<p><em>人口规模的人工智能系统使用 Claude 分析数百万份医疗记录，以识别符合指南推荐护理的患者，并支持及时的临床审查</em></p>
<p>, /PRNewswire/ -- Qualified Health 和 Anthropic 在德克萨斯大学系统（UT System）推出了一项具有里程碑意义的人工智能部署，以应对医疗保健中最持久的挑战之一：确保符合循证标准的患者能够持续被识别、适当评估，并在大规模和多样化的人群中考虑高质量护理。</p>
<p>在这一倡议下，Qualified Health 的人工智能系统由 Anthropic 的 Claude AI 模型提供支持，正在德克萨斯州 UT 系统庞大的健康网络中部署，以持续分析大量临床数据集并发现指南推荐护理中的差距。该系统应用经过验证的临床指南和适宜性标准，使 UT 系统的护理团队能够持续识别可能需要进一步临床审查和协调护理计划的患者。</p>
<p>尽管经过数十年的临床研究和成熟的指南，仍有数千万美国人符合循证护理的标准却从未及时被识别和评估。仅在德克萨斯州，每年就有估计 400 万到 600 万患者被忽视，导致可预防的并发症和死亡、获取医疗服务的不平等，以及对临床医生和医疗系统的日益压力。</p>
<p>问题不在于缺乏医学知识，而在于现代医疗的操作现实。确定患者是否符合基于指南的适宜性标准通常需要在分散的系统、非结构化的笔记、实验室、影像和历史记录中进行有意且劳动密集的图表审查。在人口规模上，跨越数百万患者和数 PB 的复杂临床数据，系统性识别循证患者护理中的差距在历史上一直是不可行的，直到现在。</p>
<p>&#34;医疗保健是人工智能最具挑战性的环境之一，因为它需要解析大量复杂的非结构化临床数据，同时在严格的治理框架内安全操作，&#34; Anthropic 生命科学负责人 Eric Kauderer-Abrams 表示。&#34;Claude 能够可靠地做到这一点，当与 Qualified Health 的治理平台和德克萨斯大学系统这样的前瞻性健康系统结合时，创造了安全大规模部署先进人工智能的条件，并最终帮助弥补数百万患者的护理差距。&#34;</p>
<p>Qualified Health 的人工智能系统整合来自不同来源的数据，解析复杂的临床数据，并应用经过验证的临床指南和适宜性标准，以保持对护理差距的持续更新的人口级视图。需要进一步考虑的患者会直接被纳入护理团队的工作流程中进行审查，支持的临床背景会自动汇总，以支持高效、高质量的决策。</p>
<p>&#34;挑战不在于我们不知道什么有效，而在于将数十年的证据和适宜性指导转化为一致的临床实践，&#34; Qualified Health 首席执行官 Justin Norden 博士表示。&#34;该系统旨在增强，而不是取代临床判断，使临床医生能够在以前无法实现的规模上应用他们的专业知识。合作伙伴们共同建立了一个可复制的框架，以大规模操作循证医学。曾经需要大量手动图表抽象和跨系统协调的工作现在可以在整个群体中持续进行。&#34;</p>
<p>经过广泛评估和测试，该系统现在在德克萨斯大学医学分校（UTMB）上线，这是 UT 系统内的第一个部署地点。初步部署重点识别指南推荐的心脏病护理中的差距，包括指南指导的药物治疗和适当的药物剂量，以及心力衰竭和瓣膜疾病的必要介入治疗。重要的是，适宜性标准也被提出，以确保高质量的评估。</p>
<p>初步部署的早期结果显示出人口规模的影响：</p>
<ul>
<li>复杂的临床数据被解析并汇总成统一的患者档案，整合了笔记、实验室结果、影像和程序信息</li>
<li>统一的患者档案根据广泛的心脏病程序的精确、基于指南的标准进行评估</li>
<li>大量以前未被识别的高可能性候选人被提出供临床医生审查</li>
<li>临床医生的审查与系统输出显示出高度一致，增强了临床信任</li>
<li>适合的患者的护理路径得到了加速</li>
</ul>
