此页面是自动翻译的,不保证翻译的准确性。请参阅 英文版 对于源文本。

Artificial Intelligence for Rare Disease Diagnosis

2026年6月3日 更新者:Shuyang Zhang, MD, PhD、Peking Union Medical College Hospital

A Multicentre, Randomised Diagnostic Accuracy Study Evaluating AI Assisted Diagnosis of Rare Diseases

A multicentre, randomised diagnostic accuracy study to evaluate whether the rare disease-specific AI can improve diagnostic accuracy and efficiency for physicians managing real-world clinical cases.

研究概览

地位

尚未招聘

详细说明

Rare diseases collectively affect approximately 300 million individuals worldwide. This prolonged diagnostic delay is attributable in large part to the breadth of over 7,000 recognized rare conditions, which far exceeds the clinical exposure of any individual physician. A rare disease-specific diagnostic AI was developed by Peking Union Medical College Hospital (PUMCH), supporting differential diagnosis generation, clinical workup planning, and genomic variant interpretation. A balanced crossover design ensures that each enrolled physician serves as their own control, substantially reducing confounding from inter-reader variability in baseline diagnostic competency. Within each physician, cases are randomly assigned at the case level to either the AI-assisted or unassisted condition, such that each physician reads a subset of cases with AI assistance and the remaining cases without. This within-reader, case-level randomization eliminates the need for a washout period and directly controls for inter-reader differences in baseline diagnostic competency. All cases are collected from real-world clinical settings with independently confirmed gold-standard diagnoses and span a pre-specified spectrum of rare and non-rare disease categories, reflecting the differential diagnostic challenge encountered in routine clinical practice, to ensure diagnostic breadth and clinical representativeness. Physician seniority (junior vs. senior) is incorporated as a pre-specified stratification and subgroup analysis variable. Diagnostic outputs are evaluated by an independent Expert Adjudication Committee, blinded to the assistance condition, using standardized scoring criteria established prior to data collection.

研究类型

介入性

注册 (估计的)

150

阶段

  • 不适用

联系人和位置

本节提供了进行研究的人员的详细联系信息,以及有关进行该研究的地点的信息。

学习联系方式

学习地点

      • Beijing、中国
        • Peking Union Medical College Hospital
        • 接触:
      • Cangzhou、中国
        • Cangzhou Central Hospital
        • 接触:
      • Changchun、中国
        • Changchun Sacred Heart Hospital
        • 接触:
      • Dongguan、中国
        • Dongguan People's Hospital
        • 接触:
      • Foshan、中国
        • First People's Hospital of Foshan
        • 接触:
      • Guiyang、中国
        • Guizhou Provincial People's Hospital
        • 接触:
      • Jilin City、中国
        • Jilin Central General Hospital
        • 接触:
      • Kunming、中国
        • The First People's Hospital of Yunnan Province
        • 接触:
          • Jianhong Hou
          • 电话号码:+86-0871-63638800
          • 邮箱:khyyyb@163.com
      • Lhasa、中国
        • Tibet Autonomous Region People's Hospital
        • 接触:
      • Tianjin、中国
        • Tianjin Children's Hospital
        • 接触:
      • Wuhai、中国
        • Wuhai People's Hospital
        • 接触:
      • Xining、中国
        • Qinghai Provincial People's Hospital
        • 接触:
      • Zhangzhou、中国
        • Zhangzhou Municipal Hospital of Fujian Province
        • 接触:

参与标准

研究人员寻找符合特定描述的人,称为资格标准。这些标准的一些例子是一个人的一般健康状况或先前的治疗。

资格标准

适合学习的年龄

  • 成人
  • 年长者

接受健康志愿者

是的

描述

Inclusion Criteria:

  • 1. Licensed physicians at the junior or senior level affiliated with internal medicine, neurology, pediatrics, and rare disease-related departments.
  • 2. Willingness to provide written informed consent, adhere to trial protocols, and complete all required pre-study training prior to enrollment.

Exclusion Criteria:

  • 1. Prior exposure to any of the clinical cases included in the study case library.
  • 2. Direct participation in the design or development of the AI model.

学习计划

本节提供研究计划的详细信息,包括研究的设计方式和研究的衡量标准。

研究是如何设计的?

