ChiCTR2500100660 版本V1.0 版本创建时间2025/04/14 08:49:19 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:

ChiCTR2500100660 

最近更新日期:

Date of Last Refreshed on:

2025-04-14 08:48:57 

注册时间:

Date of Registration:

2025-04-14 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

基于大语言模型的临床文本解析与神经外科住院患者深静脉血栓风险评分推理

Public title:

Clinical text parsing based on large language model and inference of DTV risk score in neurosurgery inpatients

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于大语言模型的临床文本解析与神经外科住院患者深静脉血栓风险评分推理

Scientific title:

Clinical text parsing based on large language model and inference of DTV risk score in neurosurgery inpatients

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:

王志豪 

研究负责人:

刘艳辉 

Applicant:

Zhihao Wang 

Study leader:

Yanhui Liu 

申请注册联系人电话:

Applicant telephone:

+86 159 0280 6330

研究负责人电话:

Study leader's
telephone:

+86 189 8060 1509

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:

wangzhihaotnl@foxmail.com

研究负责人电子邮件:

Study leader's E-mail:

liuyh@scu.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:

四川省成都市武侯区国学巷37号

研究负责人通讯地址:

四川省成都市武侯区国学巷37号

Applicant address:

#37 Guoxue Alley, Wuhou District, Chengdu, Sichuan Province, P.R.China

Study leader's address:

#37 Guoxue Alley, Wuhou District, Chengdu, Sichuan Province, P.R.China

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:

四川大学华西医院神经外科

Applicant's institution:

Department of Neurosurgery, West China Hospital, Sichuan University

研究负责人所在单位:

四川大学华西医院神经外科

Affiliation of the Leader:

Department of Neurosurgery, West China Hospital, Sichuan 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年审(623)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:

四川大学华西医院生物医学伦理审查委员会

Name of the ethic committee:

Biomedical Ethics Review Committee, West China Hospital, Sichuan University

伦理委员会批准日期:

Date of approved by ethic committee:

2025-04-02 00:00:00

伦理委员会联系人:

陈诗琦

Contact Name of the ethic committee:

Shiqi Chen

伦理委员会联系地址:

四川省成都市武侯区国学巷37号

Contact Address of the ethic committee:

#37 Guoxue Alley, Wuhou District, Chengdu, Sichuan Province, P.R.China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 28 8542 2654

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:

四川大学华西医院

Primary sponsor:

West China Hospital, Sichuan University

研究实施负责(组长)单位地址:

四川省成都市武侯区国学巷37号

Primary sponsor's address:

#37 Guoxue Alley, Wuhou District, Chengdu, Sichuan Province, P.R.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):

四川省

市(区县):

成都市

Country:

China

Province:

Sichuan

City:

Chengdu

单位(医院):

四川大学华西医院

具体地址:

四川省成都市武侯区国学巷37号

Institution
hospital:

West China Hospital, Sichuan University

Address:

#37 Guoxue Alley, Wuhou District, Chengdu, Sichuan Province, P.R.China

经费或物资来源:

四川省科技厅

Source(s) of funding:

Science and Technology Department of Sichuan Province

研究疾病:

深静脉血栓  

Target disease:

Deep venous thrombosis

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:

回顾性研究 

Study phase:

Retrospective study

研究设计:

连续入组 

Study design:

Sequential 

研究目的:

现有 DVT 风险评估工具(如Caprini、Autar 量表)依赖人工提取结构化数据,对非结构化临床文本(如病历描述、影像报告)利用率低。大语言模型(1argclanguage model,LLM)可通过自然语言处理(NLP)自动解析非结构化文本,目前,将LLM 应用于医学领域的研究较少,本研究通过回顾性收集华西医院神经外科的患者资料,通过系统性收集其在住院期间的各种文书及检查报告,对比不同 LLM 在推理住院患者深静脉血栓风险的能力,并尝试构建动态推理深静脉血栓风险的框架。  

Objectives of Study:

Existing DVT risk assessment tools (such as Caprini and Autar scales) rely on manual extraction of structured data, and have low utilization of unstructured clinical texts (such as medical record descriptions and image reports). Large Language model (LLM) can automatically parse unstructured text through natural language processing (NLP). At present, there are few studies on the application of LLM in the medical field. This study retrospectively collected the data of patients from Department of Neurosurgery, West China Hospital. Through systematic collection of various documents and examination reports during hospitalization, the ability of different LLM in reasoning about the risk of deep vein thrombosis in hospitalized patients was compared, and a framework for dynamic reasoning about the risk of deep vein thrombosis was attempted.

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.患者年龄大于18岁; 2.神经外科住院并进行手术干预。

Inclusion criteria

1. The patient is over 18 years old; 2. Neurosurgery hospitalization and surgical intervention.

排除标准:

患者资料不全,无法进行深静脉血栓风险量表评估

Exclusion criteria:

The patient data were incomplete, and the DVT risk scale could not be evaluated

研究实施时间:

Study execute time:

From 2025-04-14 00:00:00 To 2026-03-31 00:00:00  

征募观察对象时间:

Recruiting time:

From 2025-04-14 00:00:00 To 2025-06-30 00:00:00

干预措施:

Interventions:

组别:

研究组

样本量:

3000

Group:

Investigation group

Sample size:

干预措施:

无干预

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):

四川省 

市(区县):

成都市 

Country:

China

Province:

Sichuan

City:

Chengdu

单位(医院):

四川大学华西医院 

单位级别:

三甲 

Institution
hospital:

West China Hospital, Sichuan University

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

准确率

指标类型:

主要指标

Outcome:

Accuracy

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

平均绝对误差

指标类型:

主要指标

Outcome:

mean absolute error MAE

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

F1分数

指标类型:

主要指标

Outcome:

F1 score

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:

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:

不公开/Private

盲法:

Blinding:

是否共享原始数据:

IPD sharing

是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):

原始数据获取请联系研究负责人

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

For original research data, please contact PI

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:

数据来源于四川大学华西医院,由研究团队在研究负责人监管下统一管理

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

The data were collected from West China Hospital, Sichuan University and managed by the research group under the supervision of PI

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:

 2025-04-14 08:48:57