ChiCTR2500102021 版本V1.0 版本创建时间2025/05/07 15:44:44 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:

ChiCTR2500102021 

最近更新日期:

Date of Last Refreshed on:

2025-05-07 15:44:28 

注册时间:

Date of Registration:

2025-05-07 00:00:00 

注册号状态:

补注册

Registration Status:

Retrospective registration

注册题目:

基于多模态数据脑卒中吞咽障碍患者鼻饲管拔除预测模型构建与应用研究

Public title:

Construction and application of a prediction model for nasogastric feeding tube removal in stroke dysphagia patients based on multimodal data

注册题目简写:

English Acronym:

研究课题的正式科学名称:

脑卒中吞咽障碍患者鼻饲管拔除最佳时机的决策模型研究

Scientific title:

Study on the decision model of the optimal time to remove nasogastric feeding tube in patients with dysphagia after stroke

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:

姜游力 

研究负责人:

迟玥 

Applicant:

Youli Jiang 

Study leader:

Yue Chi 

申请注册联系人电话:

Applicant telephone:

+86 185 4540 3739

研究负责人电话:

Study leader's telephone:

+86 150 1359 1987

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:

h2362120381@163.com

研究负责人电子邮件:

Study leader's E-mail:

1165313432@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:

深圳市龙华区景龙建设路38号

研究负责人通讯地址:

深圳市龙华区景龙建设路38号

Applicant address:

No. 38, Jinglong Jianshe Road, Longhua District, Shenzhen

Study leader's address:

No. 38, Jinglong Jianshe Road, Longhua District, Shenzhen

申请注册联系人邮政编码:

Applicant postcode:

518109

研究负责人邮政编码:

Study leader's postcode:

518109

申请人所在单位:

深圳市龙华区人民医院

Applicant's institution:

People's Hospital of Longhua, Shenzhen

研究负责人所在单位:

深圳市龙华区人民医院

Affiliation of the Leader:

People's Hospital of Longhua, Shenzhen

是否获伦理委员会批准:

是/Yes

Approved by ethic committee:

Yes

伦理委员会批件文号:

Approved No. of ethic committee:

龙华人医伦审(研)[2024]第(052)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:

深圳市龙华区人民医院伦理审查委员会

Name of the ethic committee:

Shenzhen Longhua District People's Hospital Ethics Review Committee

伦理委员会批准日期:

Date of approved by ethic committee:

2024-07-19 00:00:00

伦理委员会联系人:

秦良玉

Contact Name of the ethic committee:

Liangyu Qin

伦理委员会联系地址:

深圳市龙华街道建设东路38号

Contact Address of the ethic committee:

No. 38 Jianshe East Road, Shenzhen

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 135 2841 1092

伦理委员会联系人邮箱:

Contact email of the ethic committee:

h2362120381@163.com

研究实施负责(组长)单位:

深圳市龙华区人民医院

Primary sponsor:

People's Hospital of Longhua, Shenzhen

研究实施负责(组长)单位地址:

深圳市龙华区景龙建设路38号

Primary sponsor's address:

No. 38, Jinglong Jianshe Road, Longhua District, Shenzhen

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

中国

省(直辖市):

广东

市(区县):

深圳

Country:

China

Province:

Guangdong

City:

Shenzhen

单位(医院):

深圳市龙华区人民医院

具体地址:

深圳市龙华区景龙建设路38号

Institution
hospital:

People's Hospital of Longhua, Shenzhen

Address:

No. 38, Jinglong Jianshe Road, Longhua District, Shenzhen

经费或物资来源:

深圳市龙华区医疗卫生机构区级科研项目

Source(s) of funding:

the Scientific Research Projects of Medical and Health Institutions of Longhua District, Shenzhen

Target disease:

stroke

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:

开发先进的数据处理和特征提取方法来处理脑卒中患者的高维医疗数据。这包括利用深度学习算法自动识别和提取与吞咽功能障碍相关的关键特征,从而克服传统方法在处理复杂医疗数据时的局限性。创新开发能够动态更新和调整预测策略的机器学习模型。这种模型能够根据患者的实时数据和治疗反应自我优化,提供更为准确和个性化的拔管时机预测,从而显著提高临床决策的质量。  

Objectives of Study:

Develop advanced data processing and feature extraction methods to process high-dimensional medical data of stroke patients. This includes using deep learning algorithms to automatically identify and extract key features related to swallowing dysfunction, thereby overcoming the limitations of traditional methods in processing complex medical data. Innovatively develop machine learning models that can dynamically update and adjust prediction strategies. This model can self-optimize based on the patient's real-time data and treatment response, providing more accurate and personalized predictions of extubation timing, thereby significantly improving the quality of clinical decision-making.

