ChiCTR2500111536 版本V1.0 版本创建时间2025/11/02 23:13:16 中国临床试验注册中心

审核状态：

Project audit state：

通过审核

Successful

注册号：

Registration number：

 ChiCTR2500111536 

最近更新日期：

Date of Last Refreshed on：

 2025-11-02 23:13:09 

注册时间：

Date of Registration：

 2025-11-02 00:00:00 

注册号状态：

预注册

Registration Status：

Prospective registration

注册题目：

机器人辅助诊疗系统临床研究

Public title：

Clinical research on robot assisted diagnosis and treatment system

注册题目简写：

English Acronym：

研究课题的正式科学名称：

方舱医院机器人辅助诊疗系统开发

Scientific title：

Development of Robot Assisted Diagnosis and Treatment System for Fangcang Hospital

研究课题代号(代码)：

Study subject ID：

在二级注册机构或其它机构的注册号：

The registration number of the Partner Registry or other register：

申请注册联系人：

李涛 

研究负责人：

李涛 

Applicant：

Li Tao 

Study leader：

Li Tao 

申请注册联系人电话：

Applicant telephone：

 +86 138 1039 8393

研究负责人电话：

Study leader's
telephone：

+86 138 1039 8393

申请注册联系人传真 ：

Applicant Fax：

研究负责人传真：

Study leader's fax：

申请注册联系人电子邮件：

Applicant E-mail：

 litao301hospital@163.com

研究负责人电子邮件：

Study leader's E-mail：

 litao301hospital@163.com

申请单位网址(自愿提供)：

Applicant website(voluntary supply)：

研究负责人网址(自愿提供)：

Study leader's website(voluntary supply)：

申请注册联系人通讯地址：

北京市海淀区复兴路28号解放军总医院医学创新研究部

研究负责人通讯地址：

北京市海淀区复兴路28号解放军总医院医学创新研究部

Applicant address：

Medical Innovation Research Department, PLA General Hospital, No. 28 Fuxing Road, Haidian District, Beijing

Study leader's address：

Medical Innovation Research Department, PLA General Hospital, No. 28 Fuxing Road, Haidian District, Beijing

申请注册联系人邮政编码：

Applicant postcode：

研究负责人邮政编码：

Study leader's postcode：

申请人所在单位：

中国人民解放军总医院

Applicant's institution：

the Chinese People's Liberation Army General Hospital

研究负责人所在单位：

中国人民解放军总医院

Affiliation of the Leader：

the Chinese People's Liberation Army General Hospital

是否获伦理委员会批准：

是

Approved by ethic committee：

Yes

伦理委员会批件文号：

Approved No. of ethic committee：

 伦审第S2022-255-04号

伦理委员会批件附件：

Approved file of Ethical Committee：

 查看附件View

批准本研究的伦理委员会名称：

中国人民解放军总医院医学伦理委员会

Name of the ethic committee：

Medical Ethics Committee of the Chinese People's Liberation Army General Hospital

伦理委员会批准日期：

Date of approved by ethic committee：

 2025-07-31 00:00:00

伦理委员会联系人：

曹江

Contact Name of the ethic committee：

Cao Jiang

伦理委员会联系地址：

北京市海淀区复兴路28号

Contact Address of the ethic committee：

28 Fuxing Road, Haidian District, Beijing

伦理委员会联系人电话：

Contact phone of the ethic committee：

 +86 10 6693 7166

伦理委员会联系人邮箱：

Contact email of the ethic committee：

研究实施负责（组长）单位：

中国人民解放军总医院

Primary sponsor：

the Chinese People's Liberation Army General Hospital

研究实施负责（组长）单位地址：

北京市海淀区复兴路28号

Primary sponsor's address：

28 Fuxing Road, Haidian District, Beijing

试验主办单位(项目批准或申办者)：

Secondary sponsor：

国家：

中国

省(直辖市)：

北京

市(区县)：

Country：

China

Province：

BeiJing

City：

单位(医院)：

解放军总医院医学创新研究部

具体地址：

北京市海淀区复兴路28号

Institution
hospital：

Medical Innovation Research Department of PLA General Hospital

Address：

28 Fuxing Road, Haidian District, Beijing

经费或物资来源：

经费来源于新一代人工智能国家科技重大专项课题

Source(s) of funding：

National Major Science and Technology Project for New Generation Artificial Intelligence

