ChiCTR2600116200 版本V1.0 版本创建时间2026/01/06 17:46:57 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:

ChiCTR2600116200 

最近更新日期:

Date of Last Refreshed on:

2026-01-06 17:46:45 

注册时间:

Date of Registration:

2026-01-06 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

人机协作模式下门诊病历自动生成智能体的开发与应用

Public title:

Development and Application of an AI Agent for Automated Outpatient Medical Record Generation under a Human–AI Collaboration Model

注册题目简写:

English Acronym:

研究课题的正式科学名称:

人机协作模式下门诊病历自动生成智能体的开发与应用

Scientific title:

Development and Application of an AI Agent for Automated Outpatient Medical Record Generation under a Human–AI Collaboration Model

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:

陈媛 

研究负责人:

陈媛 

Applicant:

Yuan Chen 

Study leader:

Chen Yuan 

申请注册联系人电话:

Applicant telephone:

+86 135 9950 6301

研究负责人电话:

Study leader's telephone:

+86 592 299 3237

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:

28837445@qq.com

研究负责人电子邮件:

Study leader's E-mail:

28837445@qq.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:

厦门市湖里区金山路2999号

研究负责人通讯地址:

厦门市湖里区金山路2999号

Applicant address:

No. 2999 Jinshan Road, Huli District, Xiamen, China

Study leader's address:

No. 2999 Jinshan Road, Huli District, Xiamen, China

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:

厦门大学附属心血管病医院

Applicant's institution:

Xiamen Cardiovascular Hospital of Xiamen University

研究负责人所在单位:

厦门大学附属心血管病医院

Affiliation of the Leader:

Xiamen Cardiovascular Hospital Xiamen University

是否获伦理委员会批准:

是/Yes

Approved by ethic committee:

Yes

伦理委员会批件文号:

Approved No. of ethic committee:

(2025)医伦科第(67)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:

厦门大学附属心血管病医院医学伦理委员会

Name of the ethic committee:

Ethics Committee of Xiamen Cardiovascular Hospital Xiamen University

伦理委员会批准日期:

Date of approved by ethic committee:

2025-12-26 00:00:00

伦理委员会联系人:

严妍

Contact Name of the ethic committee:

Yan Yan

伦理委员会联系地址:

厦门市湖里区金山路2999号

Contact Address of the ethic committee:

No. 2999 Jinshan Road, Huli District, Xiamen, China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 592 2292562

伦理委员会联系人邮箱:

Contact email of the ethic committee:

1039734296@qq.com

研究实施负责(组长)单位:

厦门大学附属心血管病医院

Primary sponsor:

Xiamen Cardiovascular Hospital Xiamen University

研究实施负责(组长)单位地址:

厦门市湖里区金山路2999号

Primary sponsor's address:

No. 2999 Jinshan Road, Huli District, Xiamen, China

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

中国

省(直辖市):

福建省

市(区县):

Country:

China

Province:

Fujian

City:

单位(医院):

厦门大学附属心血管病医院

具体地址:

厦门市湖里区金山路2999号

Institution
hospital:

Xiamen Cardiovascular Hospital Xiamen University

Address:

No. 2999 Jinshan Road, Huli District, Xiamen, China

经费或物资来源:

人机协作模式下门诊病历自动生成智能体的开发与应用

Source(s) of funding:

Department of Nursing, Xiamen Cardiovascular Hospital of Xiamen University

Target disease:

None

Target disease code:

研究类型:

干预性研究

Study type:

Interventional study

研究所处阶段:

其它 

Study phase:

N/A

研究设计:

随机交叉对照 

Study design:

Cross-over 

研究目的:

开发一款“门诊医患对话”实时转化为“结构化病历”的智能体,辅助门诊医生生成电子病历,并验证其可行性、可用性及有效性,减轻医生文书负担。  

Objectives of Study:

To develop an intelligent agent that converts real-time outpatient doctor–patient dialogues into structured medical records, assisting physicians in generating electronic medical records, and to evaluate its feasibility, usability, and effectiveness in reducing physicians’ documentation burden.

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.在岗执业医师,职称为主治医师及以上; 2.每周至少承担2个半日门诊; 3.熟悉本院电子病历系统操作流程,具备独立完成病历记录的能力; 4.会使用该智能体; 5.自愿参加。

Inclusion criteria

1. Licensed practicing physician, with a professional title of attending physician or above; 2.Responsible for at least two half-day outpatient clinics per week; 3. Familiar with the hospital’s electronic medical record system and capable of independently completing medical record documentation; 4. Able to use the AI assistant; 5.Willing to participate voluntarily.