设计细节

  • 主要用途:诊断
  • 分配:随机化
  • 介入模型:交叉作业
  • 屏蔽:单身的

武器和干预

参与者组/臂
干预/治疗
实验性的:Intervention Arm
Physicians complete assigned diagnostic tasks with the assistance of AI system in addition to conventional clinical resources.
A rare disease-specific diagnostic AI model is used to accept free text input and assist in rare disease diagnoses. During the experimental condition, physicians may interact with the system freely alongside standard clinical resources to support their diagnostic reasoning.
无干预:Control Arm
Physicians complete the assigned diagnostic tasks using conventional clinical resources only (e.g., medical databases and literature), without access to any generative AI tools. This arm reflects routine clinical diagnostic practice.

研究衡量的是什么?

主要结果指标

结果测量
措施说明
大体时间
Top-3 Diagnostic Accuracy
大体时间:Up to 60 minutes per case (from case presentation to diagnostic report submission).
The percentage of definitive diagnosis is included within the physician's top 3 choices.
Up to 60 minutes per case (from case presentation to diagnostic report submission).

次要结果测量

结果测量
措施说明
大体时间
Diagnosis Time per Case
大体时间:Up to 60 minutes per case (from case presentation to diagnostic report submission).
Elapsed time from initial case presentation to final diagnostic report submission, recorded automatically via system logs.
Up to 60 minutes per case (from case presentation to diagnostic report submission).
Workup Plan Quality
大体时间:Up to 60 minutes per case (from case presentation to diagnostic report submission).
Quality score of the clinical workup plan assigned by an independent expert committee using a standardized Likert Scale. Scores range from 1 to 10, with higher scores indicating better workup plan quality.
Up to 60 minutes per case (from case presentation to diagnostic report submission).
Physician Reported Usability of the AI-Assisted Diagnostic System
大体时间:Up to 60 minutes per case (upon completion of each case reading).
Physician-reported usability of the AI system, assessed after completion of each AI-assisted case reading using a 10-point physician-rated usability scale. Scores range from 1 to 10, with higher scores indicating better system usability.
Up to 60 minutes per case (upon completion of each case reading).
Physician Reported Workload
大体时间:Up to 60 minutes per case (upon completion of each case reading).
Task-related workload experienced by physicians, assessed after completion of each AI-assisted case reading using a 10-point Physician Workload Likert scale. Scores range from 1 to 10, with higher scores indicating a higher workload.
Up to 60 minutes per case (upon completion of each case reading).
Physician Satisfaction
大体时间:Up to 60 minutes per case (upon completion of each case reading).
Overall satisfaction of physicians with the diagnostic workflow, assessed after completion of each AI-assisted case reading using a 10-point Satisfaction Likert scale. Scores range from 1 to 10, with higher scores indicating higher satisfaction.
Up to 60 minutes per case (upon completion of each case reading).
Physician Intention to Adopt AI-Assisted Diagnostic Support
大体时间:Up to 60 minutes per case (upon completion of each case reading).
Physician willingness to integrate AI system into routine clinical practice, assessed after completion of each AI-assisted case reading using a 10-point Adoption Intention Likert scale. Scores range from 1 to 10, with higher scores indicating higher adoption intention.
Up to 60 minutes per case (upon completion of each case reading).

合作者和调查者

在这里您可以找到参与这项研究的人员和组织。

研究记录日期

这些日期跟踪向 ClinicalTrials.gov 提交研究记录和摘要结果的进度。研究记录和报告的结果由国家医学图书馆 (NLM) 审查,以确保它们在发布到公共网站之前符合特定的质量控制标准。

研究主要日期

学习开始 (估计的)

2026年6月20日

初级完成 (估计的)

2026年12月1日

研究完成 (估计的)

2027年6月1日

研究注册日期

首次提交

2026年5月28日

首先提交符合 QC 标准的

2026年6月3日

首次发布 (实际的)

2026年6月4日

研究记录更新

最后更新发布 (实际的)

2026年6月4日

上次提交的符合 QC 标准的更新

2026年6月3日

最后验证

2026年6月1日

更多信息

与本研究相关的术语

药物和器械信息、研究文件

研究美国 FDA 监管的药品

不

研究美国 FDA 监管的设备产品

不

此信息直接从 clinicaltrials.gov 网站检索,没有任何更改。如果您有任何更改、删除或更新研究详细信息的请求,请联系 register@clinicaltrials.gov. clinicaltrials.gov 上实施更改,我们的网站上也会自动更新.

订阅