基于北京协和医院围术期患者安全数据库构建外科手术患者术后30天再入院风险预测模型的回顾性研究

注册号:

Registration number:

ChiCTR2600125935 

最近更新日期:

Date of Last Refreshed on:

2026-06-01 17:28:28 

注册时间:

Date of Registration:

2026-06-01 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

基于北京协和医院围术期患者安全数据库构建外科手术患者术后30天再入院风险预测模型的回顾性研究

Public title:

Development and Validation of a 30-day Postoperative Readmission Risk Prediction Model for Surgical Patients Using the Peking Union Medical College Hospital Perioperative Patient Safety Database

注册题目简写:

外科手术患者再入院的预测

English Acronym:

Prediction for readmission among surgical patients

研究课题的正式科学名称:

基于北京协和医院围术期患者安全数据库构建外科手术患者术后30天再入院风险预测模型的回顾性研究

Scientific title:

Development and Validation of a 30-day Postoperative Readmission Risk Prediction Model for Surgical Patients Using the Peking Union Medical College Hospital Perioperative Patient Safety Database

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:

张越伦 

研究负责人:

张越伦 

Applicant:

Yuelun ZHANG 

Study leader:

Yuelun ZHANG 

申请注册联系人电话:

Applicant telephone:

+86 10 6915 4535

研究负责人电话:

Study leader's
telephone:

+86 10 6915 4535

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:

zhangyuelun@pumch.cn

研究负责人电子邮件:

Study leader's E-mail:

yuelunzhang@outlook.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:

北京市东城区帅府园1号北京协和医院

研究负责人通讯地址:

王府井帅府园1号(100730)

Applicant address:

No. 1 Shuaifuyuan, Dongcheng District, Beijing

Study leader's address:

No.1 Shuaifuyuan, Wangfujing, Dongcheng District, Beijing

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:

中国医学科学院北京协和医院

Applicant's institution:

Peking Union Medical College Hospital

研究负责人所在单位:

中国医学科学院北京协和医院

Affiliation of the Leader:

Peking Union Medical College 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:

I-26PJ1093

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:

中国医学科学院北京协和医院伦理审查委员会

Name of the ethic committee:

PUMCH Institutional Review Board

伦理委员会批准日期:

Date of approved by ethic committee:

2026-05-11 00:00:00

伦理委员会联系人:

李佳月

Contact Name of the ethic committee:

Jiayue Li

伦理委员会联系地址:

王府井帅府园1号(100730)

Contact Address of the ethic committee:

No.1 Shuaifuyuan, Wangfujing, Dongcheng District, Beijing

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 10 6915 6874

伦理委员会联系人邮箱:

Contact email of the ethic committee:

dott1994@163.com

研究实施负责(组长)单位:

中国医学科学院北京协和医院

Primary sponsor:

Peking Union Medical College Hospital

研究实施负责(组长)单位地址:

王府井帅府园1号(100730)

Primary sponsor's address:

No.1 Shuaifuyuan, Wangfujing, Dongcheng District, Beijing

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

中国

省(直辖市):

北京市

市(区县):

Country:

China

Province:

Beijing

City:

单位(医院):

中国医学科学院北京协和医院

具体地址:

王府井帅府园1号(100730)

Institution
hospital:

Peking Union Medical College Hospital

Address:

No.1 Shuaifuyuan, Wangfujing, Dongcheng District, Beijing

经费或物资来源:

北京协和医院中央高水平医院临床科研专项青年培优计划

Source(s) of funding:

National High Level Hospital Clinical Research Funding

研究疾病:

本研究涉及多种疾病,在外科手术患者(多种原始诊断)中进行再入院预测。  

Target disease:

Multiple diseases, predictions for readmission after surgery.

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:

本研究基于北京协和医院围术期患者安全数据库(POPS-PUMCH Database)所收集的临床数据,拟实现下述目的: 1. 构建基于病案静态特征的外科手术患者术后30天再入院风险预测模型(以下简称“静态特征模型”); 2. 构建融合病案静态特征与术中连续生命体征动态监测数据的多模态预测模型(以下简称“混合神经网络模型”),并量化术中动态监测数据相较于病案静态特征对预测性能的增量贡献; 3. 对上述两套模型进行内部验证,评估其区分度、校准度和可解释性,形成可纳入后续外部验证与系统集成工作的候选模型。  

Objectives of Study:

Using clinical data already collected within the POPS-PUMCH Database, this study aims to:(1) develop a prediction model for 30-day postoperative readmission in surgical patients based on static medical-record features (the "static-feature model");(2) develop a multi-modal model integrating static medical-record features and continuous intraoperative vital-sign monitoring data (the "hybrid neural network model"), and quantify the incremental predictive value of intraoperative dynamic monitoring over static features;(3) perform validation of both models, evaluating discrimination, calibration, and interpretability, and produce candidate models for subsequent external validation and system integration.