排除标准:

1.实习医生、进修医生或非固定门诊医生; 2.近3?个月未参与门诊病历书写任务者; 3.病历质量评估专家委员会成员。 4.有跟专护士。

Exclusion criteria:

1. Interns, resident physicians in training, or physicians without a fixed outpatient schedule; 2.Those who have not participated in outpatient medical record documentation in the past three months; 3. Members of the medical record quality evaluation expert committee; 4.Physicians paired with specialist nurses.

研究实施时间:

Study execute time:

From 2025-11-20 00:00:00 To 2027-09-30 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-01-06 00:00:00 To 2026-01-18 00:00:00  

干预措施:

Interventions:

组别:

A组(干预-对照顺序)

样本量:

6

Group:

A(Intervention-control sequence)

Sample size:

干预措施:

阶段l:使用智能体辅助书写病历;阶段ll:不使用智能体辅助书写病历

干预措施代码:

Intervention:

Phase I: Agent-assisted medical record documentation. Phase II: Conventional medical record documentation without agent assistance.

Intervention code:

组别:

B组(对照-干预顺序)

样本量:

6

Group:

B(Comparison-Intervention Sequence)

Sample size:

干预措施:

阶段l:不使用智能体辅助书写病历;阶段ll:使用智能体辅助书写病历

干预措施代码:

Intervention:

Phase I: Conventional medical record documentation without agent assistance.Phase II:Agent-assisted medical record documentation.

Intervention code:

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

福建省 

市(区县):

 

Country:

China 

Province:

Fujian 

City:

 

单位(医院):

厦门大学附属心血管病医院 

单位级别:

三级甲等 

Institution
hospital:

Xiamen Cardiovascular Hospital Xiamen University

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

病历质量评分

指标类型:

主要指标

Outcome:

Medical record quality score

Type:

Primary indicator

测量时间点:

阶段1结束、阶段2结束

测量方法:

由 3 名专家采用统一标准(自行设计的门诊病历质量评估调查表)进行人工评估。

Measure time point of outcome:

End of Phase I; End of Phase II

Measure method:

Manually assessed by three experts using a unified standard (a self-developed outpatient medical record quality assessment questionnaire).

指标中文名:

医生专注在病人身上的时长

指标类型:

次要指标

Outcome:

Physician-patient direct interaction time

Type:

Secondary indicator

测量时间点:

阶段I、阶段II

测量方法:

指医生在整个就诊过程中非操作电脑、 面向患者进行直接交流的时长,用于反映医生注意力分配。通过 EV 录屏与研究助理现场计时结合的方法进行评估。

Measure time point of outcome:

Phase I, Phase II

Measure method:

Refers to the duration during the entire consultation in which the physician is not operating the computer and is directly engaging with the patient, used to reflect physician attention allocation. This was assessed using a combination of EV screen recording and on-site timing by research assistants.

指标中文名:

病历生成总用时

指标类型:

主要指标

Outcome:

Total medical record generation time

Type:

Primary indicator

测量时间点:

阶段I、阶段II

测量方法:

指医生从开启电子病历文档到最终提交完成所用的总时长(单位:分钟),用于评估智能体对病历书写效率的影响。采用EV录屏方式记录病历提交时间及病历开始书写时间,之后通过人工进行计算

Measure time point of outcome:

Phase I, Phase II

Measure method:

Refers to the total time (in minutes) from opening the electronic medical record to final submission, used to evaluate the impact of the AI assistant on medical record documentation efficiency. The start and submission times of medical record documentation were recorded using the EV screen-recording system, and the total duration was calculated manually.

指标中文名:

手动输入字符时长

指标类型:

主要指标

Outcome:

Duration of manual character input

Type:

Primary indicator

测量时间点:

阶段I、阶段II

测量方法:

指在病历生成的全过程中,医生手指在键盘上实际进行按键操作的累计净时间。采用EV录屏方式记录,之后通过人工进行计算。

Measure time point of outcome:

Phase I, Phase II

Measure method:

Refers to the cumulative net time during the entire medical record generation process in which the physician’s fingers were actively engaged in keystroke input on the keyboard. Recorded using the EV screen-recording system and subsequently calculated manually

指标中文名:

医生满意度

指标类型:

主要指标

Outcome:

Physician satisfaction

Type:

Primary indicator

测量时间点:

阶段I结束、阶段II结束

测量方法:

采用自行设计的《医生满意度问卷》进行测量。

Measure time point of outcome:

End of Phase I; End of Phase II

Measure method:

Measured using a self-developed Physician Satisfaction Questionnaire.

