应激性高血糖比率与危重患者急性谵妄发生率的关联及机器学习预测模型构建

注册号:

Registration number:

ChiCTR2500105509 

最近更新日期:

Date of Last Refreshed on:

2025-07-04 12:05:54 

注册时间:

Date of Registration:

2025-07-04 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

应激性高血糖比率与危重患者急性谵妄发生率的关联及机器学习预测模型构建

Public title:

The association between stress-induced hyperglycemia ratio and the incidence of acute delirium in critically ill patients with the construction of a machine learning prediction model

注册题目简写:

English Acronym:

The association between stress-induced hyperglycemia ratio and the incidence of acute delirium in critically ill patients with the construction of a machine learning prediction model

研究课题的正式科学名称:

应激性高血糖比率与危重患者急性谵妄发生率的关联及机器学习预测模型构建

Scientific title:

The association between stress-induced hyperglycemia ratio and the incidence of acute delirium in critically ill patients with the construction of a machine learning prediction 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:

徐玉增 

研究负责人:

徐玉增 

Applicant:

Yu-zeng Xu 

Study leader:

yuzengxu 

申请注册联系人电话:

Applicant telephone:

+86 153 0653 5782

研究负责人电话:

Study leader's
telephone:

+86 158 2418 0781

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:

1173584270@qq.com

研究负责人电子邮件:

Study leader's E-mail:

1173584270@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:

浙江省杭州市萧山区育才北路728号

研究负责人通讯地址:

育才北路728号

Applicant address:

No. 728 Yucai North Road, Xiaoshan District, Hangzhou City, Zhejiang Province, China

Study leader's address:

No. 728 Yu Cai Bei Lu, Xiaoshan district, Hangzhou City, Zhejiang Province

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:

浙江萧山医院

Applicant's institution:

Zhejiang Xiaoshan Hospital

研究负责人所在单位:

浙江萧山医院

Affiliation of the Leader:

Zhejiang Xiaoshan 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:

萧医伦审2025课第010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:

浙江萧山医院医学伦理委员会

Name of the ethic committee:

Medical Ethics Committee of Zhejiang Xiaoshan Hospital

伦理委员会批准日期:

Date of approved by ethic committee:

2025-05-28 00:00:00

伦理委员会联系人:

陈青莲

Contact Name of the ethic committee:

Qinglian Chen

伦理委员会联系地址:

育才北路728号

Contact Address of the ethic committee:

No. 728 Yu Cai Bei Lu, Xiaoshan district, Hangzhou City, Zhejiang Province

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 571 8220 1925

伦理委员会联系人邮箱:

Contact email of the ethic committee:

104712256@qq.com

研究实施负责(组长)单位:

浙江萧山医院

Primary sponsor:

Zhejiang Xiaoshan Hospital

研究实施负责(组长)单位地址:

育才北路728号

Primary sponsor's address:

No. 728 Yu Cai Bei Lu, Xiaoshan district, Hangzhou City, Zhejiang Province

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

中国

省(直辖市):

浙江省

市(区县):

Country:

China

Province:

Zhejiang

City:

单位(医院):

浙江萧山医院

具体地址:

育才北路728号

Institution
hospital:

Zhejiang Xiaoshan Hospital

Address:

No. 728 Yu Cai Bei Lu, Xiaoshan district, Hangzhou City, Zhejiang Province

经费或物资来源:

Source(s) of funding:

None

研究疾病:

谵妄  

Target disease:

Delirium

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:

队列研究 

Study design:

Cohort study 

研究目的:

本研究创新性地构建基于 XGBost 算法的集成预测模型,首次纳入 SHR 及镇静药物等参数,结合 SHAP 可解释性框架解析变量贡献度,旨在为急性谵妄的精准预防提供新型生物标志物及决策支持工具。  

Objectives of Study:

This study innovatively constructs an integrated prediction model based on the XGBost algorithm, incorporating for the first time parameters such as stress-induced hyperglycemia ratio (SHR) and sedative medications. By combining the SHAP interpretability framework to analyze variable contributions, it aims to provide novel biomarkers and decision-support tools for the precision prevention of acute delirium.

