ChiCTR2600126999 版本V1.0 版本创建时间2026/06/22 17:18:14 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:

ChiCTR2600126999 

最近更新日期:

Date of Last Refreshed on:

2026-06-22 17:18:07 

注册时间:

Date of Registration:

2026-06-22 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

基于真实世界多模态临床数据围手术期危重症患者血糖动态预测人工智能模型

Public title:

Real-World Multimodal Clinical Data-Based AI Model for Perioperative Critical Patients' Dynamic Blood Glucose Prediction

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于真实世界多模态临床数据围手术期危重症患者血糖动态预测人工智能模型

Scientific title:

Real-World Multimodal Clinical Data-Based AI Model for Perioperative Critical Patients' Dynamic Blood Glucose Prediction

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:

马伟 

研究负责人:

王新颖 

Applicant:

Ma Wei 

Study leader:

Wang Xinying 

申请注册联系人电话:

Applicant telephone:

+86 136 3996 1310

研究负责人电话:

Study leader's
telephone:

+86 136 3996 1310

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:

1104775184@qq.com

研究负责人电子邮件:

Study leader's E-mail:

622024350078@smail.nju.edu.cn

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:

中国江苏省南京市玄武区中山东路305号

研究负责人通讯地址:

中国江苏省南京市玄武区中山东路305号

Applicant address:

305 Zhongshan East Road, Xuanwu District, Nanjing, Jiangsu, China

Study leader's address:

305 Zhongshan East Road, Xuanwu District, Nanjing, Jiangsu, 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:

中国人民解放军东部战区总医院(南京大学医学院附属金陵医院)

Applicant's institution:

General Hospital of the Eastern Theater Command of the People's Liberation Army of China (Jinling Hospital Affiliated to Nanjing University Medical School)

研究负责人所在单位:

中国人民解放军东部战区总医院(南京大学医学院附属金陵医院)

Affiliation of the Leader:

General Hospital of the Eastern Theater Command of the People's Liberation Army of China (Jinling Hospital Affiliated to Nanjing University Medical School)

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:

2026DZKY-091-02

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:

中国人民解放军东部战区总医院临床研究伦理委员会

Name of the ethic committee:

Clinical Research Ethics Committee of the General Hospital of the Eastern Theater Command of the People's Liberation Army of China

伦理委员会批准日期:

Date of approved by ethic committee:

2026-05-19 00:00:00

伦理委员会联系人:

吴琼

Contact Name of the ethic committee:

Wu Qiong

伦理委员会联系地址:

中国江苏省南京市玄武区中山东路305号

Contact Address of the ethic committee:

305 Zhongshan East Road, Xuanwu District, Nanjing, Jiangsu, China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 25 8086 3234

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:

中国人民解放军东部战区总医院(南京大学医学院附属金陵医院)

Primary sponsor:

General Hospital of the Eastern Theater Command of the People's Liberation Army of China (Jinling Hospital Affiliated to Nanjing University Medical School)

研究实施负责(组长)单位地址:

中国江苏省南京市玄武区中山东路305号

Primary sponsor's address:

305 Zhongshan East Road, Xuanwu District, Nanjing, Jiangsu, 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):

江苏

市(区县):

Country:

China

Province:

Jiangsu

City:

单位(医院):

中国人民解放军东部战区总医院(南京大学医学院附属金陵医院)

具体地址:

中国江苏省南京市玄武区中山东路305号

Institution
hospital:

General Hospital of the Eastern Theater Command of the People's Liberation Army of China (Jinling Hospital Affiliated to Nanjing University Medical School)

Address:

305 Zhongshan East Road, Xuanwu District, Nanjing, Jiangsu, China

经费或物资来源:

费用来源于博士后基金,项目编号:96873。

Source(s) of funding:

The funds are sourced from the postdoctoral fund, Project number: 96873.

