuous monitoring. The proposed five-dimensional framework (technical performance, clinical validity, equity, workflow integration, governance) coupled with a three-tier risk model is intended to support researchers and healthcare organisations in assessing readiness and implementing LLM-enabled tools responsibly.","背景 大语言模型（Large Language Models, LLMs）在医疗健康领域的应用评估日益增多，涵盖临床文档、决策支持、患者沟通、研究辅助和运营工作流程。尽管应用兴趣迅速增长，但证据仍呈现异质性，评估与治理的标准化方法尚未得到一致应用。目的 梳理大语言模型在医疗健康领域的应用，综合已报告的结局与风险，并提出面向数字健康实施的多维评估与治理框架。方法 按照Arksey和O'Malley、Levac等人以及乔安娜布里格斯研究所的方法学指导开展范围综述，报告遵循PRISMA-ScR清单。研究方案已在开放科学框架（Open Science Framework）前瞻性注册（https:\u002F\u002Fdoi.org\u002F10.17605\u002FOSF.IO\u002FSWP78）。检索在PubMed\u002FMEDLINE、Embase、Scopus、Web of Science、IEEE Xplore、ACM Digital Library和ACL Anthology中进行，并补充检索medRxiv\u002FbioRxiv预印本以及世界卫生组织（WHO）、美国食品药品监督管理局（FDA）和欧盟人工智能办公室（EU AI-Office）指南的灰色文献，覆盖2019年1月1日至2026年4月30日。标题\u002F摘要和全文筛选由两人独立完成；评分者间一致性为Cohen's κ = 0.78。数据采用经预试验的表格由两人独立提取。综合采用Braun和Clarke的六阶段反思性主题分析法。78项纳入研究的完整列表见补充文件S4。结果 78项研究符合纳入标准；68%发表于2023年至2025年间。识别出五个应用领域：（1）临床文档与摘要生成；（2）临床决策支持与推理辅助；（3）患者沟通与健康素养支持；（4）生物医学研究与知识综合；（5）行政与运营用例。证据基础以基准测试和模拟工作流程研究为主（89%），前瞻性嵌入工作流程的评估有限（11%）。已报告的获益集中在文档效率、文本质量和知识综合方面；与安全相关的风险包括幻觉内容、临床关键信息遗漏、人口统计学偏倚、隐私漏洞、可解释性有限和自动化偏倚。研究在地理上集中于北美和东亚，撒哈拉以南非洲、南亚和拉丁美洲的代表性有限。结论 Cu",null,"Frontiers in Digital Health","2026-09-18T00:00:00Z","论文",10,false,0,{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":17},"该文为医疗领域大语言模型的范围综述，与三农、农业信息化、智慧农业等主题无关，不予入选。",[19],{"name":10,"url":6},[12],[],{"status":23,"locked":14,"version":24,"method":25,"evidence":26},"needs_review","2026-10-22.2","rules",{"candidates":27,"agricultural_evidence":14,"reason":36},[28],{"code":29,"score":30,"supported":31,"title":32,"abstract":33,"tags":35},"I2",3,true,[],[34],"decision support",[],"农业相关性需要复核",[],"Largelanguagemodelsinhealthcare:applicat-3085",1,"10.3389\u002Ffdgth.2026.1865568",{"doi":40,"openalex_id":42,"authors":43,"venue":10,"cited_by_count":15,"oa_url":48,"card":49,"direction":55,"ingested_from":56},"W7213552002",[44,46],{"name":45,"orcid":9},"João C. Ferreira",{"name":47,"orcid":9},"Isabel Rosa","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fdigital-health\u002Farticles\u002F10.3389\u002Ffdgth.2026.1865568\u002Fpdf",{"tldr":50,"method":51,"finding":52,"direction":53,"opportunity":54},"综述医疗大模型应用，提出多维评估与治理框架。","范围综述，检索7大数据库及灰色文献，主题分析78项研究。","应用分五域，证据多为基准测试，缺前瞻性嵌入评估，风险含幻觉与偏见。","其他","医疗LLM评估治理框架可迁移至农业大模型，填补农业场景前瞻性验证空白。","数字乡村与农业信息化","openalex","2026-09-21T23:30:36.936121Z",{"total":15,"page":39,"page_size":39,"items":59},[]]