基于人工智能和CT影像对新型冠状病毒性肺炎(COVID-19)的临床分型诊断及重症化预警系统研发

注册号:

Registration number:

ChiCTR2000030838 

最近更新日期:

Date of Last Refreshed on:

2020-03-15 23:42:50 

注册时间:

Date of Registration:

2020-03-15 00:00:00 

注册号状态:

补注册

Registration Status:

Retrospective registration

注册题目:

基于人工智能和CT影像对新型冠状病毒性肺炎(COVID-19)的临床分型诊断及重症化预警系统研发

Public title:

Development of warning system with clinical differential diagnosis and prediction for severe type of novel coronavirus pneumonia (COVID-19) patients based on artificial intelligence and CT images

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于人工智能和CT影像对新型冠状病毒性肺炎的临床分型诊断及重症化预警系统研发

Scientific title:

Development of warning system with clinical differential diagnosis and prediction for severe type of SARS-Cov-2 patients based on artificial intelligence and CT images

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:

孙文博 

研究负责人:

徐海波 

Applicant:

Sun Wenbo 

Study leader:

Xu Haibo 

申请注册联系人电话:

Applicant telephone:

+86 18164259833

研究负责人电话:

Study leader's
telephone:

+86 13545009416

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:

284972480@qq.com

研究负责人电子邮件:

Study leader's E-mail:

xuhaibo1120@hotmail.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:

武汉市武昌区东湖路169号武汉大学中南医院

研究负责人通讯地址:

武汉市武昌区东湖路169号

Applicant address:

169 Donghu Road, Wuchang District, Wuhan, Hubei, China

Study leader's address:

169 Donghu Road, Wuchang District, Wuhan, Hubei, 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:

武汉大学中南医院

Applicant's institution:

Zhongnan Hospital of Wuhan University

研究负责人所在单位:

武汉大学中南医院

Affiliation of the Leader:

Wuhan University Central South 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:

20200037

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:

武汉大学中南医院临床试验伦理委员会

Name of the ethic committee:

Clinical Trial Ethics Committee of Zhongnan Hospital of Wuhan University

伦理委员会批准日期:

Date of approved by ethic committee:

2020-02-20 00:00:00

伦理委员会联系人:

郑磊

Contact Name of the ethic committee:

Zheng Lei

伦理委员会联系地址:

武汉市武昌区东湖路169号武汉大学中南医院

Contact Address of the ethic committee:

Wuhan University Central South Hospital, 169 Donghu Road, Wuchang District, Wuhan, Hubei, China

伦理委员会联系人电话:

Contact phone of the ethic committee:

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:

武汉大学中南医院

Primary sponsor:

Zhongnan Hospital of Wuhan University

研究实施负责(组长)单位地址:

武汉市武昌区东湖路169号

Primary sponsor's address:

169 Donghu Road, Wuchang District, Wuhan, Hubei, 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):

湖北省

市(区县):

武汉市

Country:

China

Province:

Hubei

City:

Wuhan

单位(医院):

武汉大学中南医院

具体地址:

武汉市武昌区东湖路169号武汉大学中南医院

Institution
hospital:

Zhongnan Hospital of Wuhan University

Address:

69 Donghu Road, Wuchang District, Wuhan

经费或物资来源:

湖北省科学技术发展厅

Source(s) of funding:

Hubei Provincial Department of Science and Technology Development

研究疾病:

新型冠状病毒肺炎(COVID-19)  

Target disease:

Novel Coronavirus Pneumonia (COVID-19)

研究疾病代码:

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:

连续入组 

Study design:

Sequential 

研究目的:

针对新型冠状病毒肺炎的迅速播散,拟依托前期基础,通过医工结合人工智能研究对该病诊断效率受限、地区诊断水平差异、难以预判疾病重症化这三大瓶颈开展紧急课题攻关。1)提升诊断效率:通过对已确诊患者胸部CT数据应用深度学习技术挖掘影像学特征,对大量初筛患者CT数据在短时间内完成疑似病例筛查,辅助高强度工作下的影像诊断。2)消除地区诊断水平差异:以第五版诊疗方案中病例特点、检验学及第一阶段影像学智能诊断基础,构建计算机智能辅助诊断评分模型。3)对各临床分型肺炎医疗数据综合学习,构建基于CT影像组学对新型冠状病毒性肺炎的临床分型诊断及重症化预警系统,提前预判便于针对性强化治疗,提升危重患者生存率。  

Objectives of Study:

Aiming at the rapid dissemination of new coronavirus pneumonia, it is planned to carry out urgent research on the three major bottlenecks, which are based on the early basis, through medical research and artificial intelligence research to limit the diagnosis efficiency of the disease, the differences in regional diagnostic levels, and the difficulty to predict the severity of the disease. 1) Improving diagnosis efficiency: By applying deep learning technology to the chest CT data of diagnosed patients to mine imaging features, a large number of newly screened patients' CT data can complete the screening of suspected cases in a short time, and assist image diagnosis under high-intensity work. 2) Eliminate the differences in regional diagnostic levels: build a computer-assisted diagnostic diagnosis scoring model based on case characteristics, laboratory science, and the first stage of imaging intelligent diagnosis in the fifth edition of the diagnosis and treatment plan. 3) Comprehensive study of medical data of each clinical type of pneumonia, build a CT typing omics-based clinical typing diagnosis and intensive warning system of new coronavirus pneumonia, predict in advance to facilitate targeted intensive treatment, and improve the survival rate of critically ill patients .