<p>通过确保临床考虑在患者群体和护理环境中更为一致地应用，该方法支持更及时、适当的护理交付，并减少德克萨斯州患者因操作或获取限制而被忽视的可能性。</p>
<p>在 UTMB 成功的基础上，该平台正在全系统扩展，评估工具也将延伸到心脏病以外的领域。到 2026 年底，额外的部署将支持在初级护理、血管、胃肠、风湿病和神经学专业中识别合格患者，帮助更多的健康系统在德克萨斯州各地扩展获得经过验证的护理。</p>
<p>&#34;UT 健康机构为德克萨斯州每个角落的患者提供服务。我们不是在现有系统上叠加解决方案，而是在 UT 系统的健康企业中建立一个新的共享基础，使新的人工智能部署能够以一致性、问责制和长期影响引入，&#34; UT 系统健康事务首席数字与分析官兼副校长 Zain Kazmi 表示。&#34;这一新伙伴关系有助于我们快速行动、共同学习，并在患者护理环境中有效应用智能。&#34;</p>
<p>作为德克萨斯大学医疗人工智能研究、工程与应用实验室（UT REAL Health AI）计划的一部分，该部署围绕两个共同目标展开：扩大基于证据的治疗的可及性，特别是针对服务不足的人群，并建立在临床环境中安全、负责任地部署人工智能的新标准。</p>
<p>“UT REAL Health AI 计划旨在改善德克萨斯州人的生活，” 德克萨斯大学医学分校首席人工智能与数字官员、UT REAL Health AI 计划主席彼得·麦卡弗里（Peter McCaffrey）表示。“通过在我们的医疗机构中部署新的人工智能技术，我们可以提升患者的护理体验，促进人口健康，并降低整体护理成本。”</p>
<p>该部署在 Anthropic 的沟通和公共论坛中得到了展示，包括在摩根大通医疗会议上，随着全国各地的医疗系统评估大规模人工智能以系统性地扩展基于证据的护理的可及性。</p>
<p><strong>关于 Qualified Health</strong></p>
<p>Qualified Health 是一个企业人工智能平台和战略人工智能合作伙伴，帮助医疗系统部署安全且可扩展的人工智能，以推动可衡量的临床和财务成果。我们的平台覆盖全国顶级医疗系统的 40 多万用户，结合了工作流程自动化、代理开发、临床保障、实时监控和端到端治理，以及深厚的医疗和人工智能专业知识，帮助医疗领导者实现规模价值。</p>
<p>Qualified Health 由前医疗系统高管、来自领先机构的一线医生、临床转型专家和硅谷工程师构建和领导，具备部署、扩展和安全、负责任地治理企业级人工智能应用所需的领域深度和运营严谨性。</p>
<p>欲了解更多信息，请访问 www.qualifiedhealthai.com。</p>
<p>来源：Qualified Health PBC</p>
<p><img src="https://imageproxy.pbkrs.com/https://rt.prnewswire.com/rt.gif/query-RGF0ZUlkPTIwMjYwMTIxJk5ld3NJdGVtSWQ9U0Y2ODMwNiZUcmFuc21pc3Npb25fSWQ9MjAyNjAxMjExMzU0UFJfTkVXU19VU1BSX19fX19TRjY4MzA2?x-oss-process=image/auto-orient,1/interlace,1/resize,w_1440,h_1440/quality,q_95/format,jpg" alt="" original-src="https://imageproxy.pbkrs.com/https://rt.prnewswire.com/rt.gif/query-RGF0ZUlkPTIwMjYwMTIxJk5ld3NJdGVtSWQ9U0Y2ODMwNiZUcmFuc21pc3Npb25fSWQ9MjAyNjAxMjExMzU0UFJfTkVXU19VU1BSX19fX19TRjY4MzA2"/></p>

