A large language model for complex cardiology care.

This issue is particularly acute in cardiology, where timely, accurate management determines outcomes.

这一问题在心脏病学中尤为严重，在那里及时、准确的管理决定了结果。

We explored the potential of Articulate Medical Intelligence Explorer (AMIE), a large language model-based experimental medical artificial intelligence system, to augment clinical decision-making in this challenging context.

我们研究了基于大型语言模型的实验性医学人工智能系统Articulate Medical Intelligence Explorer (AMIE)在这一挑战性情境中增强临床决策的潜力。

We conducted a randomized controlled trialcomparing large language model-assisted care with the usual care of complex patients suspected of having a genetic cardiomyopathy, and we curated a real-world dataset of complex cases from a subspecialist cardiology practice.

我们开展了一项随机对照试验，比较了大型语言模型辅助的护理与复杂患者疑似遗传性心肌病的常规护理，并从专科心脏病学实践中整理了一个复杂病例的真实世界数据集。

Nine participating general cardiologists were provided with access to both clinical text reports and raw diagnostic data-including electrocardiograms, echocardiograms, cardiac magnetic resonance imaging scans and cardiopulmonary exercise testing-and were randomized to manage these cases, either with or without assistance from AMIE.

九名参与的普通心脏病专家被提供临床文本报告和原始诊断数据的访问权限，包括心电图、超声心动图、心脏磁共振成像扫描和心肺运动测试，并被随机分配管理这些病例，无论是使用还是不使用AMIE的帮助。

We developed a ten-domain evaluation rubric used by three blinded subspecialists to evaluate the quality of triage, diagnosis and management.

我们开发了一个由三名盲法专家使用的十个领域的评估量表，用于评估分诊、诊断和管理的质量。

In our randomized controlled trialwith retrospective patient data, subspecialists favored large language model-assisted responses overall, and for the management plan and diagnostic testing domains, with the remaining domains considered a tie.

在我院进行的随机对照试验中，结合回顾性患者数据，专科医生总体上偏好使用大型语言模型辅助的回应，特别是在管理计划和诊断测试领域，其余领域被认为是平局。

Overall, subspecialists preferred AMIE-assisted cardiology assessments 46.7% of the time, compared with 32.7% for cardiologists alone (P = 0.02), with 20.6% rated as a tie.

总体而言，专科医生在46.7%的时间里更倾向于使用AMIE辅助的心脏病评估，而单独由心脏病专家进行评估的偏好率为32.7%（P = 0.02），另有20.6%被认为是平局。

Subspecialists also quantified errors, extra and missing content, reasoning and potential bias.

专家还量化了错误、多余和缺失的内容、推理和潜在偏见。

Cardiologists alone had more clinically significant errors (24.3% versus 13.1%, P = 0.033) and more missing content (37.4% versus 17.8%, P = 0.0021) than cardiologists assisted by AMIE.

单独的心脏病专家比由AMIE辅助的心脏病专家有更多的临床意义错误（24.3%对比13.1%，P=0.033）和更多的缺失内容（37.4%对比17.8%，P=0.0021）。

Lastly, cardiologists who used AMIE reported that AMIE helped their assessment more than half the time (57.0%) and saved time in 50.5% of cases.

最后，使用 AMIE 的心脏病专家报告称，AMIE 在超过一半的时间（57.0%）帮助了他们的评估，并在50.5%的病例中节省了时间。