药物成份或治疗方案详述:

2020.02.06-2020.03.05: 结合肺部CT和吹气肺功能参数、血氧饱和度和动脉血氧分压PaO2/吸氧浓度FiO2,建立CT扫描参数和呼吸运动校正方法,开发人工智能自动化分割的肺功能CT定量成像技术,提取与上述参数相似的定量肺功能CT评估参数; 2020.03.06-2020.04.05: 影像建模包含基于深度学习神经网络对肺内病变区域建立精准分割模型,以及通过对不同时期(如临床分型:普通、重症、危重症)患者肺部CT基于影像组学的病变特征分析,获取研究感染病变的特征变化及动态演变机理; 2020.04.06-2020.05.06: 结合重要临床特征和实验室指标(以肺功能测定为例),建立基于深度学习的各临床分型肺炎诊断及重症化预警模型。 

Description for medicine or protocol of treatment in detail:

2020.02.06-2020.03.05: Combining lung CT and inspiratory lung function parameters, blood oxygen saturation, and arterial blood oxygen partial pressure PaO2 / oxygen concentration FiO2, establishing CT scanning parameters and respiratory motion correction methods, and developing artificial intelligence automation Segmented lung function CT quantitative imaging technology to extract quantitative lung function CT evaluation parameters similar to the above parameters; 2020.03.06-2020.04.05: Image modeling includes the establishment of a precise segmentation model of lung lesions based on deep learning neural networks, and CT based on lung CT of patients at different periods (such as clinical classification: common, severe, and critically ill) Analysis of pathological features of imaging omics, to acquire and study the characteristic changes and dynamic evolution mechanism of infected pathological changes; 2020.04.06-2020.05.06: Combining important clinical features and laboratory indicators (taking lung function measurement as an example), establishing a deep learning model for the diagnosis and intensification of pneumonia in various clinical types based on deep learning. 

纳入标准:

Inclusion criteria

排除标准:

(1)CT阴性。
(2)临床资料不完整者。

Exclusion criteria:

(1) CT result is negative;
(2) Incomplete clinical data.

研究实施时间:

Study execute time:

From 2020-02-06 00:00:00 To 2020-05-06 00:00:00  

征募观察对象时间:

Recruiting time:

From 2020-01-20 00:00:00 To 2020-02-29 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):

核酸检测结果

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):

RT-PCR test results

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):

人工智能模型分型及预测得准确度

Index test:

Typing and prediction accuracy of artificial intelligence models

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)

新冠肺炎确诊及疑似患者

例数:

Sample size:

1000

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):

subjects diagnosed or suspected COVID-19 pneumonia

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):

其它肺炎患者

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:

Other patients with pneumonia

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

湖北省 

市(区县):

武汉市 

Country:

China

Province:

Hubei

City:

Wuhan

单位(医院):

武汉大学中南医院 

单位级别:

三甲医院 

Institution
hospital:

Zhongnan Hospital of Wuhan University

Level of the institution:

Tertiary A Hospital

测量指标:

Outcomes:

指标中文名:

精准度

指标类型:

主要指标

Outcome:

Precision

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

SEN, SPE, ACC, AUC of ROC

指标类型:

主要指标

Outcome:

SEN, SPE, ACC, AUC of ROC

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:

none

Tissue:

人体标本去向

使用后销毁  

说明

Fate of sample:

Destruction after use  

Note:

征募研究对象情况:

Recruiting status:

结束

/Completed

年龄范围:

Participant age:

最小 Min age 18 years
最大 Max age 80 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):

临床医生从His系统筛选

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

N/A

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:

未说明

Blinding:

Not stated

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):

2020.11.06 http://www.znhospital.cn/

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

2020.11.06 http://www.znhospital.cn/

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:

采集:从PACS.HIS和LIS系统采集。 管理:依托武汉大学中南医院临床试验数据库。

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

Acquisition: Acquisition from PACS.HIS and LIS systems. Management: Relying on clinical trial database of Zhongnan Hospital of Wuhan University

数据与安全监察委员会:

Data and Safety Monitoring Committee:

有/Yes

注册人:

Name of Registration:

 2020-03-15 18:15:22