<p>合格健康公司（Qualified Health）与 Anthropic 在德克萨斯大学系统推出了一项人工智能部署，以增强对基于证据的医疗保健的获取。该人工智能系统分析数百万份医疗记录，以识别符合指南推荐护理的患者，解决及时临床审查的挑战。初始部署集中在心脏病学领域，计划在 2026 年前扩展到其他专业。该倡议旨在填补数百万德克萨斯州居民的护理空白，确保患者获得适当的评估和治疗，最终改善全州的医疗保健结果</p>

<p><em>Population-scale AI system uses Claude to analyze millions of medical records to identify patients who qualify for guideline-recommended care and support timely clinical review</em></p>
<div class="lb-trans"><p><em>人口规模的人工智能系统使用 Claude 分析数百万份医疗记录，以识别符合指南推荐护理的患者，并支持及时的临床审查</em></p>
</div><p>, /PRNewswire/ -- Qualified Health and Anthropic have launched a landmark AI deployment across the University of Texas System (UT System) to tackle one of healthcare's most persistent challenges: ensuring that patients who meet evidence-based criteria are consistently identified, appropriately evaluated, and considered for high-quality care across large and diverse populations.</p>
<div class="lb-trans"><p>, /PRNewswire/ -- Qualified Health 和 Anthropic 在德克萨斯大学系统（UT System）推出了一项具有里程碑意义的人工智能部署，以应对医疗保健中最持久的挑战之一：确保符合循证标准的患者能够持续被识别、适当评估，并在大规模和多样化的人群中考虑高质量护理。</p>
</div><p>Under this initiative, Qualified Health's AI system, powered by Anthropic's Claude AI models, is being deployed across UT System's vast health network in Texas to continuously analyze vast clinical datasets and surface gaps in guideline-recommended care. The system applies validated clinical guidelines and appropriateness criteria to enable care teams across the UT System to consistently identify patients who may benefit from further clinical review and coordinated care planning.</p>
<div class="lb-trans"><p>在这一倡议下，Qualified Health 的人工智能系统由 Anthropic 的 Claude AI 模型提供支持，正在德克萨斯州 UT 系统庞大的健康网络中部署，以持续分析大量临床数据集并发现指南推荐护理中的差距。该系统应用经过验证的临床指南和适宜性标准，使 UT 系统的护理团队能够持续识别可能需要进一步临床审查和协调护理计划的患者。</p>
</div><p>Despite decades of clinical research and well-established guidelines, tens of millions of Americans who meet criteria for evidence-based care are never identified and evaluated in time. In Texas alone, an estimated 4-6 million patients fall through the cracks each year, leading to preventable complications and mortality, inequities in access, and growing strain on clinicians and the healthcare system.</p>
<div class="lb-trans"><p>尽管经过数十年的临床研究和成熟的指南，仍有数千万美国人符合循证护理的标准却从未及时被识别和评估。仅在德克萨斯州，每年就有估计 400 万到 600 万患者被忽视，导致可预防的并发症和死亡、获取医疗服务的不平等，以及对临床医生和医疗系统的日益压力。</p>
</div><p>The problem is not a lack of medical knowledge, but the operational reality of modern healthcare. Determining whether patients meet guideline-based and appropriateness criteria often requires intentional and labor-intensive chart review across fragmented systems, unstructured notes, labs, imaging, and historical records. At population scale, across millions of patients and petabytes of complex clinical data, systematic identification of gaps in evidence-based patient care has historically been infeasible, until now.</p>
<div class="lb-trans"><p>问题不在于缺乏医学知识，而在于现代医疗的操作现实。确定患者是否符合基于指南的适宜性标准通常需要在分散的系统、非结构化的笔记、实验室、影像和历史记录中进行有意且劳动密集的图表审查。在人口规模上，跨越数百万患者和数 PB 的复杂临床数据，系统性识别循证患者护理中的差距在历史上一直是不可行的，直到现在。</p>