研究疾病：

脊柱关节炎和颈动脉狭窄  

Target disease：

spondyloarthritis&carotid artery stenosis

研究疾病代码：

Target disease code：

研究类型：

干预性研究

Study type：

Interventional study

研究所处阶段：

 探索性研究/预试验 

Study phase：

0

研究设计：

随机平行对照 

Study design：

Parallel 

研究目的：

研究辅助诊疗机器人在神经内科病房的三个核心应用场景（机器人问诊病历自动生成、机器人宣教和机器人风险预测）中的实践效果，通过数据分析与实地调研，全面评估其在提高医疗服务质量和效率方面的潜力；研究辅助诊疗机器人在风湿免疫科的辅助问诊、影像判读和预测诊断实践效果；研究axSpA专病大模型和Agent系统在风湿科门诊的实际应用效果；研究辅助诊疗机器人在风湿免疫科病房的三个核心应用场景（机器人问诊病历自动生成、机器人宣教和机器人康复训练）中的实践效果。  

Objectives of Study：

Firstly, the practical effects of auxiliary diagnosis and treatment robots in three core application scenarios of neurology wards (automatic generation of medical records by robots, robot education, and robot risk prediction) will be studied. Through data analysis and field research, their potential in improving the quality and efficiency of medical services will be comprehensively evaluated. Next, we will study the practical effects of auxiliary diagnosis and treatment robots in the rheumatology and immunology department for assisting in inquiry, image interpretation, and predictive diagnosis. Next, we will study the practical application effects of the axSpA specialized disease model and Agent system in rheumatology clinics. Finally, the practical effects of auxiliary diagnosis and treatment robots in three core application scenarios of rheumatology and immunology wards (automatic generation of robot medical records, robot education, and robot rehabilitation training) will be studied.

药物成份或治疗方案详述：

 

Description for medicine or protocol of treatment in detail：

 

纳入标准：

1.颈动脉狭窄辅助诊疗机器人在神经内科的应用研究纳入标准 （1）单侧或双侧颅外段颈动脉狭窄或闭塞患者； （2）会说普通话； （3）患者或家属知情同意。 2.中轴型脊柱关节炎辅助诊疗机器人在风湿免疫科的临床应用研究纳入标准 （1）年龄在18 至 70 岁的住院患者； （2）入组患者为风湿免疫科入院的病人； （3）能够使用普通话或当地语言进行有效沟通； （4）意识清楚，具备完成调查问卷和参与问诊的能力； （5）自愿参与本研究，并签署知情同意书。 3.axSpA专病大模型在风湿免疫科门诊的应用研究纳入标准 （1）年龄在18 至45 岁的门诊患者； （2）入组患者为风湿免疫科门诊病人； （3）能够使用普通话或当地语言进行有效沟通； （4）意识清楚，具备完成调查问卷和参与问诊的能力； （5）自愿参与本研究，并签署知情同意书。

Inclusion criteria

1. Inclusion criteria for the application research of auxiliary diagnosis and treatment robots for carotid artery stenosis in neurology (1) Patients with unilateral or bilateral extracranial carotid artery stenosis or occlusion; (2) Can speak Mandarin; (3) Informed consent from patients or family members. 2. Inclusion criteria for clinical application research of axial spinal arthritis assisted diagnosis and treatment robot in rheumatology and immunology department (1) Hospitalized patients aged 18 to 70 years old; (2) The enrolled patients are those admitted to the rheumatology and immunology department; (3) Ability to communicate effectively in Mandarin or local language; (4) Clear consciousness and the ability to complete survey questionnaires and participate in consultations; (5) Voluntarily participate in this study and sign an informed consent form. 3. Inclusion criteria for the application research of axSpA specialized disease model in rheumatology and immunology outpatient clinics (1) Outpatient patients aged 18 to 45 years old; (2) The enrolled patients are outpatient patients from the rheumatology and immunology department; (3) Ability to communicate effectively in Mandarin or local language; (4) Clear consciousness and the ability to complete survey questionnaires and participate in consultations; (5) Voluntarily participate in this study and sign an informed consent form.

排除标准：

1.颈动脉狭窄辅助诊疗机器人在神经内科的应用研究排除标准 （1）存在言语不清、意识障碍或其他精神行为异常情况的患者； （2）有心、肝、肾、肺等重要器官不全者； （3）处于孕期的颈动脉狭窄患者； （4）恶性肿瘤患者。 2.中轴型脊柱关节炎辅助诊疗机器人在风湿免疫科的临床应用研究排除标准 （1）急诊入院或入院后需立即手术的患者； （2）患有严重精神障碍或认知功能障碍； （3）危重病情（如心肺复苏后、呼吸衰竭、肾衰竭等）或不稳定生命体征； （4）对问诊过程或查房情景存在明显排斥反应，可能影响研究过程的患者； （5）曾参与类似临床试验或使用过研究中相关干预措施的患者； （6）临床医生判断患者无法完成试验或可能因参与研究导致不良后果者。 3.axSpA专病大模型在风湿免疫科门诊的应用研究排除标准 （1）需立即手术的患者； （2）无交流沟通阅读能力； （3）患有严重的精神疾病或认知功能障碍。

