ChiCTR2500115252 版本V1.0 版本创建时间2025/12/24 10:04:58 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:

ChiCTR2500115252 

最近更新日期:

Date of Last Refreshed on:

2025-12-24 10:04:36 

注册时间:

Date of Registration:

2025-12-24 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

基于Transformer的术中获得性压力性损伤风险动态预测模型及预警系统的构建与验证研究

Public title:

Development and Validation of a Transformer-Based Dynamic Prediction Model and Early Warning System for Intraoperative Acquired Pressure Injury Risk

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于Transformer的术中获得性压力性损伤风险动态预测模型及预警系统的构建与验证研究

Scientific title:

Development and Validation of a Transformer-Based Dynamic Prediction Model and Early Warning System for Intraoperative Acquired Pressure Injury Risk

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:

杨鹏飞 

研究负责人:

杨鹏飞 

Applicant:

Pengfei Yang 

Study leader:

Pengfei Yang 

申请注册联系人电话:

Applicant telephone:

+86 21 6324 0090

研究负责人电话:

Study leader's
telephone:

+86 21 6324 0090

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:

bbdeyang@163.com

研究负责人电子邮件:

Study leader's E-mail:

bbdeyang@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:

上海市松江区新松江路650号

研究负责人通讯地址:

上海市虹口区武进路85号

Applicant address:

No. 650, Xinsongjiang Road, Songjiang District, Shanghai, China

Study leader's address:

85 Wujin Road, Hongkou District, 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:

上海市第一人民医院

Applicant's institution:

Shanghai General Hospital

研究负责人所在单位:

上海市第一人民医院

Affiliation of the Leader:

Shanghai General 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:

院伦快[2025]797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:

上海市第一人民医院人体试验伦理审查委员会

Name of the ethic committee:

Shanghai General Hospital Institutional Review Board

伦理委员会批准日期:

Date of approved by ethic committee:

2025-12-15 00:00:00

伦理委员会联系人:

耿雯倩

Contact Name of the ethic committee:

Geng Wenqian

伦理委员会联系地址:

上海市虹口区武进路85号

Contact Address of the ethic committee:

85 Wujin Road, Hongkou District, Shanghai

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 21 36126254

伦理委员会联系人邮箱:

Contact email of the ethic committee:

13262983906@163.com

研究实施负责(组长)单位:

上海市第一人民医院

Primary sponsor:

Shanghai General Hospital

研究实施负责(组长)单位地址:

上海市虹口区武进路85号

Primary sponsor's address:

85 Wujin Road, Hongkou District, 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

市(区县):

Country:

China

Province:

Shanghai

City:

单位(医院):

上海市第一人民医院

具体地址:

上海市虹口区武进路85号

Institution
hospital:

Shanghai General Hospital

Address:

85 Wujin Road, Hongkou District, Shanghai

经费或物资来源:

上海市第一人民医院特色研究项目资助

Source(s) of funding:

Clinical Research Innovation Plan of Shanghai General Hospital

研究疾病:

术中获得性压力性损伤  

Target disease:

Intraoperative acquired pressure injury

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:

连续入组 

Study design:

Sequential 

研究目的:

主要研究目的:开发基于Transformer的IAPI动态预测模型,融合术中生理参数(MAP、体温)与手术事件(体位、出血量); 次要研究目的:构建实时预警系统,提供可视化风险分层与闭环干预建议。  

Objectives of Study:

Primary Research Objective: To develop a Transformer-based dynamic prediction model for IAPI, integrating intraoperative physiological parameters (MAP, body temperature) and surgical events (patient positioning, blood loss volume). Secondary Research Objective: To construct a real-time early warning system that provides visual risk stratification and closed-loop intervention suggestions.

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. 接受全身麻醉或椎管内麻醉; 3. 手术时长≥2h; 4. 知情同意并自愿参与本研究者。

Inclusion criteria

1. Age >= 18 years old; 2. Accept general anesthesia or spinal anesthesia; 3. Surgical duration >= 2 hours; 4. Informed consent and voluntary participation in this study.