</div><p>&#34;Healthcare is one of the most demanding environments for AI because it requires parsing vast amounts of complex, unstructured clinical data while operating safely within strict governance frameworks,&#34; said Eric Kauderer-Abrams, Head of Life Sciences at Anthropic. &#34;Claude can do that reliably, and when paired with Qualified Health's governance platform and a visionary health system like the University of Texas System, it creates the conditions to deploy advanced AI safely at scale and ultimately help close care gaps for millions of patients.&#34;</p>
<div class="lb-trans"><p>&#34;医疗保健是人工智能最具挑战性的环境之一，因为它需要解析大量复杂的非结构化临床数据，同时在严格的治理框架内安全操作，&#34; Anthropic 生命科学负责人 Eric Kauderer-Abrams 表示。&#34;Claude 能够可靠地做到这一点，当与 Qualified Health 的治理平台和德克萨斯大学系统这样的前瞻性健康系统结合时，创造了安全大规模部署先进人工智能的条件，并最终帮助弥补数百万患者的护理差距。&#34;</p>
</div><p>Qualified Health's AI system integrates data across sources, parsing complex clinical data, and applying validated clinical guidelines and appropriateness criteria to maintain a continuously updated, population-level view of care gaps. Patients who warrant further consideration are surfaced directly into care team workflows for review, with supporting clinical context automatically assembled to support efficient, high-quality decision-making.</p>
<div class="lb-trans"><p>Qualified Health 的人工智能系统整合来自不同来源的数据，解析复杂的临床数据，并应用经过验证的临床指南和适宜性标准，以保持对护理差距的持续更新的人口级视图。需要进一步考虑的患者会直接被纳入护理团队的工作流程中进行审查，支持的临床背景会自动汇总，以支持高效、高质量的决策。</p>
</div><p>&#34;The challenge isn't that we don't know what works. It's translating decades of evidence and appropriateness guidance into consistent clinical practice at scale,&#34; said Justin Norden, MD, MBA, MPhil, CEO of Qualified Health. &#34;The system is designed to augment, not replace, clinical judgment and enable clinicians to apply their expertise at a scale that was previously not possible. Together, the partners are establishing a replicable framework for operationalizing evidence-based medicine at scale. What once required extensive manual chart abstraction and cross-system coordination can now happen continuously, across entire populations.&#34;</p>
<div class="lb-trans"><p>&#34;挑战不在于我们不知道什么有效，而在于将数十年的证据和适宜性指导转化为一致的临床实践，&#34; Qualified Health 首席执行官 Justin Norden 博士表示。&#34;该系统旨在增强，而不是取代临床判断，使临床医生能够在以前无法实现的规模上应用他们的专业知识。合作伙伴们共同建立了一个可复制的框架，以大规模操作循证医学。曾经需要大量手动图表抽象和跨系统协调的工作现在可以在整个群体中持续进行。&#34;</p>
</div><p>Following extensive evaluation and testing, the system is now live at the University of Texas Medical Branch (UTMB), the first deployment site within the UT System. Initial deployment focuses on identifying gaps in guideline-recommended cardiology care, ranging from guideline directed medical therapy and appropriate medication dosage to necessary interventional treatments for heart failure and valvular disease. Importantly, appropriateness criteria are also surfaced to ensure high-quality assessment.</p>
<div class="lb-trans"><p>经过广泛评估和测试，该系统现在在德克萨斯大学医学分校（UTMB）上线，这是 UT 系统内的第一个部署地点。初步部署重点识别指南推荐的心脏病护理中的差距，包括指南指导的药物治疗和适当的药物剂量，以及心力衰竭和瓣膜疾病的必要介入治疗。重要的是，适宜性标准也被提出，以确保高质量的评估。</p>
</div><p>Early results from the initial deployment demonstrate population-scale impact:</p>
<div class="lb-trans"><p>初步部署的早期结果显示出人口规模的影响：</p>
</div><ul>
<li>Complex clinical data were parsed and assembled into unified patient profiles, integrating notes, laboratory results, imaging, and procedural information</li>