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.信息系统中缺失患者唯一标识、入院时间或出院时间信息,无法判断出院后30天内再入院情况;
2.信息系统中缺失手术关键信息(手术开始/结束时间、手术或麻醉类型);
3.同一患者在研究期内多次外科住院的情况,将以每次独立的外科住院为分析单位,不额外排除;

Exclusion criteria:

1.Missing patient identifier, admission date, or discharge date in the hospital information system, precluding ascertainment of 30-day readmission;
2.Missing key operative information (surgery start/end time, surgery type, or anaesthesia type);
3.When the same patient underwent multiple surgical admissions during the study period, each admission is treated as an independent analytic unit; such patients are not otherwise excluded;

研究实施时间:

Study execute time:

From 2025-09-01 00:00:00 To 2027-08-31 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-06-01 00:00:00 To 2027-08-31 00:00:00

干预措施:

Interventions:

组别:

观察组

样本量:

8933

Group:

Observation group

Sample size:

干预措施:

不涉及

干预措施代码:

Intervention:

Not applicable.

Intervention code:

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

北京市 

市(区县):

 

Country:

China

Province:

Beijing

City:

单位(医院):

中国医学科学院北京协和医院 

单位级别:

三级甲等 

Institution
hospital:

Peking Union Medical College Hospital

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

外科手术患者本次住院出院后30天内的全因再入院

指标类型:

主要指标

Outcome:

All-cause readmission within 30 calendar days after discharge from the index surgical admission

Type:

Primary indicator

测量时间点:

出院后30天内

测量方法:

基于病历系统记录进行判断。

Measure time point of outcome:

Within 30 calendar days after discharge from the index surgical admission

Measure method:

Judged by the records in the hospital information system.

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 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):

不涉及

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

Not applicable.

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:

数据治理:POPS-PUMCH数据库的数据治理流程已运行超过十年,具备成熟的质量控制机制,包括自动化数据导入时的强制逻辑核查、异常值定期监察与溯源核对、结构化数据定期质控抽样复核等。 去标识化:从POPS-PUMCH数据库向研究分析数据集的导出过程中,所有直接识别患者个体的字段(姓名、身份证号、联系方式、家庭住址、住院号等)在导出时即完成去标识化处理。研究分析人员所接触的数据集中仅保留研究编号,不含直接识别信息。去标识化对应关系映射表由数据治理团队单独保存于医院受控信息系统中,与研究分析数据物理隔离,仅在因研究进展确需进行数据核查时,经项目负责人书面申请并经数据治理责任人审核后方可有限度调用。 数据存储与访问控制:研究分析数据集仅存储在处于医院内部网络环境下的专用服务器中,不复制至移动存储设备,不上传至任何公有云服务。访问权限实行基于研究角色的分级授权,每位研究人员使用个人实名账号登录,所有对研究数据集的访问与操作均留有系统日志。 分析过程管理:数据清洗与建模脚本全程留痕,使用版本控制工具管理代码变更。所有统计分析在研究方案锁定后方开始执行。分析结果以最终分析报告与代码仓库形式归档保存。

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

Data governance: the POPS-PUMCH Database has operated under a mature data governance pipeline for more than a decade, with automated logical integrity checks at ingestion, periodic surveillance and source-verification of extreme values, and periodic structured-data quality sampling.De-identification: during extraction from the POPS-PUMCH Database to the research analytic dataset, all directly identifying fields (name, national ID, contact, address, inpatient number) are de-identified at source. Analysts see only a study ID. The re-identification key is kept solely within a hospital-controlled information environment under the custody of the data governance team, physically isolated from the analytic dataset. Access to the key for data verification is granted on a restricted case-by-case basis, subject to written application from the principal investigator and approval by the data governance lead.Data storage and access control: the analytic dataset resides exclusively on a dedicated server within the National Facility of Translational Medicine (PUMCH) — Prevention and Early-Intervention Platform, behind the hospital internal network. No copies are created on removable media and no upload to any public cloud service is permitted. Role-based access authorisation is in force, with personal accounts and full audit trails of all data access and operations.Analytic process management: all data-cleaning and modelling scripts are version-controlled and fully logged. All analyses are performed only after the protocol is locked. Analytic artefacts (final report, code repository) are archived.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

无/No

注册人:

Name of Registration:

 2026-06-01 17:28:16