ChiCTR2500113592 版本V1.0 版本创建时间2025/12/01 11:35:21 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:

ChiCTR2500113592 

最近更新日期:

Date of Last Refreshed on:

2025-12-01 11:35:14 

注册时间:

Date of Registration:

2025-12-01 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

儿童牙数异常AI智能诊断模型的研发及临床应用

Public title:

Development and Clinical Application of an AI Diagnostic Model for Detecting Dental Numerical Anomalies in Children

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于曲面体层片的儿童牙数异常AI智能诊断模型的研发及临床应用

Scientific title:

Development and Clinical Application of an AI Diagnostic Model for Detecting Dental Numerical Anomalies in Children Based on Panoramic Radiographs

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:

冯芝恩 

研究负责人:

冯芝恩 

Applicant:

Zhien Feng 

Study leader:

Zhien Feng 

申请注册联系人电话:

Applicant telephone:

+86 10 57099150

研究负责人电话:

Study leader's telephone:

+86 10 57099150

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:

jyfzhen@126.com

研究负责人电子邮件:

Study leader's E-mail:

jyfzhen@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:

中国北京市丰台区樊家村路9号

研究负责人通讯地址:

中国北京市丰台区樊家村路9号院

Applicant address:

No. 9, Fanjiacun Road, Fengtai District, Beijing

Study leader's address:

No. 9 Fanjiacun Road, Fengtai District, Beijing, 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:

首都医科大学附属北京口腔医院

Applicant's institution:

Beijing Stomatological Hospital, Capital Medical University

研究负责人所在单位:

首都医科大学附属北京口腔医院

Affiliation of the Leader:

Beijing Stomatological Hospital , Capital Medical University

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:

CMUSH-IRB-KJ-PJ-2025-57

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:

首都医科大学附属北京口腔医院伦理委员会

Name of the ethic committee:

Ethics Committee of Beijing Stomatological Hospital, Capital Medical University

伦理委员会批准日期:

Date of approved by ethic committee:

2025-09-15 00:00:00

伦理委员会联系人:

夏晓钰

Contact Name of the ethic committee:

Xia Xiaoyu

伦理委员会联系地址:

中国北京市丰台区樊家村路9号院

Contact Address of the ethic committee:

No. 9 Fanjiacun Road, Fengtai District, Beijing, China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 10 57099307

伦理委员会联系人邮箱:

Contact email of the ethic committee:

18602615270@163.com

研究实施负责(组长)单位:

首都医科大学附属北京口腔医院

Primary sponsor:

Beijing Stomatological Hospital , Capital Medical University

研究实施负责(组长)单位地址:

中国北京市丰台区樊家村路9号院

Primary sponsor's address:

No. 9 Fanjiacun Road, Fengtai District, 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):

Country:

China

Province:

Beijing

City:

单位(医院):

首都医科大学附属北京口腔医院

具体地址:

中国北京市丰台区樊家村路9号院

Institution
hospital:

Beijing Stomatological Hospital , Capital Medical University

Address:

No. 9 Fanjiacun Road, Fengtai District, Beijing, China

经费或物资来源:

丰台区卫生健康系统科研项目

Source(s) of funding:

Scientific research project of the Health and Wellness System in Fengtai District;Beijing Stomatological Hospital, Capital Medical University

Target disease:

Dental numerical anomalies

Target disease code:

研究类型:

诊断试验

Study type:

Diagnostic test

研究所处阶段:

其它 

Study phase:

N/A

研究设计:

诊断试验诊断准确性 

Study design:

Diagnostic test for accuracy 

研究目的:

(1)基于多中心、多设备、大样本的6-7岁儿童的曲面体层片数据的深度学习模型研发,实现曲面体层片智能诊断多生牙、缺失牙等牙齿数目异常性疾病。 (2)建立泛化程度最高、诊断最精确、基层可推广的具有自主知识产权的AI智能诊断系统。 (3)降低儿童牙齿数目异常疾病的误诊率,早诊断、早干预,有利于儿童牙颌系统和身心健康发育。  

Objectives of Study:

(1)The development of a deep learning model based on multi-center, multi-device, and large-sample panorama datas of 6-7-year-old children enables intelligent diagnosis of dental numerical anomalies such as supernumerated teeth and missing teeth from panorama radiographs. (2)Establish an AI intelligent diagnosis system with the highest degree of generalization, the most accurate diagnosis, and the ability to be promoted at the grassroots level, which has independent intellectual property rights (3)Reducing the misdiagnosis rate of dental numerical anomalies in children, early diagnosis and early intervention are conducive to the healthy development of children's dental and maxillofacial systems as well as their physical and mental health

