基于大语言模型的卒中智能健康随访管理系统的研发及应用验证

注册号:

Registration number:

ChiCTR2500115830 

最近更新日期:

Date of Last Refreshed on:

2025-12-31 15:30:31 

注册时间:

Date of Registration:

2025-12-31 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

基于大语言模型的卒中智能健康随访管理系统的研发及应用验证

Public title:

Development and Application Verification of LLM Based Stroke Intelligent Health Rivisit Mangage System

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于大语言模型的卒中智能健康随访管理系统的研发及应用验证

Scientific title:

Development and Application Verification of LLM Based Stroke Intelligent Health Rivisit Mangage System

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:

赵洁 

研究负责人:

赵洁 

Applicant:

Zhao Jie  

Study leader:

Zhao Jie 

申请注册联系人电话:

Applicant telephone:

+86 186 0124 3661

研究负责人电话:

Study leader's
telephone:

+86 186 0124 3661

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:

Smilezoe51@163.com

研究负责人电子邮件:

Study leader's E-mail:

Smilezoe51@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:

中国北京市西城区长椿街 45 号

研究负责人通讯地址:

中国北京市西城区长椿街 45 号

Applicant address:

45 Changchun Street, Beijing China

Study leader's address:

45 Changchun Street, Beijing China

申请注册联系人邮政编码:

Applicant postcode:

100053

研究负责人邮政编码:

Study leader's postcode:

100053

申请人所在单位:

首都医科大学宣武医院

Applicant's institution:

Xuanwu Hospital Capital Medical University

研究负责人所在单位:

首都医科大学宣武医院

Affiliation of the Leader:

Xuanwu Hospital Capital Medical 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:

临研审[2025]026号-001

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:

首都医科大学宣武医院伦理委员会

Name of the ethic committee:

Ethics Committee of Xuanwu Hospital Capital Medical University

伦理委员会批准日期:

Date of approved by ethic committee:

2025-09-05 00:00:00

伦理委员会联系人:

易津

Contact Name of the ethic committee:

Yi Jin

伦理委员会联系地址:

中国北京市西城区长椿街 45 号

Contact Address of the ethic committee:

45 Changchun Street, Beijing China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 10 8319 9270

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:

首都医科大学宣武医院

Primary sponsor:

Xuanwu Hospital Capital Medical University

研究实施负责(组长)单位地址:

中国北京市西城区长椿街 45 号

Primary sponsor's address:

45 Changchun Street, Beijing 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):

北京

市(区县):

西城

Country:

China

Province:

Beijing

City:

Xicheng

单位(医院):

首都医科大学宣武医院

具体地址:

中国北京市西城区长椿街 45 号

Institution
hospital:

Xuanwu Hospital Capital Medical University

Address:

45 Changchun Street, Beijing China

经费或物资来源:

中国医学基金会临床医学科研促进计划,课题名称:基于大语言模型的卒中智能语音随访系统的研发及应用验证(课题编号2025CMFA04)

Source(s) of funding:

Clinical Medical Research Promotion Program of the China Medical Foundation Project Title: Development and Application Validation of an Intelligent Speech Follow-up System for Stroke Based on Large Language Models (Project Number: 2025CMFA04)

研究疾病:

脑卒中[中风]  

Target disease:

Stroke

研究疾病代码:

I64.X04

Target disease code:

I64.X04

研究类型:

干预性研究

Study type:

Interventional study

研究所处阶段:

探索性研究/预试验 

Study phase:

0

研究设计:

随机平行对照 

Study design:

Parallel 

研究目的:

评估卒中智能健康随访管理系统与人工随访在实际临床应用中,脑卒中患者 收缩压、90 天脑卒中复发等指标的差异。  

Objectives of Study:

Assess the difference of systolic blood pressure, chance of recurrence of stroke in 90 days and other indicators between the clinical application of stroke intelligent health rivisit mangage system and artificial follow-up.