Exclusion criteria：

1.Exclusion criteria for the application research of carotid artery stenosis assisted diagnosis and treatment robot in neurology (1) Patients with unclear speech, consciousness disorders, or other abnormal mental behavior; (2) Individuals with heart, liver, kidney, lung and other important organ deficiencies; (3) Patients with carotid artery stenosis during pregnancy; (4) Patients with malignant tumors. 2. Exclusion criteria for clinical application research of axial spinal arthritis assisted diagnosis and treatment robot in rheumatology and immunology department (1) Patients admitted to the emergency department or requiring immediate surgery upon admission; (2) Suffering from severe mental or cognitive impairments; (3) Critical illness (such as post cardiopulmonary resuscitation, respiratory failure, renal failure, etc.) or unstable vital signs; (4) Patients who have obvious rejection reactions to the consultation process or ward rounds, which may affect the research process; (5) Patients who have participated in similar clinical trials or used relevant interventions in the study; (6) Clinical doctors determine that patients are unable to complete the trial or may experience adverse consequences due to their participation in the study. 3.Exclusion criteria for the application of axSpA specialized disease model in rheumatology and immunology outpatient clinics (1) Patients who require immediate surgery; (2) Lack of communication and reading skills; (3) Suffering from severe mental illness or cognitive impairment.

研究实施时间：

Study execute time：

从 From 2025-10-24 00:00:00至 To 2027-07-31 00:00:00  

征募观察对象时间：

Recruiting time：

从 From 2025-11-03 00:00:00 至 To 2027-07-31 00:00:00

干预措施：

Interventions：

组别：

机器人问诊组

样本量：

 960

Group：

Robot Consultation Team

Sample size：

干预措施：

机器人独立查房并自动生成结构化病历（包含颈动脉狭窄患者问诊和强直性脊柱炎患者），研究期间医生不在现场。

干预措施代码：

Intervention：

The robot independently conducts ward rounds and automatically generates structured medical records (including consultations with patients with carotid artery stenosis and ankylosing spondylitis), with doctors not present during the study period.

Intervention code：

组别：

医生问诊组

样本量：

 960

Group：

Doctor Consultation Team

Sample size：

干预措施：

医生独立查房并手写查房病历（包含颈动脉狭窄患者问诊和强直性脊柱炎患者），研究期间禁止医生查看机器人生成的病历。

干预措施代码：

Intervention：

Doctors independently conduct ward rounds and handwrite ward round medical records (including consultations with patients with carotid artery stenosis and ankylosing spondylitis). During the study, doctors are prohibited from viewing the medical records generated by the robot.

Intervention code：

组别：

机器人宣教组

样本量：

 788

Group：

Robot Health Education Group

Sample size：

干预措施：

机器人对患者进行语音播报健康管理事项并带领患者熟悉病房环境（包含颈动脉狭窄患者问诊和强直性脊柱炎患者），护士不在现场。

干预措施代码：

Intervention：

Robots provide voice announcements on health management matters to patients and lead them to familiarize themselves with the ward environment (including consultations for patients with carotid artery stenosis and ankylosing spondylitis), while nurses are not present on site.

Intervention code：

组别：

护士宣教组

样本量：

 788

Group：

Nurse Health Education Group

Sample size：

干预措施：

护士向患者宣讲健康管理事项并带领患者熟悉病房环境（包含颈动脉狭窄患者问诊和强直性脊柱炎患者），机器人不在现场。

干预措施代码：

Intervention：

Nurses explain health management matters to patients and lead them to familiarize themselves with the ward environment (including consultations with patients with carotid artery stenosis and ankylosing spondylitis), while robots are not present on site.

Intervention code：

组别：

机器人康复训练组

样本量：

 142

Group：

Robot Rehabilitation Training Group

Sample size：

干预措施：

无干预

干预措施代码：

Intervention：

non-intervention

Intervention code：

组别：

护士康复训练组

样本量：

 142

Group：

Nurse Rehabilitation Training Group

Sample size：

干预措施：

无干预

干预措施代码：

Intervention：

non-intervention

Intervention code：

组别：

专病模型门诊问诊组

样本量：

 246

Group：

Specialized Disease Model Outpatient Consultation Group

Sample size：

干预措施：

由 axSpA 专病大模型独立完成问诊对话并自动生成门诊病历；研究期间低年资医生仅在场保障安全，不主动提问、不书写记录。

干预措施代码：

Intervention：

Independently complete the consultation dialogue and automatically generate outpatient medical records using the axSpA specialized disease model; During the research period, junior doctors were only present to ensure safety and did not actively ask questions or write records.