研究疾病:

围术期重症患者  

Target disease:

Perioperative critically ill patients

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:

本研究旨在将回顾性研究中构建的深度学习预测模型应用于真实的临床环境,以评估其在未知患者队列中的实际预测效能、临床安全性、与现有监测技术的优劣性及卫生经济学价值。  

Objectives of Study:

This study aims to apply the deep learning prediction model constructed in the retrospective study to the real clinical environment to evaluate its actual predictive efficacy, clinical safety, superiority and inferiority compared with existing monitoring techniques, and health economics value in an unknown patient cohort.

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. 年龄>=18岁; 2. 术后入ICU预计停留时间>24小时。

Inclusion criteria

1. Age >=18 years old; 2. The estimated length of stay in the ICU after the operation is more than 24 hours.

排除标准:

1. 孕妇或哺乳期患者; 2. 患有糖尿病急性并发症的患者,如酮症酸中毒或高渗高血糖状态; 3. 接受糖皮质激素治疗的患者; 4. 严重的血流动力学不稳定,需大剂量血管活性药物维持的患者; 5. 皮肤有严重损伤或感染,无法佩戴连续的动态血糖监测 (CGM) 传感器; 6. 拒绝签署知情同意书。

Exclusion criteria:

1. Pregnant or lactating patients; 2. Patients with acute complications of diabetes, such as ketoacidosis or hyperosmolar hyperglycemic state; 3. Patients receiving glucocorticoid treatment; 4. Patients with severe hemodynamic instability who require high-dose vasoactive drugs for maintenance; 5. There is severe skin damage or infection, making it impossible to wear a continuous ambulatory blood glucose monitoring (CGM) sensor; 6. Refuse to sign the informed consent form.

研究实施时间:

Study execute time:

From 2026-04-01 00:00:00 To 2026-10-01 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-07-01 00:00:00 To 2026-09-01 00:00:00

干预措施:

Interventions:

组别:

人工智能组

样本量:

52

Group:

Artificial Intelligence Group

Sample size:

干预措施:

人工智能组采用在前期回顾性研究中建立并经外部验证的围术期血糖预测模型。该模型基于患者的基线临床特征以及术后24小时内连续6个时间点的时间序列特征,对未来24小时内6个时间点的血糖水平进行预测。当模型预测未来4小时内血糖值超出目标血糖范围(7.8–10 mmol/L)时,定义为“近期高血糖风险”,并据此将指尖血糖监测频率由常规的每4小时一次增加至每1–2小时一次;当模型预测未来8–24小时内血糖值超出目标血糖范围时,定义为“远期高血糖风险”,作为预警信号提示临床医师关注后续血糖变化,但不直接触发治疗调整。当实测血糖值大于10 mmol/L时,均依据《中国住院患者血糖管理专家共识》的推荐,启动静脉胰岛素泵注治疗;当血糖值低于目标下限(7.8 mmol/L)时,给予高浓度葡萄糖注射液静脉输注。

干预措施代码:

Intervention:

The artificial intelligence group adopted a perioperative blood glucose prediction model established in a previous retrospective study and externally validated. This model predicts the blood glucose levels at six consecutive time points within the next 24 hours based on the baseline clinical characteristics of the patients and the time series characteristics of six consecutive time points within 24 hours after the operation. When the model predicts that the blood glucose level exceeds the target blood glucose range (7.8-10 mmol/L) within the next 4 hours, it is defined as "near-term hyperglycemia risk", and based on this, the frequency of fingertip blood glucose monitoring is increased from the conventional once every 4 hours to once every 1-2 hours. When the model predicts that the blood glucose level will exceed the target blood glucose range within the next 8 to 24 hours, it is defined as "long-term hyperglycemia risk", serving as a warning signal to prompt clinicians to pay attention to subsequent blood glucose changes, but does not directly trigger treatment adjustments. When the measured blood glucose value is greater than 10 mmol/L, intravenous insulin pump injection therapy is initiated in accordance with the recommendation of the "Expert Consensus on Blood Glucose Management of Inpatients in China". When the blood glucose level is lower than the lower limit of the target (7.8 mmol/L), intravenous infusion of high-concentration glucose injection is given.

