基于Transformer的实时MAP预测模型指导下的血流动力学管理对老年腹部手术患者术中低血压时间加权平均值的影响:一项单中心、随机对照临床试验

注册号:

Registration number:

ChiCTR2500113333 

最近更新日期:

Date of Last Refreshed on:

2025-11-27 09:56:02 

注册时间:

Date of Registration:

2025-11-27 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

基于Transformer的实时MAP预测模型指导下的血流动力学管理对老年腹部手术患者术中低血压时间加权平均值的影响:一项单中心、随机对照临床试验

Public title:

Effect of Transformer-based Real-time MAP Prediction Model-guided Hemodynamic Management on the Time-weighted Average of Intraoperative Hypotension in Elderly Patients Undergoing Abdominal Surgery: A Single-center, Randomized Controlled Trial

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于Transformer的实时MAP预测模型指导下的血流动力学管理对老年腹部手术患者术中低血压时间加权平均值的影响:一项单中心、随机对照临床试验

Scientific title:

Effect of Transformer-based Real-time MAP Prediction Model-guided Hemodynamic Management on the Time-weighted Average of Intraoperative Hypotension in Elderly Patients Undergoing Abdominal Surgery: A Single-center, Randomized Controlled Trial

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:

朱守强 

研究负责人:

顾小萍 

Applicant:

Shouqiang Zhu 

Study leader:

Xiaoping Gu 

申请注册联系人电话:

Applicant telephone:

+86 188 0569 0880

研究负责人电话:

Study leader's
telephone:

+86 25 8310 6666

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:

sq_zhu_anesth@163.com

研究负责人电子邮件:

Study leader's E-mail:

xiaopinggu@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:

江苏省南京市鼓楼区中山路321号

研究负责人通讯地址:

江苏省南京市鼓楼区中山路321号

Applicant address:

No. 321, Zhongshan Road, Gulou District, Nanjing City, Jiangsu Province

Study leader's address:

No. 321, Zhongshan Road, Gulou District, Nanjing City, Jiangsu 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:

南京大学医学院附属南京鼓楼医院

Applicant's institution:

Nanjing Drum Tower Hospital, Affiliated Hospital of Medical School, Nanjing University

研究负责人所在单位:

南京大学医学院附属南京鼓楼医院

Affiliation of the Leader:

Nanjing Drum Tower Hospital, Affiliated Hospital of Medical School, Nanjing University

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:

2025-0807-02

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:

南京大学医学院附属鼓楼医院医学伦理委员会

Name of the ethic committee:

The Institutional Review Board of The Affiliated Drum Tower Hospital of Nanjing University Medical School

伦理委员会批准日期:

Date of approved by ethic committee:

2025-11-06 00:00:00

伦理委员会联系人:

仇毓东

Contact Name of the ethic committee:

Yudong Qiu

伦理委员会联系地址:

江苏省南京市鼓楼区中山路321号

Contact Address of the ethic committee:

No. 321, Zhongshan Road, Gulou District, Nanjing City, Jiangsu Province

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 188 0569 0883

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:

南京大学医学院附属南京鼓楼医院

Primary sponsor:

Nanjing Drum Tower Hospital, Affiliated Hospital of Medical School, Nanjing University

研究实施负责(组长)单位地址:

江苏省南京市鼓楼区中山路321号

Primary sponsor's address:

No. 321, Zhongshan Road, Gulou District, Nanjing City, Jiangsu 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):

江苏

市(区县):

南京市

Country:

China

Province:

Jiangsu

City:

Nanjing

单位(医院):

南京鼓楼医院

具体地址:

江苏省南京市鼓楼区中山路321号

Institution
hospital:

Nanjing Drum Tower hospital

Address:

No. 321, Zhongshan Road, Gulou District, Nanjing City, Jiangsu Province

经费或物资来源:

南京大学医学院附属南京鼓楼医院临床专项基金 (2021-LCYJ-DBZ-04, 2024-LCYJ-MS-18).

Source(s) of funding:

Clinical Trials from the Affiliated Drum Tower Hospital, Medical School of Nanjing University (2021-LCYJ-DBZ-04, 2024-LCYJ-MS-18).