Intervention code：

组别：

医生门诊问诊组

样本量：

 246

Group：

Doctor Outpatient Consultation Team

Sample size：

干预措施：

由低年资医生按常规流程独立完成问诊并手工书写门诊病历；禁用大模型辅助，确保反映其真实日常水平。

干预措施代码：

Intervention：

Independently completing consultations and manually writing outpatient medical records by junior doctors according to routine procedures; Disable large model assistance to ensure it reflects its true daily level.

Intervention code：

组别：

专病模型诊断组

样本量：

 600

Group：

Specialized Disease Model Diagnosis Group

Sample size：

干预措施：

本研究为诊断准确性研究，未对患者实施任何干预。

干预措施代码：

Intervention：

This study is a diagnostic accuracy study and no intervention was performed on the patients

Intervention code：

研究实施地点：

Countries of recruitment and research settings：

国家：

 中国

省(直辖市)：

 北京 

市(区县)：

  

Country：

China

Province：

Beijing

City：

单位(医院)：

 中国人民解放军总医院 

单位级别：

 三甲 

Institution
hospital：

Chinese PLA General Hospital

Level of the institution：

Tertiary A

测量指标：

Outcomes：

指标中文名：

病历质量评分（查房病历和门诊病历）

指标类型：

主要指标

Outcome：

Medical record quality rating (ward round medical records and outpatient medical records)

Type：

Primary indicator

测量时间点：

测量方法：

Measure time point of outcome：

Measure method：

指标中文名：

病历完成时间（查房病历和门诊病历）

指标类型：

次要指标

Outcome：

Completion time of medical records (ward round medical records and outpatient medical records)

Type：

Secondary indicator

测量时间点：

测量方法：

Measure time point of outcome：

Measure method：

指标中文名：

宣教满意度

指标类型：

主要指标

Outcome：

Satisfaction with education and propaganda

Type：

Primary indicator

测量时间点：

测量方法：

Measure time point of outcome：

Measure method：

指标中文名：

宣教用时

指标类型：

次要指标

Outcome：

Health education time

Type：

Secondary indicator

测量时间点：

测量方法：

Measure time point of outcome：

Measure method：

指标中文名：

机器人康复训练满意度

指标类型：

主要指标

Outcome：

Satisfaction with robot rehabilitation training

Type：

Primary indicator

测量时间点：

测量方法：

Measure time point of outcome：

Measure method：

指标中文名：

灵敏度

指标类型：

主要指标

Outcome：

Sensitivity

Type：

Primary indicator

测量时间点：

测量方法：

Measure time point of outcome：

Measure method：

指标中文名：

特异性

指标类型：

主要指标

Outcome：

Specificity

Type：

Primary indicator

测量时间点：

测量方法：

Measure time point of outcome：

Measure method：

指标中文名：

诊断时间

指标类型：

次要指标

Outcome：

Diagnosis time

Type：

Secondary indicator

测量时间点：

测量方法：

Measure time point of outcome：

Measure method：

采集人体标本：

Collecting sample(s)
from participants：

标本中文名：

无

组织：

Sample Name：

None

Tissue：

人体标本去向

 其它  

说明

Fate of sample：

0thers  

Note：

征募研究对象情况：

Recruiting status：

尚未开始

Not yet recruiting

年龄范围：

Participant age：
最小 Min age 18 岁 years
最大 Max age 70 岁 years

性别：

男女均可

Gender：

Both

随机方法（请说明由何人用什么方法产生随机序列）：

1.机器人独立查房：按照分层区组随机化，由独立统计师??，使用SAS PROC PLAN或R blockrand包生成。为每个中心-科室组合（如：中心A-神经内科、中心A-风湿科...）生成独立的随机序列。 2.机器人健康宣教?：按病区和护理单元分层，由研究协调员??，使用在线随机化工具（如Research Randomizer）或统计软件生成区组随机序列。 3.专病模型生成病历?：采取个体简单随机化?，患者在挂号时，由医疗内网内置的随机算法自动分配，拟使用SQL的 RAND()函数。 4.专病模型辅助诊断：配对设计下的随机化?，由独立程序员??编写脚本，对每个病例，随机决定??模型诊断??和??医生诊断??报告的??呈现顺序??。?

