ChiCTR2400094116 版本V1.0 版本创建时间2024/12/17 11:31:39 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:

ChiCTR2400094116 

最近更新日期:

Date of Last Refreshed on:

2024-12-17 11:31:04 

注册时间:

Date of Registration:

2024-12-17 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

医疗大语言模型MedGo在急诊疑似脓毒症识别和管理中的临床研究

Public title:

Clinical Study of the Medical Large Language Model MedGo in the Identification and Management of Suspected Sepsis in the Emergency Department

注册题目简写:

English Acronym:

研究课题的正式科学名称:

医疗大语言模型MedGo在急诊疑似脓毒症识别和管理中的临床研究

Scientific title:

Clinical Study of the Medical Large Language Model MedGo in the Identification and Management of Suspected Sepsis in the Emergency Department

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:

蒋森 

研究负责人:

唐伦先 

Applicant:

Sen Jiang 

Study leader:

Lunxian Tang 

申请注册联系人电话:

Applicant telephone:

+86 15800914116

研究负责人电话:

Study leader's telephone:

+86 21 38804518

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:

sdtzjiangsen@126.com

研究负责人电子邮件:

Study leader's E-mail:

456tlx@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:

上海市浦东新区陆家嘴街道即墨路150号

研究负责人通讯地址:

上海市浦东新区陆家嘴街道即墨路150号

Applicant address:

150 Jimo Road, Lujiazui Street,Pudong New Area, Shanghai

Study leader's address:

150 Jimo Road, Lujiazui Street,Pudong New Area, Shanghai

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:

上海市东方医院(同济大学附属东方医院)

Applicant's institution:

Shanghai East Hospital (East Hospital Affiliated To Tongji University)

研究负责人所在单位:

上海市东方医院

Affiliation of the Leader:

Shanghai East Hospital

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:

【2024】研审第(177)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:

上海市东方医院医学伦理委员会

Name of the ethic committee:

Medical Ethics Committee of Shanghai East Hospital

伦理委员会批准日期:

Date of approved by ethic committee:

2024-08-07 00:00:00

伦理委员会联系人:

鲍思蔚

Contact Name of the ethic committee:

Siwei Bao

伦理委员会联系地址:

上海市浦东新区陆家嘴街道即墨路150号

Contact Address of the ethic committee:

150 Jimo Road, Lujiazui Street,Pudong New Area, Shanghai

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 21 38804518

伦理委员会联系人邮箱:

Contact email of the ethic committee:

siwei_bao@163.com

研究实施负责(组长)单位:

上海市东方医院

Primary sponsor:

Shanghai East Hospital

研究实施负责(组长)单位地址:

上海市浦东新区陆家嘴街道即墨路150号

Primary sponsor's address:

150 Jimo Road, Lujiazui Street,Pudong New Area, Shanghai

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

中国

省(直辖市):

上海

市(区县):

Country:

China

Province:

Shanghai

City:

单位(医院):

上海市东方医院

具体地址:

上海市浦东新区陆家嘴街道即墨路150号

Institution
hospital:

Shanghai East Hospital

Address:

150 Jimo Road, Lujiazui Street,Pudong New Area, Shanghai

经费或物资来源:

上海市科技局

Source(s) of funding:

Shanghai Municipal Science and Technology Bureau

Target disease:

Sepsis

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:

回顾性研究 1)早期识别脓毒症:验证 MedGo 大语言模型在急诊科患者中早期识别脓毒症的有效性和可靠性。 2)比较诊断准确性:比较不同年资医生在有无 MedGo 辅助情况下对疑似脓毒症患者的诊断准确性和决策支持性能。 3)评估模型辅助效果:评估 MedGo 在不同严重程度和不同诊断难度病例中的辅助诊疗效果。 4)提高诊疗效率:探索如何利用人工智能工具提高急诊科医生的诊疗效率和准确性,减少误诊和漏诊的发生。 前瞻性研究 1)实时应用和验证:在急诊科中实时应用 MedGo,验证其在实际临床环境中的诊断性能。 2)动态优化模型:通过前瞻性数据收集,及时调整和优化 MedGo 模型,提高其诊断准确性和临床实用性。 3)临床决策支持:评估 MedGo 在实时临床决策中的辅助效果,提升急诊科医生的诊疗质量和效率。 4)长期预后跟踪:通过跟踪患者的治疗效果和预后情况,进一步验证 MedGo在脓毒症管理中的长期临床价值。  