<li>Unified patient profiles were evaluated against precise, guideline-based criteria across a broad set of cardiology procedures</li>
<li>Large cohorts of previously unrecognized, high-likelihood candidates were surfaced for clinician review</li>
<li>Clinician review demonstrated a high level of agreement with system outputs, reinforcing clinical trust</li>
<li>Care pathways for appropriately eligible patients were accelerated</li>
</ul>
<div class="lb-trans"><ul>
<li>复杂的临床数据被解析并汇总成统一的患者档案，整合了笔记、实验室结果、影像和程序信息</li>
<li>统一的患者档案根据广泛的心脏病程序的精确、基于指南的标准进行评估</li>
<li>大量以前未被识别的高可能性候选人被提出供临床医生审查</li>
<li>临床医生的审查与系统输出显示出高度一致，增强了临床信任</li>
<li>适合的患者的护理路径得到了加速</li>
</ul>
</div><p>By ensuring that clinical consideration is applied more uniformly across patient populations and care settings, the approach supports more timely, appropriate care delivery and reduces the likelihood that patients across Texas are overlooked due to operational or access constraints.</p>
<div class="lb-trans"><p>通过确保临床考虑在患者群体和护理环境中更为一致地应用，该方法支持更及时、适当的护理交付，并减少德克萨斯州患者因操作或获取限制而被忽视的可能性。</p>
</div><p>Building on UTMB's success, the platform is expanding systemwide and evaluation tools are extending beyond cardiology. By the end of 2026, additional deployments will support identification of eligible patients across primary care, vascular, gastrointestinal, rheumatology, and neurology specialties, helping additional health systems extend access to proven care all across Texas.</p>
<div class="lb-trans"><p>在 UTMB 成功的基础上，该平台正在全系统扩展，评估工具也将延伸到心脏病以外的领域。到 2026 年底，额外的部署将支持在初级护理、血管、胃肠、风湿病和神经学专业中识别合格患者，帮助更多的健康系统在德克萨斯州各地扩展获得经过验证的护理。</p>
</div><p>&#34;UT health institutions serve patients in every corner of Texas. Rather than laying solutions on top of existing systems, we are building a new shared foundation across the UT System's health enterprise that allows new AI deployments to be introduced with consistency, accountability, and long-term impact,&#34; said Zain Kazmi, chief digital &amp; analytics officer and associate vice chancellor of health affairs at the UT System. &#34;This new partnership contributes to our ability to move quickly, learn collectively, and apply intelligence effectively within patient care environments.&#34;</p>
<div class="lb-trans"><p>&#34;UT 健康机构为德克萨斯州每个角落的患者提供服务。我们不是在现有系统上叠加解决方案，而是在 UT 系统的健康企业中建立一个新的共享基础，使新的人工智能部署能够以一致性、问责制和长期影响引入，&#34; UT 系统健康事务首席数字与分析官兼副校长 Zain Kazmi 表示。&#34;这一新伙伴关系有助于我们快速行动、共同学习，并在患者护理环境中有效应用智能。&#34;</p>
</div><p>As part of the University of Texas Research, Engineering, and Application Laboratory for Healthcare Artificial Intelligence (UT REAL Health AI) initiative, the deployment is anchored around two shared goals: expanding access to evidence-based treatment, particularly for underserved populations, and establishing a new standard for the safe, responsible deployment of AI in clinical environments.</p>
<div class="lb-trans"><p>作为德克萨斯大学医疗人工智能研究、工程与应用实验室（UT REAL Health AI）计划的一部分，该部署围绕两个共同目标展开：扩大基于证据的治疗的可及性，特别是针对服务不足的人群，并建立在临床环境中安全、负责任地部署人工智能的新标准。</p>
</div><p>&#34;The UT REAL Health AI Initiative is about improving the lives of Texans,&#34; said Peter McCaffrey, chief AI &amp; digital officer at the University of Texas Medical Branch and chair of the UT REAL Health AI initiative. &#34;Through new AI deployments across our health institutions, we can enhance patients' experience of care, advance population health, and reduce the overall cost of care.&#34;</p>