指标中文名:

手动输入字数

指标类型:

主要指标

Outcome:

Number of manually entered characters

Type:

Primary indicator

测量时间点:

阶段I、阶段II

测量方法:

指在病历生成的全过程中手动输入的净字数。通过搜狗输入法后台自动记录,之后进行人工核算。

Measure time point of outcome:

Phase I, Phase II

Measure method:

Refers to the net number of characters manually entered during the entire medical record generation process. This was automatically recorded by the backend of the Sogou Input Method and subsequently verified through manual calculation.

指标中文名:

用户行为分析(医生调用智能体的次数、引用率、复制率)

指标类型:

次要指标

Outcome:

User behavior analysis (including the number of times physicians accessed the AI assistant, citation rate, and copy rate).

Type:

Secondary indicator

测量时间点:

阶段I、阶段II

测量方法:

由系统日志导出。

Measure time point of outcome:

Phase I, Phase II

Measure method:

Exported from the system logs.

指标中文名:

净推荐值

指标类型:

主要指标

Outcome:

Net Promoter Score (NPS)

Type:

Primary indicator

测量时间点:

阶段I结束、阶段II结束

测量方法:

通过“您是否愿意向同事推荐此智能体系统?”单项评分获取

Measure time point of outcome:

End of Phase I; End of Phase II

Measure method:

Obtained via a single-item question: “Would you recommend this AI assistant system to your colleagues?”

指标中文名:

医生反馈

指标类型:

主要指标

Outcome:

Physician feedback

Type:

Primary indicator

测量时间点:

阶段I结束、阶段II结束

测量方法:

在每个阶段结束后(即医生完成智能体使用阶段后),及时开 展半结构式访谈,访谈提纲如下:1在使用智能体辅助病历生成的过程中,您有什么感受和体会?您认为它给您的工作带来的最大帮助或价值是什么?能否请您结合一两个具体事例谈谈?2基于您的使用经验,您认为哪些因素最能激励或驱动您在未来长期、主动地使用这个工具?3相反,在目前 的使用中,您遇到了哪些主要的不便、挑战或让您犹豫是否继续使用的因素?4 为使其更贴

Measure time point of outcome:

End of Phase I; End of Phase II

Measure method:

Semi-structured Interviews:What are your experiences and impressions while using the AI assistant to support medical record generation?What do you consider its greatest benefit or value to your work? Could you provide one or two specific examples?Based on your experience, which factors do you think most motivate or drive you to use this tool proactively and consistently in the future?Conversely, what major inconveniences, challenges, or factors have caused hesitation in your current use of the s

采集人体标本:

Collecting sample(s)
from participants:

标本中文名:

组织:

Sample Name:

NA

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:

正在进行

Recruiting

年龄范围:

Participant age:

最小 Min age 18 years
最大 Max age 100 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):

由不直接参与本研究的随机数字保管员 Research Randomizer(https://www.randomizer.org/) 生成一套1~12的随机数字序列

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

A sequence of random numbers from 1 to 12 was generated using Research Randomizer (https://www.randomizer.org/) by a custodian who is not directly involved in this study.

是否公开试验完成后的统计结果:

Calculated Results after the Study Completed public access:

不公开/Private

盲法:

开放标签

Blinding:

Open-label study

是否共享原始数据:

IPD sharing

Yes

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):

数据和材料可向通讯作者提出请求后获取。

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

The data and materials are available upon request from the corresponding author.

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:

一、用户行为分析指标(调用次数、引用率、复制率)向系统后台获取 二、医生满意度、净推荐值由医生自行填写问卷获取 三、医生反馈通过半结构化访谈获取定性资料 四、病历生成总用时、手动输入字符时长、手动输入字数、 病历质量评分、专注在病人身上的时长为ev录屏、搜狗输入法结合人工核算获取

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

1.User behavior analysis indicators (number of accesses, citation rate, copy rate) were obtained from the system backend.2.Physician satisfaction and Net Promoter Score were collected via self-administered questionnaires.3.Physician feedback was collected as qualitative data through semi-structured interviews.4.Total medical record generation time, duration of manual character input, number of manually entered characters, medical record quality score, and physician-patient direct interaction time were obtained using EV screen recording and Sogou Input Method combined with manual calculation.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

有/Yes

注册人:

Name of Registration:

 2026-01-06 17:46:45