使用多模态大语言模型辅助门诊患者分诊的应用研究

注册号:

Registration number:

ChiCTR2500104394 

最近更新日期:

Date of Last Refreshed on:

2025-06-17 08:29:36 

注册时间:

Date of Registration:

2025-06-17 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

使用多模态大语言模型辅助门诊患者分诊的应用研究

Public title:

Application of a multimodal large language model to assist outpatient triage

注册题目简写:

English Acronym:

研究课题的正式科学名称:

使用多模态大语言模型辅助门诊患者分诊的应用研究

Scientific title:

Application of a multimodal large language model to assist outpatient triage

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:

孟祥彬 

研究负责人:

苗孟丹 

Applicant:

Xiangbin Meng 

Study leader:

Miao Mengdan 

申请注册联系人电话:

Applicant telephone:

+86 158 9685 0171

研究负责人电话:

Study leader's
telephone:

+86 180 3293 6267

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:

15896850171@163.com

研究负责人电子邮件:

Study leader's E-mail:

15896850171@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:

河北省邯郸市丛台区丛台路25号

研究负责人通讯地址:

河北省邯郸市丛台区丛台路25号

Applicant address:

No. 25, Congtai Road, Congtai District, Handan, Hebei

Study leader's address:

No. 25, Congtai Road, Congtai District, Handan, Hebei

申请注册联系人邮政编码:

Applicant postcode:

056001

研究负责人邮政编码:

Study leader's postcode:

056001

申请人所在单位:

邯郸市第一医院

Applicant's institution:

Handan First Hospital

研究负责人所在单位:

邯郸市第一医院

Affiliation of the Leader:

Handan First Hospital

是否获伦理委员会批准:

Approved by ethic committee:

Yes

伦理委员会批件文号:

Approved No. of ethic committee:

HDYY-LW-25002

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:

邯郸市第一医院医学伦理委员会

Name of the ethic committee:

Medical Ethics Committee of Handan First Hospital

伦理委员会批准日期:

Date of approved by ethic committee:

2024-01-02 00:00:00

伦理委员会联系人:

路新卿

Contact Name of the ethic committee:

Lu Xinqing

伦理委员会联系地址:

河北省邯郸市丛台区丛台路25号

Contact Address of the ethic committee:

No. 25, Congtai Road, Congtai District, Handan, Hebei

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 180 3293 6267

伦理委员会联系人邮箱:

Contact email of the ethic committee:

m18032936267@163.com

研究实施负责(组长)单位:

邯郸市第一医院

Primary sponsor:

Handan First Hospital

研究实施负责(组长)单位地址:

河北省邯郸市丛台区丛台路25号

Primary sponsor's address:

No. 25, Congtai Road, Congtai District, Handan, Hebei

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

中国

省(直辖市):

河北

市(区县):

邯郸

Country:

China

Province:

Hebei

City:

Handan

单位(医院):

邯郸市第一医院

具体地址:

河北省邯郸市丛台区丛台路25号

Institution
hospital:

Handan First Hospital

Address:

No. 25, Congtai Road, Congtai District, Handan, Hebei

经费或物资来源:

医院经费支持

Source(s) of funding:

Hospital funding support

研究疾病:

无  

Target disease:

None

研究疾病代码:

Target disease code:

研究类型:

观察性研究

Study type:

Observational study

研究所处阶段:

其它 

Study phase:

N/A

研究设计:

横断面 

Study design:

Cross-sectional 

研究目的:

研究目的旨在使用多模态大语言模型门诊分诊的应用价值。评估其在准确性和效率上的表现,并与传统分诊方法进行比较。探究该模型能否有效减轻医务人员的工作负担,同时提高分诊的速度和质量。此外,评估该模型在预测需进一步住院治疗的能力。还包括调查患者对使用AI辅助分诊系统的接受度和满意度。分析采用这种技术的经济效益,包括成本节约和资源的优化配置。  

Objectives of Study:

The purpose of this study is to investigate the application value of a multimodal large language model for outpatient triage. To evaluate its performance in terms of accuracy and efficiency and compare it with traditional triage methods. To explore whether the model can effectively reduce the workload of medical staff while improving the speed and quality of triage. In addition, to evaluate the model's ability to predict the need for further hospitalization. It also includes investigating patients' acceptance and satisfaction with the use of an AI-assisted triage system. Analyze the economic benefits of adopting this technology, including cost savings and optimal allocation of resources.