<div class="lb-trans"><p>“UT REAL Health AI 计划旨在改善德克萨斯州人的生活，” 德克萨斯大学医学分校首席人工智能与数字官员、UT REAL Health AI 计划主席彼得·麦卡弗里（Peter McCaffrey）表示。“通过在我们的医疗机构中部署新的人工智能技术，我们可以提升患者的护理体验，促进人口健康，并降低整体护理成本。”</p>
</div><p>The deployment was featured in Anthropic's communications and public forums, including at the J.P. Morgan Healthcare Conference, as health systems nationwide evaluate population-scale AI to systematically extend access to evidence-based care.</p>
<div class="lb-trans"><p>该部署在 Anthropic 的沟通和公共论坛中得到了展示，包括在摩根大通医疗会议上，随着全国各地的医疗系统评估大规模人工智能以系统性地扩展基于证据的护理的可及性。</p>
</div><p><strong>About Qualified Health</strong></p>
<div class="lb-trans"><p><strong>关于 Qualified Health</strong></p>
</div><p>Qualified Health is the enterprise AI platform and strategic AI partner helping health systems deploy safe and scalable AI to drive measurable clinical and financial outcomes. Reaching over 400,000 users across top health systems nationwide, our platform combines workflow automation, agent development, clinical safeguards, real-time monitoring, and end-to-end governance with deep healthcare and AI expertise, helping healthcare leaders realize value at scale.</p>
<div class="lb-trans"><p>Qualified Health 是一个企业人工智能平台和战略人工智能合作伙伴，帮助医疗系统部署安全且可扩展的人工智能，以推动可衡量的临床和财务成果。我们的平台覆盖全国顶级医疗系统的 40 多万用户，结合了工作流程自动化、代理开发、临床保障、实时监控和端到端治理，以及深厚的医疗和人工智能专业知识，帮助医疗领导者实现规模价值。</p>
</div><p>Qualified Health is built and led by former health system executives, frontline physicians from leading institutions, clinical transformation experts, and Silicon Valley engineers, bringing the domain depth and operational rigor required to deploy, scale, and govern AI applications safely and responsibly at enterprise scale.</p>
<div class="lb-trans"><p>Qualified Health 由前医疗系统高管、来自领先机构的一线医生、临床转型专家和硅谷工程师构建和领导，具备部署、扩展和安全、负责任地治理企业级人工智能应用所需的领域深度和运营严谨性。</p>
</div><p>For more information, visit www.qualifiedhealthai.com.</p>
<div class="lb-trans"><p>欲了解更多信息，请访问 www.qualifiedhealthai.com。</p>
</div><p>SOURCE Qualified Health PBC</p>
<div class="lb-trans"><p>来源：Qualified Health PBC</p>
</div><p><img src="https://imageproxy.pbkrs.com/https://rt.prnewswire.com/rt.gif/query-RGF0ZUlkPTIwMjYwMTIxJk5ld3NJdGVtSWQ9U0Y2ODMwNiZUcmFuc21pc3Npb25fSWQ9MjAyNjAxMjExMzU0UFJfTkVXU19VU1BSX19fX19TRjY4MzA2" alt="" original-src="https://rt.prnewswire.com/rt.gif?NewsItemId=SF68306&amp;Transmission_Id=202601211354PR_NEWS_USPR_____SF68306&amp;DateId=20260121"/></p>

13:54 ET
			
			
				Qualified Health and Anthropic Launch Landmark AI Deployment at University of Texas Institutions to Expand Access to Life-Saving, Evidence-Based Care for Millions of Texans

prnewswire

标普健康医疗设备 ETF - SPDR

生物科技 ETF - VanEck Vectors

KraneShares Artfcl Intllgnc and Tech ETF

纳斯达克生物科技指数 ETF - iShares Nasdaq

CUE HEALTH INC

2 倍做多纳斯达克生物技术 ETF - ProShares

Tema Cardiovascular And Metabolic ETF

美国医药设备 ETF - iShares

标普生物技术 ETF - SPDR

动态生物技术与基因组 ETF - Invesco

医药突破 ETF - ALPS

纽交所高增长板生物技术指数 ETF - First Trust

Qualified Health 和 Anthropic 在德克萨斯大学的机构推出了具有里程碑意义的 AI 部署，以扩大数百万德克萨斯人获得拯救生命的循证护理的机会