[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-452701-105":59,"doc-detail-452701-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","artificial-intelligence-for-clinical-reasoning-the-reliability-challenge-and-path-to-evidence-based-practice","Artificial intelligence for clinical reasoning: the reliability challenge and path to evidence-based practice","","The integration of generative artificial intelligence, especially large language models (LLMs), into clinical reasoning offers transformative potential but raises uncertainty about authentic replication of human clinical decision-making, framed here as the reliability challenge. Although studies show performance on licensing exams and diagnostic accuracy comparable to physicians, key limits remain. LLMs often imitate reasoning patterns, not true logical reasoning, and may rely on outdated or non-regional data that weakens clinical relevance. A synergistic paradigm is proposed: physicians contribute expertise while AI advances toward transparency and interpretability. This requires real-time, context-specific evidence integration, alignment with local healthcare constraints, and explainable architectures such as multi-step reasoning frameworks or clinical knowledge graphs to clarify decision pathways, supporting ethical, patient-centered evidence-based care.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":35,"@type":76,"position":81},"https://docshare.wps.com/document/healthcare/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/artificial-intelligence-for-clinical-reasoning-the-reliability-challenge-and-path-to-evidence-based-practice/452701/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/artificial-intelligence-for-clinical-reasoning-the-reliability-challenge-and-path-to-evidence-based-practice/452701.png","ImageObject",300,407,{"name":92,"@type":93},"ahduag","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-30","2026-09-30",true,{"@type":102,"interactionType":103,"userInteractionCount":44},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What does the article call the “reliability challenge” for AI in clinical reasoning?","Question",{"text":112,"@type":113},"It refers to uncertainty about whether generative AI and LLMs can authentically replicate the complex clinical decision-making process used by humans.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"Why are current LLMs considered limited for clinical reasoning reliability?",{"text":117,"@type":113},"The article notes that LLMs mimic reasoning patterns rather than performing genuine logical reasoning, and they may depend on outdated or non-regional data that reduces clinical relevance.",{"name":119,"@type":110,"acceptedAnswer":120},"What paradigm does the article propose to improve reliable AI for clinical reasoning?",{"text":121,"@type":113},"It advocates a synergistic approach where physicians apply advanced clinical expertise while AI evolves toward transparency and interpretability, using real-time context-specific evidence and explainable architectures.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},452701,1791309215,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":34,"category_name":35,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":44,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":81,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":143,"read_time":39,"preview_page_count":4},3985747870414,"https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc","QJM: An International Journal of Medicine, 2025, 118(11), 802–804  \n[https://doi.org/10.1093/qjmed/hcaf114](https://doi.org/10.1093/qjmed/hcaf114)  \nAdvance Access Publication Date: 19 May 2025  \nCommentary  \nCommentary  \nArtificial intelligence for clinical reasoning: the reliability challenge and path to evidence-based practice  \nHe Xu 1,2,3, Yueqing Wang2, Yangqin Xun2, Ruitai Shao2, 􀀃 and Yang Jiao 1, 􀀃  \n1Department of General Practice (General Internal Medicine), Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China  \n2School of Population Medicine and Public Health, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China  \n34 þ 4 MD Program, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China  \n􀀃 Address correspondence to Yang Jiao, Department of General Practice (General Internal Medicine), Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, No. 1 Shuaifuyuan, Dongcheng district, Beijing, 100730, [China. Email: peterpumch@163.com](China. Email: peterpumch@163.com); Ruitai Shao, School of Population Medicine and Public Health, Chinese Academy of Medical Sciences and Peking Union Medical College, No.9 Dongdansantiao, Dongcheng  \ndistrict, Beijing, 100730, China. Email: [shaoruitai@sph.pumc.edu.cn](shaoruitai@sph.pumc.edu.cn)  \nAbstract  \nThe integration of generative artificial intelligence (AI), particularly large language models (LLMs), into clinical reasoning heralds transformative potential for medical practice. However, their capacity to authentically replicate the complexity of human clinical decision-making remains uncertain—a challenge defined here as the reliability challenge. While studies demonstrate LLMs’ ability to pass medical licensing exams and achieve diagnostic accuracy comparable to physicians, critical limitations persist. Crucially, LLMs mimic reasoning patterns rather than executing genuine logical reasoning, and their reliance on outdated or non-regional data undermines clinical relevance. To bridge this gap, we advocate for a synergistic paradigm where physicians leverage advanced clinical expertise while AI evolves toward transparency and interpretability. This requires AI systems to integrate real-time, context-specific evidence, align with local healthcare constraints, and adopt explainable architectures (e.g. multi-step reasoning frameworks or clinical knowledge graphs) to demystify decision pathways. Ultimately, reliable AI for clinical reasoning hinges on harmonizing technological innovation with human oversight, ensuring ethical adherence to beneficence and non-maleficence while advancing evidence-based, patient-centered care.  \nIntroduction  \nThe rise of artificial intelligence (AI) marks a transformative era that looks set to reshape medical practice. With the advent of generative large language models (LLMs), especially those capable of producing chain-of-thought (CoT) narrative,1 AI’s role seems to be shifting from merely supporting to potentially executing clinical reasoning. However, this raises a critical question: can CoT AI authentically replicate the intricate clinical reasoning required of human clinical decision-making?  \nCertainly, the literature continues to expand with studies applying generative AI to different problems in healthcare. However, followers of the topic will also be aware that many AI studies exaggerate the benefits and potential and downplay the drawbacks of AI. Overall, the specific value and reliability of generative AI in clinical reasoning remain underexplored and poorly understood.2 Clinical settings are highly diverse, varying according to geography, resourcing, and the unique interpersonal dynamics of physician-patient relationships. Reliable clinical  \nreasoning is fundamental for safe, high-quality care delivery in heterogeneous clinical settings, while reliable clin","cbCaitvcoYO7lQpt","https://ap.wps.com/l/cbCaitvcoYO7lQpt","pdf",299675,"English","# Introduction\n## Reliability challenge and clinical reasoning\n## Proposed path toward evidence-based practice","[{\"question\":\"What does the article call the “reliability challenge” for AI in clinical reasoning?\",\"answer\":\"It refers to uncertainty about whether generative AI and LLMs can authentically replicate the complex clinical decision-making process used by humans.\"},{\"question\":\"Why are current LLMs considered limited for clinical reasoning reliability?\",\"answer\":\"The article notes that LLMs mimic reasoning patterns rather than performing genuine logical reasoning, and they may depend on outdated or non-regional data that reduces clinical relevance.\"},{\"question\":\"What paradigm does the article propose to improve reliable AI for clinical reasoning?\",\"answer\":\"It advocates a synergistic approach where physicians apply advanced clinical expertise while AI evolves toward transparency and interpretability, using real-time context-specific evidence and explainable architectures.\"}]","Artificial intelligence for clinical reasoning: the reliability challenge and path to evidence-based practice | PDF",1790737592]