Objectives of Study:

Retrospective study 1) Early identification of sepsis: To verify the effectiveness and reliability of the MedGo large language model for early identification of sepsis in emergency department patients. 2) Comparative diagnostic accuracy: To compare the diagnostic accuracy and decision support performance of doctors with and without MedGo in patients with suspected sepsis with and without the assistance of MedGo. 3) Evaluation of the auxiliary effect of the model: to evaluate the auxiliary diagnosis and treatment effect of MedGo in cases of different severity and different diagnostic difficulties. 4) Improve the efficiency of diagnosis and treatment: Explore how to use artificial intelligence tools to improve the efficiency and accuracy of diagnosis and treatment of emergency doctors, and reduce the occurrence of misdiagnosis and missed diagnosis. Prospective study 1) Real-time application and validation: Real-time application of MedGo in the emergency department to verify its diagnostic performance in a real-world clinical setting. 2) Dynamic optimization of the model: Through prospective data collection, the MedGo model can be adjusted and optimized in a timely manner to improve its diagnostic accuracy and clinical practicability. 3) Clinical decision support: Evaluate the auxiliary effect of MedGo in real-time clinical decision-making to improve the quality and efficiency of emergency physicians' diagnosis and treatment. 4) Long-term prognosis tracking: By tracking the treatment effect and prognosis of patients, the long-term clinical value of MedGo in the management of sepsis was further verified.

药物成份或治疗方案详述:

 

Description for medicine or protocol of treatment in detail:

 

纳入标准:

回顾性研究 入选标准: (1)年龄>=18 岁,性别不限; (2)入院前被诊断为疑似脓毒症,入院后确诊为脓毒症; 前瞻性研究入选标准: (1)年龄>=18 岁,性别不限; (2)符合 Sepsis-3 诊断标准的脓毒症患者; (3)获得知情同意并签订知情同意书。

Inclusion criteria

Retrospective Study Inclusion Criteria: (1) Age>=18 years old, gender is not limited; (2) Diagnosed with suspected sepsis before admission, and diagnosed with sepsis after admission; Prospective Study Inclusion Criteria: (1) Age>=18 years old, gender is not limited; (2) Sepsis patients who meet Sepsis-3 diagnostic criteria; (3) Obtain informed consent and sign an informed consent form.

排除标准:

1.活动期恶性肿瘤、HIV患者; 2.年龄小于18岁; 3.妊娠和哺乳期患者。

Exclusion criteria:

1.Patients with active malignancy or HIV; 2.Patients younger than 18 years old; 3.Pregnant or breastfeeding patients.

研究实施时间:

Study execute time:

From 2024-12-01 00:00:00 To 2025-12-15 00:00:00  

征募观察对象时间:

Recruiting time:

From 2024-12-20 00:00:00 To 2025-12-15 00:00:00  

干预措施:

Interventions:

组别:

干预组

样本量:

300

Group:

Intervention group

Sample size:

干预措施:

使用 MedGo 模型对急诊科脓毒症患者的诊断和管理进行实时辅助。

干预措施代码:

Intervention:

Real-time assistance in the diagnosis and management of patients with sepsis using the MedGo model.

Intervention code:

组别:

标准治疗组

样本量:

300

Group:

Standard treatment group

Sample size:

干预措施:

按照现行常规诊疗流程进行诊断与治疗,不使用 MedGo 进行辅助。

干预措施代码:

Intervention:

Diagnosis and treatment are carried out according to the current routine diagnosis and treatment procedures, and MedGo is not used as an aid.