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.已知妊娠期或哺乳期女性,或整群随机分组前妊娠试验阳性;2.正在接受可能污染结果的精神/心理治疗的患者;3.预期生存时间小于 1 年(如合并恶性肿瘤、严重心肺疾病等);4.已经参与可能会对结局评估产生影响的其他干预性临床研究;5.研究者认为不适合参与本研究或者可能会对患者造成显著风险的其他情形(如认知障碍无法理解和/或服从研究程序和/或随访)。满足上述排除标准中一条,即不纳入本研究。

Exclusion criteria:

1.Female individuals in gestation or breastfeeding period, or possitive result of pregnancy test before cluster randomization; 2.Patient accepting psychiatric or mental treatment that might pollut the result; 3.Life expectancy less than one year (e.g. complicated with malignant tumour, severe cardiac or pulmonary diseases); 4.Participant in other intervention studies that might interfere the result; 5.Investigators belief that patient is not suitable for this trial, or other situations that might have significant threat to the patient (e.g. cognitive impairment that could not understand and/or obey the programme and/or follow-up). The patient would be excluded if any one of these criteria have been attached.

研究实施时间:

Study execute time:

From 2026-01-26 00:00:00 To 2026-09-05 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-01-26 00:00:00 To 2026-09-05 00:00:00

干预措施:

Interventions:

组别:

干预组

样本量:

159

Group:

Intervention group

Sample size:

干预措施:

通过卒中智能健康随访管理系统对卒中患者进行卒中随访管理,包括血压监测、卒中症状评估、药物使用依从性监测和身体活动鼓励。

干预措施代码:

Intervention:

Rivisit management for stroke patients via stroke intelligent health rivisit mangage system, includes blood pressure monitor, stroke symptom assess, compliance monitor of drug usage and physical activity encouragement

Intervention code:

组别:

对照组

样本量:

159

Group:

Control group

Sample size:

干预措施:

基于人工的常规出院健康教育计划及电话随访

干预措施代码:

Intervention:

Ordinary health education after discharge and telephone revisit based on artificial way.

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(区县):

西城 

Country:

China

Province:

Beijing

City:

Xicheng

单位(医院):

首都医科大学宣武医院 

单位级别:

三甲 

Institution
hospital:

Xuanwu Hospital Capital Medical University

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

90 天收缩压达标率

指标类型:

主要指标

Outcome:

Qualified rate of 90 days' systolic blood pressure

Type:

Primary indicator

测量时间点:

卒中后90天

测量方法:

在安静休息 5 分钟后,受试者坐位,使用经过验证的电子血压监测仪(HEM-7052;欧姆龙)进行两次测量值并计算平均值。如果前两次收缩压读数之间的差异超过 10 毫米汞柱,则进行第三次测量,并使用最后两次读数进行计算。

Measure time point of outcome:

90 days after stroke

Measure method:

Participants take seat position after rest in quiet situation for 5 minutes. Using certified electronic blood pressure monitor (HEM-7052;Omron) to measure twice and calculate the average. If the difference between the systolic blood pressure beyond 10 mmHg, the third time measurment would be took and the last two value would be calculated.

指标中文名:

脑卒中90天复发

指标类型:

次要指标

Outcome:

Relapse of stroke in 90 days

Type:

Secondary indicator

测量时间点:

卒中后90天

测量方法:

Measure time point of outcome:

90 days after stroke

Measure method:

指标中文名:

药物使用依从性

指标类型:

次要指标

Outcome:

Compliance monitor of drug usage

Type:

Secondary indicator

测量时间点:

卒中后90天

测量方法:

采用4 项 Morisky Green Levine 量表,测量为 0 分的患者判定为依从性良好,分数越低表明依从性越高

Measure time point of outcome:

90 days after stroke

Measure method:

Using the 4 tasks Morisky Green Levine Scale, result of 0 indicates that the patient have ideal compliance, and the lower the score, the higher the compliance.

