ChiCTR2600124960 版本V1.0 版本创建时间2026/05/19 17:07:50 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:

ChiCTR2600124960 

最近更新日期:

Date of Last Refreshed on:

2026-05-19 17:07:22 

注册时间:

Date of Registration:

2026-05-19 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ICD精准编码模型研究与应用

Public title:

Research and Application of a Large Language Model-Based Precise ICD Coding Model

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ICD精准编码模型研究与应用

Scientific title:

Research and Application of a Large Language Model-Based Precise ICD Coding Model

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:

苏奥南 

研究负责人:

苏奥南 

Applicant:

Aonan Su 

Study leader:

Aonan Su 

申请注册联系人电话:

Applicant telephone:

+86 18814885258

研究负责人电话:

Study leader's
telephone:

+86 571 87666666

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:

suaonan_512917@126.com

研究负责人电子邮件:

Study leader's E-mail:

suaonan_512917@126.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:

浙江省杭州市拱墅区上塘路158号

研究负责人通讯地址:

浙江省杭州市拱墅区上塘路158号

Applicant address:

No. 158, Shangtang Road, Gongshu District, Hangzhou, Zhejiang Province, China

Study leader's address:

No. 158, Shangtang Road, Gongshu District, Hangzhou, Zhejiang Province, 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:

浙江省人民医院

Applicant's institution:

Zhejiang Provincial People’s Hospital

研究负责人所在单位:

浙江省人民医院

Affiliation of the Leader:

Zhejiang Provincial People's 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:

浙人医伦审2026其他第(060)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:

浙江省人民医院医学伦理委员会

Name of the ethic committee:

Ethical Committee of Zhejiang Provincial Peoples Hospital

伦理委员会批准日期:

Date of approved by ethic committee:

2026-03-10 00:00:00

伦理委员会联系人:

李青青

Contact Name of the ethic committee:

Li QingQing

伦理委员会联系地址:

浙江省杭州市拱墅区上塘路158号

Contact Address of the ethic committee:

No. 158, Shangtang Road, Gongshu District, Hangzhou, Zhejiang Province, China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 571 85893643

伦理委员会联系人邮箱:

Contact email of the ethic committee:

zryllwyh@163.com

研究实施负责(组长)单位:

浙江省人民医院

Primary sponsor:

Zhejiang Provincial People's Hospital

研究实施负责(组长)单位地址:

浙江省杭州市拱墅区上塘路158号

Primary sponsor's address:

No. 158, Shangtang Road, Gongshu District, Hangzhou, Zhejiang Province, 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):

浙江省

市(区县):

Country:

China

Province:

Zhejiang

City:

单位(医院):

浙江省人民医院

具体地址:

浙江省杭州市拱墅区上塘路158号

Institution
hospital:

Zhejiang Provincial People's Hospital

Address:

No. 158, Shangtang Road, Gongshu District, Hangzhou, Zhejiang Province, China

经费或物资来源:

自选课题(自筹)

Source(s) of funding:

Self-funded

研究疾病:

无  

Target disease:

None

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:

连续入组 

Study design:

Sequential 

研究目的:

本研究旨在开发一套融合大语言模型(LLM)与检索增强生成(RAG)技术的ICD编码智能体引擎,通过构建“病历-代码-思维链”高质量数据集,利用RAG技术实时调取权威字典知识,模拟编码员与质控员的协作逻辑,有效解决长病历处理与罕见病精准预测难题。  

Objectives of Study:

This study aims to develop an intelligent ICD coding agent engine integrating large language models (LLMs) and retrieval-augmented generation (RAG) technology. By constructing a high-quality dataset of “medical records–codes–chain of thought,” and leveraging RAG to retrieve authoritative dictionary knowledge in real time, the system is designed to simulate the collaborative logic of coders and quality control reviewers, thereby effectively addressing the challenges of processing lengthy medical records and achieving precise prediction for rare diseases.

药物成份或治疗方案详述:

 

Description for medicine or protocol of treatment in detail:

 

纳入标准:

1.2015年-2025年住院患者病历文本与病案首页;

Inclusion criteria

1.Textual data from inpatient medical records and discharge abstracts for hospitalized patients from 2015 to 2025;

排除标准:

1.住院天数超过30天,同一疾病2天内再入院患者;

Exclusion criteria:

1.Patients whose length of stay exceeded 30 days, as well as patients readmitted within 2 days for the same condition.

研究实施时间:

Study execute time:

From 2026-01-01 00:00:00 To 2028-09-01 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-06-01 00:00:00 To 2026-12-31 00:00:00

干预措施:

Interventions:

组别:

观察组

样本量:

120000

Group:

Observation group

Sample size:

干预措施:

干预措施代码:

Intervention:

None

Intervention code:

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

浙江省 

市(区县):

 

Country:

China

Province:

Zhejiang

City:

单位(医院):

浙江省人民医院 

单位级别:

三级甲等 

Institution
hospital:

Zhejiang Provincial People's Hospital

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

编码耗时、编码准确率

指标类型:

主要指标

Outcome:

Coding time and coding accuracy

Type:

Primary indicator

测量时间点:

智能编码系统投入使用后

测量方法:

通过为期3-6个月的实际运行,收集编码耗时、编码准确率等数据。使用统计学方法(如t检验、卡方检验)分析AI介入后的显著性差异,量化评估系统的管理效益

Measure time point of outcome:

Following the implementation of the intelligent coding system

Measure method:

During 3–6 months of real-world operation, data on coding time, coding accuracy, and other relevant indicators will be collected. Statistical methods, such as the t-test and chi-square test, will be applied to assess the significance of differences after AI intervention, thereby quantitatively evaluating the system’s management effectiveness.

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):

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:

从院内电子病历系统获取2015年-2025年的出院患者的病历文本及病案首页信息

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

Medical record texts and discharge abstract data of patients discharged between 2015 and 2025 will be retrieved from the hospital’s electronic medical record system.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

有/Yes

注册人:

Name of Registration:

 2026-05-19 17:07:22