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.通过CT或MRI确认的缺血性或出血性卒中诊断 2.年龄在18岁及以上 3.FOIS(Functional Oral Intake Scale)评分小于5分或GUSS(Gugging Swallowing Screen)评分小于20分的患者,这表明患者存在显著的吞咽功能障碍,且需要留置鼻饲管 4.患者或其法定监护人已签署知情同意书,同意参与本研究。

Inclusion criteria

1. Ischemic or hemorrhagic stroke diagnosis confirmed by CT or MRI 2. Aged 18 years and above 3. Patients with a FOIS (Functional Oral Intake Scale) score of less than 5 points or a GUSS (Gugging Swallowing Screen) score of less than 20 points, indicating that the patient has significant swallowing dysfunction and requires a nasogastric feeding tube 4. The patient or his/her legal guardian has signed an informed consent form and agreed to participate in this study.

排除标准:

1.从卒中发病到入院的时间超过48小时 2.卒中发病后4天内未能完成首次吞咽功能评估的患者,除非能结合临床情况进行评估 3.有语言、认知、忽视等障碍,或视听残疾严重到妨碍研究交流者 4.有重大精神系统病史,如抑郁、焦虑、躁狂等的患者 5.孕妇、哺乳期妇女 6.有消化系统癌症或消化道占位性病变 7.既往吞咽障碍者 8.不需要留置鼻饲管的患者

Exclusion criteria:

1. The time from stroke onset to hospitalization exceeds 48 hours 2. Patients who fail to complete the first swallowing function assessment within 4 days after stroke onset, unless the assessment can be combined with clinical conditions 3. Patients with language, cognitive, neglect and other disorders, or visual and auditory disabilities that are so severe that they hinder research communication 4. Patients with a history of major mental illness, such as depression, anxiety, mania, etc. 5. Pregnant women and breastfeeding women 6. Patients with digestive system cancer or digestive tract space-occupying lesions 7. Patients with previous swallowing disorders 8. Patients who do not need a nasogastric feeding tube

研究实施时间:

Study execute time:

From 2024-04-01 00:00:00 To 2027-07-31 00:00:00  

征募观察对象时间:

Recruiting time:

From 2024-05-01 00:00:00 To 2026-07-31 00:00:00  

干预措施:

Interventions:

组别:

吞咽障碍组

样本量:

180

Group:

Swallowing disorder 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):

广东 

市(区县):

深圳 

Country:

China 

Province:

Guangdong 

City:

Shenzhen 

单位(医院):

深圳市龙华区人民医院 

单位级别:

三甲 

Institution
hospital:

People's Hospital of Longhua, Shenzhen

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

GUSS和FOIS评分

指标类型:

主要指标

Outcome:

GUSS and FOIS ratings

Type:

Primary indicator

测量时间点:

根据GUSS和FOIS的评估结果来判断测量节点,GUSS评分 0-9 (7天/次 ),10-14(3天/次), 15-19 (<3天/次)

测量方法:

经培训的科研护士依照量表急性评估

Measure time point of outcome:

The measurement nodes are determined based on the evaluation results of GUSS and FOIS. The GUSS score is 0-9 (7 days/time), 10-14 (3 days/time), 15-19 (<3 days/time)

Measure method:

Acute assessment by trained research nurses according to the scale

指标中文名:

模型准确性

指标类型:

主要指标

Outcome:

Accuracy

Type:

Primary indicator

测量时间点:

模型评估阶段

测量方法:

基于Python代码计算模型精准性

Measure time point of outcome:

Model evaluation phase

Measure method:

Calculating Model Accuracy Based on Python Code

指标中文名:

模型F1 分数

指标类型:

次要指标

Outcome:

F1-score

Type:

Secondary indicator

测量时间点:

模型评估阶段

测量方法:

使用Python代码计算模型F1分数

Measure time point of outcome:

Model evaluation phase

Measure method:

Calculating model F1 scores using Python code

指标中文名:

混淆矩阵

指标类型:

主要指标

Outcome:

Confusion Matrix

Type:

Primary indicator

测量时间点:

模型评估阶段

测量方法:

使用Python代码绘制混淆矩阵

Measure time point of outcome:

Model evaluation phase

Measure method:

Plotting Confusion Matrices with Python Code

指标中文名:

AUC值

指标类型:

主要指标

Outcome:

Area Under the Curve (AUC)

Type:

Primary indicator

测量时间点:

模型评估阶段

测量方法:

ROC曲线下面积计算

Measure time point of outcome:

Model evaluation phase

Measure method:

Calculation of area under the Receiver Operating Characteristic (ROC) curve

采集人体标本:

Collecting sample(s)
from participants:

标本中文名:

组织:

Sample Name:

none

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:

正在进行

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:

公开/Public

盲法:

Blinding:

None

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

Yes

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):

本研究相关数据可在研究结束后,即2027年7月31日后,通过邮箱h2362120381@163.com以合理的研究事由获取。

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

The data related to this study can be accessed after the end of the study, i.e., after July 31, 2027, at h2362120381@163.com with reasonable cause for the study.

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:

病例记录表

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

Case Record Form, CRF

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:

 2025-05-07 15:44:28