Randomization Procedure (please state who generates the random number sequence and by what method)：

1. Robot independent ward rounds: Randomly divided into stratified groups, generated by independent statisticians using SAS PROC PLAN or R blockrand packages. For each center department combination (e.g. Center A - Neurology, Center A - Rheumatology) Generate independent random sequences. 2. Robot health education: Stratified by ward and nursing unit, the study coordinator uses online randomization tools (such as Research Randomizer) or statistical software to generate randomized sequences for each ward. 3. Specialized disease model generates medical records: Individual simple randomization is adopted, and patients are automatically assigned by a random algorithm built into the medical intranet during registration, using the RAND() function of SQL. 4. Specialized disease model assisted diagnosis: Randomization under paired design, written by independent programmers, randomly determines the presentation order of model diagnosis and doctor's diagnosis report for each case. ?

是否公开试验完成后的统计结果:

Calculated Results after the Study Completed public access:

公开/Public

盲法：

1.机器人独立查房： 设盲角色为患者和结局评估者（病历评审专家）。采取结局评估者设盲方法，将所有生成的病历去除所有标识（如分组信息、提及“机器人”或特定医生的内容），由不知分组情况的独立专家小组进行盲态评审。病历的呈现顺序应打乱。 2. 机器人健康宣教?：设盲角色为结局评估者（数据收集/分析者），采取结局评估者设盲方法，负责发放和收集满意度问卷的研究助理??不应知晓??患者的分组情况。问卷上仅标注患者ID，不包含任何分组信息。数据分析人员在统计分析前，数据中的分组变量应被编码（如A组/B组）。 3.专病模型生成病历：设盲角色为结局评估者（病历评审专家）?，采取结局评估者设盲方法，方案同研究1。将所有门诊病历匿名化、打乱顺序后，交由独立的盲态评审委员会进行质量评估。评审专家不知道每份病历的来源是AI预处理还是医生独立书写。 4.专病模型辅助诊断：设盲角色为??参与医生、金标准评估者??，采取金标准评估者设盲方法，负责判定最终诊断正确与否的专家小组，在评估时应不知道哪份诊断报告来自AI，哪份来自医生。所有报告应匿名并随机编号。

Blinding：

1. Robot independent ward rounds: Set blind roles as patients and outcome assessors (medical record review experts). Adopting the outcome evaluator blinding method, all generated medical records are stripped of all identifiers (such as grouping information, references to "robots" or specific doctors), and a blind review is conducted by an independent expert group who is unaware of the grouping situation. The presentation order of medical records should be disrupted. 2. Robot health education: Set the blind role as the outcome evaluator (data collector/analyst), adopt the outcome evaluator blinding method, and the research assistant responsible for distributing and collecting satisfaction questionnaires should not be aware of the patient grouping situation. The questionnaire only indicates the patient ID and does not contain any grouping information. Before conducting statistical analysis, data analysts should encode the grouping variables in the data (such as Group A/Group B). 3. Specialized disease model generates medical records: The blinded role is the outcome evaluator (medical record review expert), and the outcome evaluator blinding method is adopted. The protocol is the same as Study 1. After anonymizing and reordering all outpatient medical records, they will be submitted to an independent blind review committee for quality assessment. The reviewing experts do not know whether the source of each medical record is AI preprocessing or independent writing by doctors. 4. Specialized disease model assisted diagnosis: The blind role is set as participating doctors and gold standard evaluators, using the gold standard evaluator blind method. The expert group responsible for determining the correctness of the final diagnosis should not know which diagnostic report comes from the AI and which one comes from the doctor during the evaluation. All reports should be anonymous and randomly numbered. ?

试验完成后的统计结果（上传文件）：

Calculated Results after
the Study Completed(upload file)：

是否共享原始数据：

IPD sharing

否No

共享原始数据的方式（说明：请填入公开原始数据日期和方式，如采用网络平台，需填该网络平台名称和网址）：

无

The way of sharing IPD”(include metadata and protocol, If use web-based public database, please provide the url)：

None

数据采集和管理（说明：数据采集和管理由两部分组成，一为病例记录表(Case Record Form, CRF)，二为电子采集和管理系统(Electronic Data Capture, EDC)，如ResMan即为一种基于互联网的EDC：

数据通过医院HIS系统和相关信息以及自研的Agent系统采集。所有数据为医疗内网存在管理，不接入外网。以保证数据和患者信息安全。

Data collection and Management (A standard data collection and management system include a CRF and an electronic data capture：

The data is collected through the hospital HIS system and related information, as well as the self-developed Agent system. All data is managed within the medical intranet and is not connected to the external network. To ensure the security of data and patient information. ?

数据与安全监察委员会：

Data and Safety Monitoring Committee：

暂未确定/Not yet

注册人：

Name of Registration：

  2025-11-02 23:13:09