研究疾病:

老年患者常见的腹部外科疾病,如结直肠癌、胃癌、胆石症等  

Target disease:

Patients undergoing major abdominal surgery

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:

1.主要目的:评估 MAP-PeriFormer 模型(鼓楼医院自主研发)指导的围手术期血流动力学管理方案在预防择期老年腹部手术患者术中低血压的发生率、持续时间及时间加权平均值等方面是否优于常规临床血流动力学实践管理。⒉次要目的:①评估 MAP-PeriFormer 模型指导的血流动力学管理方案在择期老年腹部手术中应用对于术后 AKI、MINS 和 POD 的发生率的影响;②评估 MAP-PeriFormer 模型指导的管理方案对于择期老年腹部手术患者术后相关并发症及住院时间等相关恢复指标的改善作用。  

Objectives of Study:

1. Primary Objective: To evaluate whether the MAP-PeriFormer model (independently developed by Drum Tower Hospital) guided perioperative hemodynamic management protocol is superior to conventional clinical hemodynamic practice in preventing the incidence, duration, and time-weighted average (TWA) of intraoperative hypotension in elderly patients undergoing elective abdominal surgery. 2. Secondary Objectives: To assess the impact of the MAP-PeriFormer model-guided hemodynamic management protocol on the incidence of postoperative acute kidney injury (AKI), myocardial injury after non-cardiac surgery (MINS), and postoperative delirium (POD) in elderly patients undergoing elective abdominal surgery. To evaluate the effect of the MAP-PeriFormer model-guided management protocol on the improvement of postoperative recovery indicators, including postoperative complications and hospital length of stay (LOS), in this patient population.

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. 拒绝参加本研究; 2. 长期酗酒史、药物依赖史; 3. 术前严重认知功能障碍,MMSE评分< 24分; 4. 慢性肾脏病患者,基线eGFR <30 mL/min/1.73m²或血肌酐>133μmol/L或已接受透析; 5. 近3个月内发生脑血管意外、心肌梗塞或不稳定性心绞痛; 6. 已知的严重肝硬化,或术前实验室检查提示Child-Pugh分级为B级或以上; 7. 神经系统疾病:痴呆或帕金森病、既往卒中伴认知障碍、长期使用抗精神病药物; 8. 近3个月内接受过手术;近30天内参加其他研究; 9. 术前即存在严重心动过缓(如病态窦房结综合征、高度房室传导阻滞未安装起搏器)或严重心律失常,预计术中需频繁干预心率者; 10. 术前严重血流动力学不稳定,例如,因脓毒症、活动性出血等导致术前即需要大剂量血管活性药物(如去甲肾上腺素 > 0.1 μg/kg/min)维持血压;

Exclusion criteria:

1. Refusal to participate in the study; 2. History of chronic alcoholism or substance/drug dependence; 3. Preoperative severe cognitive dysfunction, defined as a Mini-Mental State Examination (MMSE) score of < 24; 4. Chronic kidney disease, defined as a baseline estimated glomerular filtration rate (eGFR) of < 30 mL/min/1.73m^2, or baseline serum creatinine > 133 μmol/L, or ongoing renal replacement therapy (dialysis); 5. History of cerebrovascular accident, myocardial infarction, or unstable angina within the past 3 months; 6. Known severe liver cirrhosis, or preoperative laboratory tests indicating Child-Pugh class B or higher; 7. Pre-existing neurological disorders, including: dementia, Parkinson's disease, history of stroke with associated cognitive impairment, or long-term use of antipsychotic medications. 8. Having undergone any surgery within the past 3 months, or participation in any other interventional clinical trial within the past 30 days; 9. Pre-existing severe bradycardia (e.g., sick sinus syndrome, high-grade atrioventricular block without a pacemaker) or severe arrhythmia that is anticipated to require frequent intervention during surgery; 10. Preoperative severe hemodynamic instability, for instance, requiring high-dose vasopressor support (e.g., norepinephrine > 0.1 μg/kg/min) to maintain blood pressure due to conditions such as sepsis or active bleeding.

研究实施时间:

Study execute time:

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

征募观察对象时间:

Recruiting time:

From 2025-12-15 00:00:00 To 2026-12-01 00:00:00

干预措施:

Interventions:

组别:

MAP-PeriFormer 指导管理组

样本量:

41

Group:

MAP-PeriFormer Guided Management Group

Sample size:

干预措施:

MAP-PeriFormer模型指导血流动力学管理组:当模型提示预期时间(3/5/10min)内会发生低血压时,麻醉医生根据自身经验判断可能低血压的原因,给予扩容、血管活性药物或者其他措施。

干预措施代码:

Intervention:

In this group, the MAP-PeriFormer model will provide an alert to the anesthesiologist when it predicts a high probability of hypotension occurring within a specified future time window (e.g., 3, 5, or 10 minutes). Upon receiving the alert, the anesthesiologist will integrate this prediction with their clinical expertise to assess the potential cause of the impending hypotension (such as hypovolemia or decreased vascular tone) and initiate appropriate management. The interventions may include fluid bolus, administration of vasoactive agents, or other individualized measures.

Intervention code:

组别:

常规管理组

样本量:

41

Group:

Routine management group

Sample size:

干预措施:

本组患者按常规临床实践管理,对照组依然有MAP-PeriFormer,但麻醉医生不依赖其管理血流动力学,可自由选择其他血流动力学监测设备。

干预措施代码:

Intervention:

Patients in this group were managed according to standard clinical practice. Although the MAP-PeriFormer was still available in the control group, anesthesiologists did not rely on it for hemodynamic management and were free to choose other hemodynamic monitoring devices.