Intervention code:

组别:

指尖血糖组

样本量:

52

Group:

Fingertip blood glucose group

Sample size:

干预措施:

指尖血糖组按照常规围术期血糖管理流程进行管理,术后每4小时进行一次指尖血糖监测;当实测血糖超出目标血糖范围(7.8–10 mmol/L)时,将指尖血糖监测频率增加至每1–2小时一次。当实测血糖值大于10 mmol/L时,均依据《中国住院患者血糖管理专家共识》的推荐,启动静脉胰岛素泵注治疗;当血糖值低于目标下限(7.8 mmol/L)时,给予高浓度葡萄糖注射液静脉输注。

干预措施代码:

Intervention:

The fingertip blood glucose group was managed according to the conventional perioperative blood glucose management process, and fingertip blood glucose monitoring was conducted every 4 hours after the operation. When the measured blood glucose exceeds the target blood glucose range (7.8-10 mmol/L), increase the frequency of fingertip blood glucose monitoring to once every 1-2 hours. When the measured blood glucose value is greater than 10 mmol/L, intravenous insulin pump injection therapy is initiated in accordance with the recommendation of the "Expert Consensus on Blood Glucose Management of Inpatients in China". When the blood glucose level is lower than the lower limit of the target (7.8 mmol/L), intravenous infusion of high-concentration glucose injection is given.

Intervention code:

组别:

连续血糖监测组

样本量:

52

Group:

Continuous blood glucose monitoring group

Sample size:

干预措施:

连续血糖监测组在术后将连续血糖监测仪安置于患者左上臂,持续监测血糖变化,连续血糖监测组数据实时向临床医师显示,并用于指导血糖管理。当血糖值大于10 mmol/L时,均依据《中国住院患者血糖管理专家共识》的推荐,启动静脉胰岛素泵注治疗;当血糖值低于目标下限(7.8 mmol/L)时,给予高浓度葡萄糖注射液静脉输注。

干预措施代码:

Intervention:

The continuous blood glucose monitoring group placed the continuous blood glucose monitor on the left upper arm of the patients after the operation to continuously monitor the changes in blood glucose. The data of the continuous blood glucose monitoring group was displayed to the clinicians in real time and used to guide blood glucose management. When the blood glucose level is greater than 10 mmol/L, intravenous insulin pump injection therapy is initiated in accordance with the recommendation of the "Expert Consensus on Blood Glucose Management of Inpatients in China". When the blood glucose level is lower than the lower limit of the target (7.8 mmol/L), intravenous infusion of high-concentration glucose injection is given.

Intervention code:

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

江苏 

市(区县):

 

Country:

China

Province:

Jiangsu

City:

单位(医院):

中国人民解放军东部战区总医院(南京大学医学院附属金陵医院) 

单位级别:

三甲 

Institution
hospital:

General Hospital of the Eastern Theater Command of the People's Liberation Army of China (Jinling Hospital Affiliated to Nanjing University Medical School)

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

应激性高血糖发生率

指标类型:

主要指标

Outcome:

Incidence of stress-induced hyperglycemia

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

血糖在目标范围内的时间比例(TIR)

指标类型:

次要指标

Outcome:

Time in Range (TIR)

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

血糖高于目标范围的时间比例(TAR)

指标类型:

次要指标

Outcome:

Time Above Range (TAR)

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

血糖低于目标范围的时间比例(TBR)

指标类型:

次要指标

Outcome:

Time Below Range (TBR)

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

每日血糖变异度

指标类型:

次要指标

Outcome:

Daily Glycemic Variability

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

平均每日血糖浓度

指标类型:

次要指标

Outcome:

Mean Daily Glucose Concentration

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

低血糖发生率

指标类型:

次要指标

Outcome:

Incidence of Hypoglycemia

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

使用后销毁  

说明

Fate of sample:

Destruction after use  

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 NA 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):

采用计算机生成随机数字表法进行简单随机分组。

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

A computer-generated random number table was used for simple random grouping.

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

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):

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:

EDC;CRF

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

EDC;CRF

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:

 2026-06-22 17:18:07