药物成份或治疗方案详述:

 

Description for medicine or protocol of treatment in detail:

 

纳入标准:

Inclusion criteria

排除标准:

1. 重度认知障碍或无法沟通的患者。 2. 已有明确转诊到特定科室的患者(例如部分外地转诊病人或120转运患者,该部分患者可能直接进入绿色通道)。 3. 生命体征不稳定的患者 4. 有潜在医患纠纷的患者 5. 正在参与其他临床试验; 6. 无法遵循试验程序; 7. 拒绝签署知情同意书者。

Exclusion criteria:

1. Patients with severe cognitive impairment or inability to communicate. 2. Patients who have been clearly referred to a specific department (e.g. some patients referred from other places or transferred by 120, these patients may enter the green channel directly). 3. Patients with unstable vital signs 4. Patients with potential medical disputes 5. Patients participating in other clinical trials; 6. Unable to follow the trial procedures; 7. Those who refuse to sign the informed consent form.

研究实施时间:

Study execute time:

From 2024-02-01 00:00:00 To 2025-12-30 00:00:00  

征募观察对象时间:

Recruiting time:

From 2025-06-30 00:00:00 To 2025-10-30 00:00:00

干预措施:

Interventions:

组别:

大模型辅助分诊组

样本量:

250

Group:

Large model assisted triage group

Sample size:

干预措施:

干预措施代码:

1

Intervention:

None

Intervention code:

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

河北 

市(区县):

邯郸 

Country:

China

Province:

Hebei

City:

Handan

单位(医院):

邯郸市第一医院 

单位级别:

三甲 

Institution
hospital:

Handan First Hospital

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

分诊准确性

指标类型:

主要指标

Outcome:

Triage accuracy

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

分诊时间效率

指标类型:

主要指标

Outcome:

Triage time efficiency

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

患者满意度

指标类型:

次要指标

Outcome:

Patient satisfaction with triage experience

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

风险预测能力

指标类型:

次要指标

Outcome:

Risk prediction ability

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

医疗资源分配

指标类型:

主要指标

Outcome:

Allocation of medical resources

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

医务人员满意度

指标类型:

次要指标

Outcome:

Medical staff satisfaction

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

经济评估

指标类型:

次要指标

Outcome:

Economic evaluation

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

系统适应性和稳定性

指标类型:

次要指标

Outcome:

System adaptability and stability

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:

组织:

Sample Name:

N/A

Tissue:

N/A

人体标本去向

其它  

说明

Fate of sample:

0thers  

Note:

N/A

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 years
最大 Max age 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):

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

None

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:

Blinding:

None

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

是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):

原始数据将于研究完成后公开,预计公开日期为2025年10月30日。数据将通过ResMan平台共享,平台名称为“中国临床试验注册中心研究管理平台 (ResMan)”,网址为:http://www.medresman.org.cn。共享数据包括去标识化的患者分诊数据、多模态语言模型输出结果及统计分析数据集,供学术研究使用。

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

The raw data will be made public after the study is completed, with an estimated release date of October 30, 2025. The data will be shared through the ResMan platform, which is called the China Clinical Trial Registry Research Management Platform (ResMan) and is available at http://www.medresman.org.cn. The shared data includes de-identified patient triage data, multimodal language model output results, and statistical analysis data sets for academic research.

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:

病例记录表 (CRF):采用标准化的纸质和电子病例记录表,记录患者基本信息(如年龄、性别、主诉)、分诊结果(模型分诊和人工分诊)以及随访数据。CRF由研究人员在门诊现场填写,并定期录入电子系统。 电子采集和管理系统 (EDC):使用ResMan平台(中国临床试验注册中心研究管理平台,网址:http://www.medresman.org.cn)进行数据电子采集和管理。研究数据通过ResMan实时上传、存储和审核,确保数据完整性和安全性。EDC系统支持数据输入、质控和导出功能,由研究协调员负责管理。

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

Case Record Form (CRF): Standardized paper and electronic case record forms are used to record basic patient information (such as age, gender, chief complaint), triage results (model triage and manual triage), and follow-up data. CRF is filled out by researchers at the outpatient clinic and entered into the electronic system regularly. Electronic Collection and Management System (EDC): The ResMan platform (China Clinical Trial Registry Research Management Platform, website: http://www.medresman.org.cn) is used for electronic data collection and management. Research data is uploaded, stored, and reviewed in real time through ResMan to ensure data integrity and security. The EDC system supports data input, quality control, and export functions, and is managed by the research coordinator.

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:

 2025-06-17 08:29:30