排除标准:

1.术前患者明确存在 PI 的; 2.术前有皮肤外伤、红斑或斑疹等影响观察者。 3.手术体位为坐位; 4.临终关怀患者; 5.参与其他冲突的临床研究。

Exclusion criteria:

1. The patient clearly has PI before surgery; 2. Preoperative skin trauma, erythema, or rash may affect the observer. 3. The surgical position is seated; 4. End of life care for patients; 5. Participate in other conflicting clinical studies.

研究实施时间:

Study execute time:

From 2025-07-01 00:00:00 To 2027-07-01 00:00:00  

征募观察对象时间:

Recruiting time:

From 2025-12-25 00:00:00 To 2026-12-25 00:00:00

干预措施:

Interventions:

组别:

手术组

样本量:

1000

Group:

Operation Group

Sample size:

干预措施:

干预措施代码:

Intervention:

NA

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 

市(区县):

 

Country:

China

Province:

Shanghai

City:

单位(医院):

上海市第一人民医院 

单位级别:

三级甲等 

Institution
hospital:

Shanghai General Hospital

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

术中获得性压力性损伤发生率

指标类型:

主要指标

Outcome:

Incidence of Intraoperative acquired pressure injury

Type:

Primary indicator

测量时间点:

术后72小时内

测量方法:

Measure time point of outcome:

Within 72 hours after surgery

Measure method:

指标中文名:

术中获得性压力性损伤严重程度

指标类型:

次要指标

Outcome:

Severity of Intraoperative acquired pressure injur

Type:

Secondary indicator

测量时间点:

术后72h内

测量方法:

Measure time point of outcome:

Within 72 hours after surgery

Measure method:

指标中文名:

模型决策曲线分析

指标类型:

次要指标

Outcome:

Clinical Decision Curve Analysis

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

模型校准度

指标类型:

次要指标

Outcome:

Model calibration

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

受试者工作特征曲线下面积

指标类型:

主要指标

Outcome:

the area under the receiver operating characteristic curve

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):

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:

1)数据采集:采用病例记录表,数据来源于以下系统: ①医院信息系统/电子病历系统:采集患者人口统计学信息、诊断、comorbidities(合并症)。 ②麻醉临床信息系统:采集术中分钟级的生命体征数据(血压、心率、SpO?、体温等)、药物使用、液体管理信息。 ③手术室护理管理系统:采集手术类型、手术时长、手术体位、体位垫使用情况、术中压力性损伤评估记录。 ④专用体位压力监测系统(如配备):采集术中体-支持界面之间的实时压力分布数据。 (2)数据管理工具与系统: ①数据提取与整合:使用SQL脚本从各源系统数据库视图接口提取数据。 ②数据清洗与处理:使用R语言进行。 ③数据存储:使用MySQL关系型数据库存储处理后的结构化数据。原始数据和中间数据均使用版本控制进行管理。 ④分析与建模:使用Python(PyTorch, Scikit-learn)。

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

Data Source Systems:(1) Hospital Information System/Electronic Medical Record System: Collects patient demographic information, diagnoses, and comorbidities. (2) Anesthesia Clinical Information System: Captures minute-by-minute intraoperative vital signs data (blood pressure, heart rate, SpO?, body temperature, etc.), medication administration, and fluid management details. (3) Operating Room Nursing Management System: Records surgery type, duration, patient positioning, positioning pad usage, and intraoperative pressure injury assessment documentation. (4) Specialized Posture Pressure Monitoring System (if equipped): Collects real-time pressure distribution data at the body-support interface during surgery.Data Management Tools and Systems:(1) Data Extraction and Integration: Python and SQL scripts are used to extract data from the database view interfaces of each source system.(2) Data Cleaning and Processing: Python (utilizing Pandas and NumPy) and R are employed for data cleaning and processing.(3) Data Storage: Processed structured data is stored in a MySQL relational database. Both raw data and intermediate data are managed using version control.(4) Analysis and Modeling: Python (with PyTorch and Scikit-learn) is used for data analysis and modeling.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

无/No

注册人:

Name of Registration:

 2025-12-24 10:04:36