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.无 CAM-ICU 评分;
2.存在痴呆、酒精戒断 或药物引起的谵妄;
3.入 ICU 后 24 小时内无 血糖 和近三个月无 糖化血红蛋白数据;

Exclusion criteria:

1.CAM-ICU not performed;
2.pre-existing dementia, alcohol withdrawal delirium, or drug-induced delirium;
3.absence of blood glucose data within 24 hours post-ICU admission AND no HbA1c records within preceding 3 months;

研究实施时间:

Study execute time:

From 2025-06-30 00:00:00 To 2027-06-30 00:00:00  

征募观察对象时间:

Recruiting time:

From 2025-07-04 00:00:00 To 2027-06-30 00:00:00

干预措施:

Interventions:

组别:

观察组

样本量:

9812

Group:

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):

浙江省 

市(区县):

 

Country:

China

Province:

Zhejiang

City:

单位(医院):

浙江萧山医院 

单位级别:

三级乙等 

Institution
hospital:

Zhejiang Xiaoshan Hospital

Level of the institution:

Tertiary B

测量指标:

Outcomes:

指标中文名:

入住ICU后7天的急性谵妄发生率

指标类型:

主要指标

Outcome:

7-day incidence of acute delirium post-ICU admission

Type:

Primary indicator

测量时间点:

入ICU7天内

测量方法:

ICU-CAM

Measure time point of outcome:

within 7 days post-ICU admission

Measure method:

ICU-CAM

指标中文名:

应激性高血糖比值

指标类型:

主要指标

Outcome:

Stress hyperglycemia ratio (SHR)

Type:

Primary 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):

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:

不公开/Private

盲法:

Blinding:

None

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):

联系通讯作者

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

Correspondence should be addressed to 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:

我们使用Navicat mPremiu (17.0)中的结构化查询语言提取数据,以提取或计算以下变量。我们收集了入住ICU前24小时内的人口统计学特征(年龄、性别、种族、身高、体重)和生命体征(心率、收缩压、舒张压、体温),我们根据MIMIC-IV3.1数据库中ICD-9或ICD-10编码的诊断分段提取合并症(心肌梗塞、严重肝病、充血性心力衰竭、外周血管疾病、脑血管疾病、慢性肺病、糖尿病、肾病和恶性肿瘤)。我们获得了ICU简化急性生理学评分II (SAPSII)、牛津急性病严重程度评分(0ASIS)、逻辑器官功能障碍系统(LODs)和序贯器官衰竭评估(SOFA)中记录的第一天的具体评分。此外,我们还提取了入住重症监护室24小时后的检测结果(血糖、血清白蛋白、阴离子间隙、INR、钾、钠钙、血红蛋白、、白细胞、血小板、血糖、乳酸),近三个月内的糖化血红蛋白。如果在24小时内有多个数值和检测结果,则选择最初的临床数值。最后,记录接受的治疗(机械通气、镇静药物、血管加压、肾脏替代疗法(RRT))

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

Data extraction was performed using Structured Query Language in Navicat Premium (v17.0). We collected demographic characteristics (age, sex, race, height, weight) and vital signs (heart rate, systolic/diastolic blood pressure, temperature) within 24 hours before ICU admission. Comorbidities (myocardial infarction, severe liver disease, congestive heart failure, peripheral vascular disease, cerebrovascular disease, chronic pulmonary disease, diabetes, renal disease, malignancy) were extracted based on ICD-9/ICD-10 codes from MIMIC-IV v3.1. We obtained severity scores recorded on the first ICU day, including Simplified Acute Physiology Score II (SAPS II), Oxford Acute Severity of Illness Score (OASIS), Logistic Organ Dysfunction System (LODS), and Sequential Organ Failure Assessment (SOFA). Laboratory results (blood glucose, serum albumin, anion gap, INR, potassium, sodium, calcium, hemoglobin, white blood cells, platelets, lactate) post-24-hour ICU admission and glycated hemoglobin (HbA1c) within the preceding 3 months were extracted. For multiple measurements within 24 hours, the first clinically documented value was selected. Finally, administered treatments (mechanical ventilation, sedatives, vasopressors, renal replacement therapy [RRT]) were recorded

数据与安全监察委员会:

Data and Safety Monitoring Committee:

无/No

注册人:

Name of Registration:

 2025-07-04 12:05:48