指标中文名:

病后患者功能状态

指标类型:

次要指标

Outcome:

Ability status post disease

Type:

Secondary indicator

测量时间点:

卒中后90天

测量方法:

改良Rankin量表(mRS)评分超过1分

Measure time point of outcome:

90 days after stroke

Measure method:

Using modified Rankin Scale and scored over 1

指标中文名:

生活质量

指标类型:

次要指标

Outcome:

Life quality

Type:

Secondary indicator

测量时间点:

卒中后90天

测量方法:

欧洲五维五水平健康量表(EQ-5D-5L)评分超过1分

Measure time point of outcome:

90 days after stroke

Measure method:

Ranked over 1, using European 5 Dimensions 5 Levels Health Scale

指标中文名:

二级预防危险因素了解程度

指标类型:

次要指标

Outcome:

Knowledgement degree of secondary prevention against risk factor

Type:

Secondary indicator

测量时间点:

卒中后90天

测量方法:

相关的知识、态度、行为指标评分低于60分

Measure time point of outcome:

90 days after stroke

Measure method:

Relative knowledge, attitude and behavior score under 60 degree.

指标中文名:

卒中危险因素其他相关指标

指标类型:

次要指标

Outcome:

Other relative index of stroke risk factor

Type:

Secondary indicator

测量时间点:

卒中后90天

测量方法:

空腹血糖、总胆固醇、低密度脂蛋白胆固醇水平等

Measure time point of outcome:

90 days after stroke

Measure method:

Fasting Blood Glucose, Total Cholesterol, LDL and other.

指标中文名:

不良心脑血管事件

指标类型:

附加指标

Outcome:

Adverse cardiovascular and cerebrovascular events

Type:

Additional indicator

测量时间点:

卒中后90天

测量方法:

包括心肌梗死、短暂性脑缺血发作等

Measure time point of outcome:

90 days after stroke

Measure method:

Including myocardial infarction, transient ischemic attack, etc.

采集人体标本:

Collecting sample(s)
from participants:

标本中文名:

组织:

Sample Name:

None

Tissue:

None

人体标本去向

其它  

说明

Fate of sample:

0thers  

Note:

None

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 N/A 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):

本研究采用传统随机信封法,使用 SAS 9.4 (SAS Institute, Cary, NC) 软件生成随机数字表,随机数字及分组方案装在按顺序编号的密封的不透明信封中,并对负责招募和参加本研究的研究人员隐藏分配顺序。研究对象签署知情同意书后分配筛选编号,经过研究人员筛选后,符合研究纳入排除标准的患者,按顺序分配随机信封,并按随机信封内随机分组信息将研究对象随机分至两组。

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

Traditional random evenlope method is used in this study. Using software SAS9.4 (SAS Institute, Cary, NC) to generate random number table. Random numbers and seperate plans are sealed in opaque envelopes, and are concealed to researchers either take charge in hirement or take part in the study. The participants will be sent a fliter number after they signed the informed consent forms. After researchers' fliter, pariticipants will be sent a random envelope and seperated to two groups by the information carried in it if they fulfill all the inclusion criterias and avoid all of exclusion criterias.

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:

对进行终点评价的研究人员进行隐蔽患者分组情况。

Blinding:

Conceal the patient groupings from researchers conducting endpoint evaluations.

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:

录入采用相应的数据库系统双人双机录入,之后对数据库进行两遍比对,期间若发现问题及时通知监查员,要求研究者做出回答。他们之间的各种疑问及解答的交换应当采用疑问表形式,疑问表应保存备查。当所有病例报告表经双份输入并核对无误后,由数据管理员写出数据库检查报告,其内容包括研究完成情况(含脱落受试者清单)、入选/排除标准检查、完整性检查、逻辑一致性检査、离群数据检查、时间窗检查、不良事件检查等。

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

Data entry shall be conducted through a validated database system using double data entry by two independent operators. The database will then undergo duplicate verification (double-checking). Should any discrepancies be identified, the clinical monitor must be notified promptly, and the investigator is required to provide clarifications. All questions and responses must be documented using formal data query forms, which shall be retained for audit and inspection purposes. Upon completion of double data entry and full reconciliation of all case report forms (CRFs), the data manager will generate a comprehensive database validation report. This report will include, but is not limited to: study completion status (including a listing of subjects who discontinued), review of inclusion/exclusion criteria compliance, data completeness checks, logical consistency checks, outlier analyses, time-window compliance checks, and adverse event data verification.

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:

 2025-12-31 15:30:28