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.曲面体层片拍摄时年龄为6-7岁,性别不限,拍摄时间为2015年及以后;
2.影像清晰,无变形或伪影等;

Inclusion criteria

1.The age at the time of shooting the panorama radiograph should be 6 to 7 years old, with no gender restrictions. The shooting time should be in 2015 or later;
2.The image is clear, without distortion or artifacts, etc;

排除标准:

1.拍摄时患有遗传病、颌骨发育异常等疾病;

Exclusion criteria:

1.At the time of shooting, there were genetic diseases, abnormal development of the jawbone and other diseases;

研究实施时间:

Study execute time:

From 2025-09-01 00:00:00 To 2028-09-30 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-01-01 00:00:00 To 2028-07-31 00:00:00  

诊断试验:

Diagnostic Tests:

金标准或参考标准(即可准确诊断某疾病的单项方法或多项联合方法,在本研究中用于诊断是否有该病的临床参考标准):

两名高级职称研究者的共同标记结果

Gold Standard or Reference Standard (The clinical reference standards required to establish the presence or absence of the target condition in the tested population in present study):

The joint labeling results of two senior title researchers

指标试验(即本研究的待评估诊断试验,无论为方法、生物标志物或设备,均请列出名称):

1.曲面体层片数据收集 2.牙齿标注 3.人工智能模型的研发

Index test:

1.Collection of Panoramic Radiograph Data 2.Tooth Annotation 3.Development of the Artificial Intelligence Model

目标人群(可以是某种疾病患者或正常人群,详细描述其疾病特征,注意应纳入符合分布特点的全序列病例,具有良好的代表性)

6-7岁的儿童。他们牙齿是混合牙列期,存在牙齿数目异常。

例数:

Sample size:

3000

Target condition (The target condition is a particular disease or disease stage that the index test will be intended to identify. Please specify the characteristics in detail; the population should has a complete spectrum and good representative):

Children aged 6 to 7. Their teeth are in the mixed dentition stage and there are dental numerical anomalies.

容易混淆的疾病人群(即与目标疾病不易区分的一种或多种不同疾病,应避免采用正常人群对照的病例-对照设计):

先天融合牙

例数:

Sample size:

0

Population with condition difficult to distinguish from the target condition, the normal population in a case-control study design should be avoid:

Congenital fused teeth

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):

 

Country:

China 

Province:

Beijing 

City:

 

单位(医院):

首都医科大学附属北京口腔医院 

单位级别:

三级甲等 

Institution
hospital:

Beijing Stomatological Hospital , Capital Medical University

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

北京 

市(区县):

 

Country:

China 

Province:

Beijing 

City:

 

单位(医院):

北京怀柔医院 

单位级别:

三级 

Institution
hospital:

Beijing Huairou Hospital

Level of the institution:

Tertiary

国家:

中国

省(直辖市):

北京 

市(区县):

 

Country:

China 

Province:

Beijing 

City:

 

单位(医院):

首都医科大学附属北京世纪坛医院 

单位级别:

三级甲等 

Institution
hospital:

Capital Medical University Affiliated Beijing Shijitan Hospital

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

灵敏度

指标类型:

主要指标

Outcome:

Sensitivity

Type:

Primary indicator

测量时间点:

试验数据完全获得后

测量方法:

“True/False”表示以医师的分类结果作为标准时模型的分类结果准确/不准确,“Positive/Negative”表示模型诊断图像中有/无牙齿数目异常(即有无多生牙和/或缺失牙),图像可分为四类:真正例(true positive, TP),真负例(true negative,TN),假负例(false negative, FN),假正例(false positive,FP)。灵敏度=TP/

Measure time point of outcome:

Test data were obtained

Measure method:

"True/False" indicates whether the classification result of the model is accurate or inaccurate when the classification result of the physician is used as the standard. "Positive/Negative" indicates whether there is an abnormal number of teeth (i.e., whether there are supernumerary teeth and/or missing teeth) in the diagnostic image of the model. Images can be divided into four categories: true positive example (TP), true negative example (TN), false negative example (FN), false positive example

指标中文名:

阴性预测值

指标类型:

次要指标

Outcome:

Negative predictive value

Type:

Secondary indicator

测量时间点:

试验数据完全获得后

测量方法:

“True/False”表示以医师的分类结果作为标准时模型的分类结果准确/不准确,“Positive/Negative”表示模型诊断图像中有/无牙齿数目异常(即有无多生牙和/或缺失牙),图像可分为四类:真正例(true positive, TP),真负例(true negative,TN),假负例(false negative, FN),假正例(false positive,FP)。阴性预测值=T

Measure time point of outcome:

Test data were obtained

Measure method:

"True/False" indicates whether the classification result of the model is accurate or inaccurate when the classification result of the physician is used as the standard. "Positive/Negative" indicates whether there is an abnormal number of teeth (i.e., whether there are supernumerary teeth and/or missing teeth) in the diagnostic image of the model. Images can be divided into four categories: true positive example (TP), true negative example (TN), false negative example (FN), false positive example

指标中文名:

特异度

指标类型:

主要指标

Outcome:

Specificity

Type:

Primary indicator

测量时间点:

试验数据完全获得后

测量方法:

“True/False”表示以医师的分类结果作为标准时模型的分类结果准确/不准确,“Positive/Negative”表示模型诊断图像中有/无牙齿数目异常(即有无多生牙和/或缺失牙),图像可分为四类:真正例(true positive, TP),真负例(true negative,TN),假负例(false negative, FN),假正例(false positive,FP)。特异度=TN/

Measure time point of outcome:

Test data were obtained

Measure method:

"True/False" indicates whether the classification result of the model is accurate or inaccurate when the classification result of the physician is used as the standard. "Positive/Negative" indicates whether there is an abnormal number of teeth (i.e., whether there are supernumerary teeth and/or missing teeth) in the diagnostic image of the model. Images can be divided into four categories: true positive example (TP), true negative example (TN), false negative example (FN), false positive example

指标中文名:

阳性预测值

指标类型:

次要指标

Outcome:

Positive predictive value

Type:

Secondary indicator

测量时间点:

试验数据完全获得后

测量方法:

“True/False”表示以医师的分类结果作为标准时模型的分类结果准确/不准确,“Positive/Negative”表示模型诊断图像中有/无牙齿数目异常(即有无多生牙和/或缺失牙),图像可分为四类:真正例(true positive, TP),真负例(true negative,TN),假负例(false negative, FN),假正例(false positive,FP)。阳性预测值=T

Measure time point of outcome:

Test data were obtained

Measure method:

"True/False" indicates whether the classification result of the model is accurate or inaccurate when the classification result of the physician is used as the standard. "Positive/Negative" indicates whether there is an abnormal number of teeth (i.e., whether there are supernumerary teeth and/or missing teeth) in the diagnostic image of the model. Images can be divided into four categories: true positive example (TP), true negative example (TN), false negative example (FN), false positive example

采集人体标本:

Collecting sample(s)
from participants:

标本中文名:

组织:

Sample Name:

N/A

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 6 years
最大 Max age 7 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

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:

(1)数据采集:由主要研究者从各中心影像学软件中收集并脱敏。 (2)数据管理:本试验设有试验记录本,在试验记录本上记录本研究中试验过程和试验结果以及招募过程中的相关问题。所有数据将由课题负责人及时、真实、准确、完整的记录在试验记录本内并由课题负责人负责管理。电子数据文件,如:数据库、检查程序、分析程序、分析结果、编码本和说明文件等,将分类保存,双备份保存于不同磁盘或记录介质上,妥善保存,防止损坏。被纳入受试者的电子版资料将被保存在课题组专用的移动硬盘中,使用时仅限于课题组研究人员使用专用电脑打开,禁止使用公用电脑打开受试者电子版资料。移动硬盘被妥善保存在上锁的柜子中,由课题负责人妥善保存。提供给北京石油化工学院虞欣教授团队用于图像处理与模式识别的受试者电子版资料将被保存在本课题专用的移动硬盘中,移动硬盘将被妥善保存在研究所上锁的柜子中。

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

(1)Data collection: The principal investigator collected and desensitized the data from the imaging software of each center. (2)Data Management: This trial is equipped with a trial record book, in which the trial process, results and related issues during the recruitment process in this study are recorded. All data will be recorded in the test record book in a timely, true, accurate and complete manner by the project leader and managed by the project leader. Electronic data files, such as databases, inspection programs, analysis programs, analysis results, codebooks and instruction documents, etc., will be classified and saved, with dual backups on different disks or recording media, properly preserved to prevent damage. The electronic data of the included subjects will be saved on the dedicated portable hard drive of the research group. When in use, it can only be opened by the dedicated computers of the researchers of the research group. It is strictly prohibited to open the electronic data of the subjects on public computers. The portable hard drive is properly stored in a locked cabinet and kept by the project leader. The electronic data of the subjects provided to Professor Yu Xin's team from Beijing Institute of Petrochemical Technology for image processing and pattern recognition will be saved in the dedicated portable hard drive for this project. The portable hard drive will be properly stored in the locked cabinet of the research institute.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

无/No

注册人:

Name of Registration:

 2025-12-01 11:35:14