人工智能在急诊中的应用

注册号:

Registration number:

ChiCTR2600125287 

最近更新日期:

Date of Last Refreshed on:

2026-05-25 11:08:10 

注册时间:

Date of Registration:

2026-05-25 00:00:00 

注册号状态:

补注册

Registration Status:

Retrospective registration

注册题目:

人工智能在急诊中的应用

Public title:

Artificial Intelligence in Emergency Medicine

注册题目简写:

English Acronym:

研究课题的正式科学名称:

人工智能在急诊中的应用

Scientific title:

Artificial Intelligence in Emergency Medicine

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:

肖李锋 

研究负责人:

肖李锋 

Applicant:

Lifeng Xiao 

Study leader:

Lifeng Xiao 

申请注册联系人电话:

Applicant telephone:

+86 754 8859 9551

研究负责人电话:

Study leader's
telephone:

+86 754 8859 9551

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:

xiaolifeng05@163.com

研究负责人电子邮件:

Study leader's E-mail:

xiaolifeng05@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:

广东省汕头市金平区学成路1号

研究负责人通讯地址:

广东省汕头市金平区学成路1号

Applicant address:

No. 1 Xuecheng Road, Jinping District, Shantou, Guangdong

Study leader's address:

No. 1 Xuecheng Road, Jinping District, Shantou, Guangdong

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:

汕头大学医学院附属肿瘤医院

Applicant's institution:

Cancer Hospital Of Shantou University Medical College

研究负责人所在单位:

汕头大学医学院附属肿瘤医院

Affiliation of the Leader:

Cancer Hospital Of Shantou University Medical College

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:

2025-Ⅱ-025

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:

汕头大学医学院附属肿瘤医院医学伦理委员会

Name of the ethic committee:

The Medical Ethics Committee of the Affiliated Tumor Hospital of Shantou University Medical College

伦理委员会批准日期:

Date of approved by ethic committee:

2025-04-30 00:00:00

伦理委员会联系人:

刘宏芝

Contact Name of the ethic committee:

Hongzhi Liu

伦理委员会联系地址:

广东省汕头市金平区学成路1号

Contact Address of the ethic committee:

No. 1 Xuecheng Road, Jinping District, Shantou, Guangdong

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 137 2928 4905

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:

汕头大学医学院附属肿瘤医院

Primary sponsor:

Cancer Hospital Of Shantou University Medical College

研究实施负责(组长)单位地址:

广东省汕头市金平区学成路1号

Primary sponsor's address:

No. 1 Xuecheng Road, Jinping District, Shantou, Guangdong

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

中国

省(直辖市):

广东

市(区县):

汕头

Country:

China

Province:

Guangdong

City:

Shantou

单位(医院):

汕头大学医学院附属肿瘤医院

具体地址:

广东省汕头市金平区学成路1号

Institution
hospital:

Cancer Hospital Of Shantou University Medical College

Address:

No. 1 Xuecheng Road, Jinping District, Shantou, Guangdong

经费或物资来源:

自筹经费

Source(s) of funding:

Self-funded

研究疾病:

晚期癌症  

Target disease:

Advanced Cancer

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:

其它 

Study phase:

N/A

研究设计:

随机平行对照 

Study design:

Parallel 

研究目的:

1.探讨AI在急诊诊疗方案中的应用; 2.通过构建智能体等形式提高急诊急救效率。  

Objectives of Study:

1.Exploring the application of AI in emergency diagnosis and treatment protocols; 2.Enhancing the efficiency of emergency care through the development of agent-based systems and similar innovations.

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. 临床禁忌 需立即抢救的危重症(如心脏骤停、严重创伤、休克等) 妊娠或哺乳期妇女(治疗选择受特殊限制) 已知终末期疾病患者(预期寿命 <72 小时) 2. 信息完整性限制 语言障碍/认知障碍无法提供可靠病史 院前急救记录缺失超过关键信息项(如症状起始时间) 3. 研究干扰因素 同时参与其他干预性临床试验 涉及医疗纠纷或法医学鉴定的特殊病例

Exclusion criteria:

1.Clinical Contraindications Critically ill patients requiring immediate resuscitation (e.g., cardiac arrest, severe trauma, shock); Pregnant or breastfeeding women (due to specific treatment limitations); Patients with known end-stage disease (life expectancy < 72 hours). 2.Information Integrity Constraints Language or cognitive impairments preventing reliable history taking; Missing critical information in pre-hospital emergency records (e.g., symptom onset time). 3.Study Interference Factors Concurrent participation in other interventional clinical trials; Special cases involving medical disputes or forensic identification.