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):

南京 

Country:

China

Province:

Jiangsu

City:

Nanjing

单位(医院):

南京大学医学院附属南京鼓楼医院 

单位级别:

三甲 

Institution
hospital:

Nanjing University Medical School Affiliated Nanjing Drum Tower Hospital

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

平均动脉压小于65 mmHg时间曲线下面积 (时间加权平均值)

指标类型:

主要指标

Outcome:

The time-weighted average (TWA) of intraoperative hypotension, defined as the area under the curve (AUC) of mean arterial pressure (MAP) less than 65 mmHg over the duration of surgery.

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

术后谵妄

指标类型:

次要指标

Outcome:

Postoperative delirium

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

术后急性肾损伤

指标类型:

次要指标

Outcome:

Acute kidney injury

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

非心脏手术后心肌损伤

指标类型:

次要指标

Outcome:

Myocardial injury after non cardiac surgery, MINS

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

术后谵妄的发生率

指标类型:

次要指标

Outcome:

Incidence of postoperative delirium

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

不良事件

指标类型:

次要指标

Outcome:

Adverse event

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

术后 POD 的严重程度

指标类型:

次要指标

Outcome:

Severity of postoperative POD

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

术后48h内 PONV发生率

指标类型:

次要指标

Outcome:

Incidence of PONV within 48 hours after surgery

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

术后恶心呕吐严重程度

指标类型:

次要指标

Outcome:

Severity of postoperative nausea and vomiting

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:

血液

组织:

Sample Name:

Blood

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 65 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):

本研究将采用区组随机化方法。随机序列由一名不参与试验过程的独立统计学家,使用STATA 17.0软件生成。为确保组间样本量平衡并增强分配隐蔽性,将采用随机排列的区组,区组大小设定为4和6。生成的序列将隐藏于按顺序编号、密封、不透明的信封中,或更优地,存储在中央随机化系统中。

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

This trial will employ a blocked randomization method. The random sequence will be generated by an independent statistician using STATA software (version 17.0), with randomly permuted block sizes of 4 and 6 to maintain balance in group sizes and enhance allocation concealment. The allocation sequence will be concealed using sequentially numbered, opaque, sealed envelopes or, preferably, a centralized web-based randomization system.

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:

鉴于干预措施的性质,对实施干预的麻醉医生设盲不可行。然而,为最大限度地减少测量偏倚,本研究将采用结局评估者盲法。具体而言,负责收集所有术后结局数据(包括急性肾损伤、心肌损伤、术后谵妄、其他并发症及住院时间)的研究人员,以及进行最终数据分析的统计师,将对患者的分组信息完全不知情。此外,在研究过程中,将对患者进行适当的盲法处理,不向其透露具体的分组细节。所有主要和次要结局指标均尽可能采用客观定义和标准化评估工具,以进一步保证结果判读的公正性。

Blinding:

Due to the nature of the intervention, blinding of the anesthesiologists performing the management is not feasible. However, to minimize measurement bias, this trial will implement outcome assessor blinding. Specifically, the research personnel responsible for collecting all postoperative outcome data—including acute kidney injury, myocardial injury after non-cardiac surgery, postoperative delirium, other complications, and hospital length of stay—as well as the statistician performing the final data analysis, will be kept blind to the group assignments. Furthermore, patients will be blinded to their specific group allocation throughout the study period. All primary and secondary outcomes will be defined using objective criteria and standardized assessment tools wherever possible to further ensure impartial interpretation of the results.

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:

本研究将采用结构化的病例报告表(CRF)与基于互联网的电子数据采集(EDC)系统相结合的方式进行数据管理,以确保数据的质量、安全与完整性。所有数据将由经过专门培训的研究协调员,根据源文件直接录入至经认证的EDC系统。该系统内置自动逻辑核查与质控功能,能在数据录入时实时提示异常值与逻辑错误,从而从源头保障数据的准确性。数据管理员将定期核查数据并生成疑问表,由研究者核实并在线修订,所有数据修改痕迹将被系统自动记录和保存。最终,所有与研究相关的电子文件及数据库将按照机构规定,在研究结束后被安全地存档备查。

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

Data collection and management for this study will be conducted using a structured Case Report Form (CRF) in conjunction with a web-based Electronic Data Capture (EDC) system to ensure data quality, security, and integrity. All data will be entered directly from source documents into a certified EDC system by specially trained research coordinators. The system features built-in automatic logic checks and quality control functions, which provide real-time prompts for outliers and logical errors during data entry, thereby safeguarding data accuracy at the source. The data manager will periodically review the data and generate query forms for the investigators to verify and resolve online. All modifications to the data are automatically tracked and archived by the system. Upon study completion, all related electronic documents and the final database will be securely stored in accordance with institutional policies for future audit.

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:

 2025-11-27 09:55:22