Intervention code:

组别:

回顾性观察组

样本量:

200

Group:

Retrospective observation group

Sample size:

干预措施:

干预措施代码:

Intervention:

None

Intervention code:

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

上海 

市(区县):

 

Country:

China 

Province:

Shanghai 

City:

 

单位(医院):

上海市东方医院 

单位级别:

三级甲等 

Institution
hospital:

Shanghai East Hospital

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

28天死亡率

指标类型:

主要指标

Outcome:

28-day mortality

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

诊断准确率

指标类型:

次要指标

Outcome:

Diagnostic accuracy

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

误诊率

指标类型:

次要指标

Outcome:

Misdiagnosis rate

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

漏诊率

指标类型:

次要指标

Outcome:

Missed diagnosis rate

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:

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:

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):

由研究团队中负责数据管理的人员使用专业的计算机软件产生随机数列。

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

Random sequences are generated by the person responsible for data management in the research team using specialized computer software.

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:

单盲,研究参与者盲

Blinding:

Single-blind, study participants blinded

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):

1、学术期刊:在提交学术论文时,可以将原始数据作为补充材料提交至期刊,供同行查阅。研究者决定;公开时间于研究结果发表之后的6 个月内; 2、使用基于互联网的EDC系统如ResMan平台

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

1、Academic journal: When submitting academic papers, original data can be provided as supplementary material for peer review. Researchers will decide the disclosure timing, which should occur within six months after the publication of the research results; 2、Using internet-based EDC systems such as the ResMan platform.

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、病例记录表 (CRF) 设计: CRF 将根据研究方案中定义的指标和测量时间点进行设计,包含以下内容: 受试者基本信息 (例如,年龄、性别、既往病史等) 脓毒症诊断信息 (例如,诊断时间、诊断标准、SOFA 评分等) 治疗信息 (例如,抗生素使用情况、液体复苏情况等) 结局指标 (例如,28 天死亡率、诊断时间、医疗成本等) 其他相关信息 (例如,不良事件、并发症等) 填写: CRF 将由经过培训的研究人员填写,并确保数据的准确性和完整性。 保存: 纸质 CRF 将存放在安全的地方,并进行备份和存档。 二、电子采集和管理系统 选择: 将选择一个安全可靠的电子数据采集 (EDC) 系统,例如 REDCap、Medidata Rave 等。 搭建: 根据 CRF 的内容和研究方案的要求,在 EDC 系统中搭建电子数据库。 数据录入: 研究人员将使用 EDC 系统录入数据,并进行数据校验和逻辑检查,以确保数据的准确性和一致性。 数据管理: EDC 系统将提供数据管理功能,例如,数据备份、用户权限管理、审计追踪等,以确保数据的安全性和完整性。 数据导出: 在研究结束后,将从 EDC 系统中导出数据进行统计分析。

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

1. Case Report Forms (CRFs) Design: CRFs will be designed based on the outcomes and timepoints defined in the study protocol and will include the following information: Participant demographics (e.g., age, sex, medical history) Sepsis diagnosis information (e.g., time to diagnosis, diagnostic criteria, SOFA score) Treatment information (e.g., antibiotic use, fluid resuscitation) Outcome measures (e.g., 28-day mortality, time to diagnosis, healthcare costs) Other relevant information (e.g., adverse events, complications) Completion: CRFs will be completed by trained research personnel, ensuring data accuracy and completeness. Storage: Paper CRFs will be stored securely and backed up for archiving. 2. Electronic Data Capture and Management System Selection: A secure and reliable Electronic Data Capture (EDC) system will be selected, such as REDCap or Medidata Rave. Development: An electronic database will be developed within the EDC system based on the CRF content and study protocol requirements. Data Entry: Research personnel will enter data using the EDC system, employing data validation and logic checks to ensure accuracy and consistency. Data Management: The EDC system will provide data management functionalities such as data backup, user access control, and audit trails to ensure data security and integrity. Data Export: Upon study completion, data will be exported from the EDC system for statistical analysis.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

无/No

注册人:

Name of Registration:

 2024-12-17 11:31:04