研究实施时间:

Study execute time:

From 2025-04-01 00:00:00 To 2026-03-03 00:00:00  

征募观察对象时间:

Recruiting time:

From 2025-04-01 00:00:00 To 2025-09-30 00:00:00

干预措施:

Interventions:

组别:

ChatGPT-4.0组

样本量:

30

Group:

ChatGPT-4.0 group

Sample size:

干预措施:

AI生成诊疗建议: 所有患者均接受一份基于其自身临床信息(包括人口学特征、疾病史、当前状况)生成的个性化复苏建议文档。建议内容涵盖疾病进展评估、可能出现的危急情况及复苏措施、复苏后预期生存率与生活质量、以及针对该患者的复苏价值综合评估。患者分别在阅读建议前和阅读建议后填写一份抢救意愿量表。

干预措施代码:

Intervention:

AI-generated treatment recommendations: All participants received a personalized resuscitation recommendation document generated based on their own clinical information (including demographic characteristics, medical history, and current condition). The recommendations covered: assessment of disease progression, potential critical scenarios requiring resuscitation, necessary resuscitation measures, estimated five-year survival rate and quality of life post-resuscitation, and a comprehensive evaluation of the value of resuscitation for that patient. Patients completed a resuscitation preference scale both before and after reading the recommendation document.

Intervention code:

组别:

Deepseek组

样本量:

30

Group:

Deepseek group

Sample size:

干预措施:

AI生成诊疗建议: 所有患者均接受一份基于其自身临床信息(包括人口学特征、疾病史、当前状况)生成的个性化复苏建议文档。建议内容涵盖疾病进展评估、可能出现的危急情况及复苏措施、复苏后预期生存率与生活质量、以及针对该患者的复苏价值综合评估。患者分别在阅读建议前和阅读建议后填写一份抢救意愿量表。

干预措施代码:

Intervention:

AI-generated treatment recommendations: All participants received a personalized resuscitation recommendation document generated based on their own clinical information (including demographic characteristics, medical history, and current condition). The recommendations covered: assessment of disease progression, potential critical scenarios requiring resuscitation, necessary resuscitation measures, estimated five-year survival rate and quality of life post-resuscitation, and a comprehensive evaluation of the value of resuscitation for that patient. Patients completed a resuscitation preference scale both before and after reading the recommendation document.

Intervention code:

组别:

Grok组

样本量:

30

Group:

Grok group

Sample size:

干预措施:

AI生成诊疗建议: 所有患者均接受一份基于其自身临床信息(包括人口学特征、疾病史、当前状况)生成的个性化复苏建议文档。建议内容涵盖疾病进展评估、可能出现的危急情况及复苏措施、复苏后预期生存率与生活质量、以及针对该患者的复苏价值综合评估。患者分别在阅读建议前和阅读建议后填写一份抢救意愿量表。

干预措施代码:

Intervention:

AI-generated treatment recommendations: All participants received a personalized resuscitation recommendation document generated based on their own clinical information (including demographic characteristics, medical history, and current condition). The recommendations covered: assessment of disease progression, potential critical scenarios requiring resuscitation, necessary resuscitation measures, estimated five-year survival rate and quality of life post-resuscitation, and a comprehensive evaluation of the value of resuscitation for that patient. Patients completed a resuscitation preference scale both before and after reading the recommendation document.

Intervention code:

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

广东 

市(区县):

 

Country:

China

Province:

Guangdong

City:

单位(医院):

汕头大学医学院附属肿瘤医院 

单位级别:

三甲 

Institution
hospital:

Cancer Hospital Of Shantou University Medical College

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

广东 

市(区县):

 

Country:

China

Province:

Guangdong

City:

单位(医院):

汕头大学医学院第一附属医院 

单位级别:

三甲 

Institution
hospital:

The First Affiliated Hospital of Shantou University Medical College

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

广东 

市(区县):

 

Country:

China

Province:

Guangdong

City:

单位(医院):

汕头大学医学院第二附属医院 

单位级别:

三甲 

Institution
hospital:

The Second Affiliated Hospital of Shantou University Medical College

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

诊断一致性

指标类型:

主要指标

Outcome:

Diagnostic consistency

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

模型间比较结果

指标类型:

次要指标

Outcome:

Comparison results among models

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:

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:

结束

/Completed

年龄范围:

Participant age:

最小 Min age 18 years
最大 Max age 80 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):

由独立研究人员使用计算机生成随机分配序列,采用区组随机化方法,以1:1:1的比例将受试者随机分配至ChatGPT组、DeepSeek组和Grok组。分配序列存储在密码保护的Word文档中,仅由指定研究人员保管,该人员不参与受试者招募、干预实施及结局评估。招募人员不知晓分配序列,且无法访问该文档。每位受试者完成基线评估后,由指定研究人员揭晓分组。

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

The randomization sequence was generated by an independent researcher using a computer-generated random allocation sequence with block randomization, assigning participants in a 1:1:1 ratio to the ChatGPT Group, DeepSeek Group, and Grok Group. The allocation sequence was stored in a password-protected Word document accessible only to a designated researcher who was not involved in participant enrollment, intervention delivery, or outcome assessment. Personnel responsible for enrollment were unaware of the allocation sequence and had no access to the document containing the sequence. Group assignment was revealed by the designated researcher only after each participant had completed the baseline assessment.

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:

双盲,对研究参与者和研究者设盲

Blinding:

Double-blind, with both the research participants and the researchers being blinded.d C.

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):

研究结束后半年内,通过ResMan(www.medresman.org.cn)方式共享

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

Within six months after the completion of the research, the results will be shared via the ResMan platform (www.medresman.org.cn)

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:

EDC

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

EDC

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:

 2026-05-25 11:08:05