CT大数据驱动的类鼻疽肺炎预警、准确诊断及预后预测研究

注册号:

Registration number:

ChiCTR2200060613 

最近更新日期:

Date of Last Refreshed on:

2023-03-26 20:19:02 

注册时间:

Date of Registration:

2022-06-05 00:00:00 

注册号状态:

补注册

Registration Status:

Retrospective registration

注册题目:

CT大数据驱动的类鼻疽肺炎预警、准确诊断及预后预测研究

Public title:

Study on Early Warning, Accurate Diagnosis and Prognostic Prediction of Melioidosis Pneumonia Driven by CT Big Data

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于CT图像的人工智能技术构建类鼻疽肺炎诊断、分级及预警系统

Scientific title:

Study on Early Warning, Accurate Diagnosis and Prognostic Prediction of Melioidosis Pneumonia Driven by CT Big Data

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:

赵羿丞 

研究负责人:

陈杨 

Applicant:

Yicheng Zhao 

Study leader:

Yang Chen 

申请注册联系人电话:

Applicant telephone:

+86 17208273857

研究负责人电话:

Study leader's
telephone:

+86 18980605561

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:

2424796029@qq.com

研究负责人电子邮件:

Study leader's E-mail:

Sophie-0627@163.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:

四川省成都市武侯区玉林街道人民南路三段四川大学华西校区

研究负责人通讯地址:

成都市武侯区国学巷37号四川大学华西医院超声科

Applicant address:

West China Campus of Sichuan University, Section 3, Renmin Road South, Yulin Street, Wuhou District, Chengdu , Sichuan,China

Study leader's address:

West China Campus of Sichuan University, Section 3, Renmin Road South, Yulin Street, Wuhou District, Chengdu , Sichuan,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

Applicant's institution:

Sichuan University

研究负责人所在单位:

Affiliation of the Leader:

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:

ZY-IRB-FOM-063

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:

海口市人民医院生物医学伦理委员会

Name of the ethic committee:

Hakou Municipal People's Hospital Biomedical Ethics Committee

伦理委员会批准日期:

Date of approved by ethic committee:

2021-04-27 00:00:00

伦理委员会联系人:

邱英麒

Contact Name of the ethic committee:

Yingqi Qiu

伦理委员会联系地址:

海口市人民大道42号

Contact Address of the ethic committee:

42 Renmin Avenue, Haikou

伦理委员会联系人电话:

Contact phone of the ethic committee:

0989-66189770

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 of Sichuan University

研究实施负责(组长)单位地址:

四川省成都市国学巷37号

Primary sponsor's address:

37 Guoxue Lane,Chengdu Sichuan,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 of Sichuan University

Address:

37 Guoxue lane, Wuhou District, Chengdu, Sichuan, China

经费或物资来源:

Source(s) of funding:

none

研究疾病:

类鼻疽肺炎  

Target disease:

Melioidosis pneumonia

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:

回顾性研究 

Study phase:

Retrospective study

研究设计:

病例对照研究 

Study design:

Case-Control study 

研究目的:

建立类鼻疽肺炎和常见CAP影像及临床数据库,可靠的数据库是奠定AI 研究的基础;在CT大数据驱动下,以医生对肺炎的诊断和鉴别诊断思维为指导, 建立基于医学领域知识引导的深度学习模型,开发类鼻疽肺炎早期预警、准确 诊断及预后预测的AI新方法,为类鼻疽肺炎辅助诊疗提供重要参考。以及在将 来的另一传染性肺炎的临床实践中可能发挥可靠的作用,并为迁移学习到医学 其他方向或其他领域提供一个新的视角。  

Objectives of Study:

The establishment of a database of common pneumonia and rhinocercosis is the basis for the clinical study of cap; Driven by CT big data and guided by doctors' Thinking on diagnosis and differential diagnosis of pneumonia, a deep learning model guided by medical knowledge is established, and a new AI method for early warning, accurate diagnosis and prognosis prediction of melioidosis pneumonia is developed, so as to provide an important reference for the auxiliary diagnosis and treatment of melioidosis pneumonia. And it may play a reliable role in the clinical practice of another infectious pneumonia in the future, and provide a new perspective for migrating learning to other directions or other fields of medicine.

药物成份或治疗方案详述:

 

Description for medicine or protocol of treatment in detail:

 

纳入标准:

Inclusion criteria

排除标准:

① 一次胸部CT扫描<25张图片;② CT扫描序列信息丢失;③ 有运动伪影或分辨率显著降低的CT图像;④ 排除肿瘤或结核而并发类鼻疽肺炎的患者;⑤ 孕妇或对检查不能耐受的患者;⑥ 对于实验室检查病原学结果与临床、影像和/或病理不同诊断意见需排除。

Exclusion criteria:

1. one chest CT scan < 25 images;
2. CT scan sequence information is lost;
3. CT images with motion artifacts or significantly reduced resolution;
4. Patients with tumor or tuberculosis complicated with melioidosis pneumonia were excluded;
5. Pregnant women or patients who cannot tolerate the examination;
6. If the etiological results of laboratory examination are different from clinical, imaging and / or pathology, the diagnostic opinions should be excluded.

研究实施时间:

Study execute time:

From 2002-01-01 00:00:00 To 2021-12-31 00:00:00  

征募观察对象时间:

Recruiting time:

From 2020-09-01 00:00:00 To 2021-12-31 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):

由微生物培养结果确定,从患者的任一标本中分离培 养出Bp即可诊断,标本集包括血液、呼吸道分泌物、尿液、脓液和/或来自伤口、 病变的拭子,以及脑脊液。

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):

Diagnosed by isolation and culture of Bp from any specimen from a patient, as determined by microbial culture, the specimen set includes blood, respiratory secretions, urine, pus and/or swabs from wounds, lesions, and cerebrospinal fluid.

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):

CT试验

Index test:

CT test

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)

类鼻疽肺炎患者,最常见感染类型,表现为原发性或血源播散性肺炎。 前者最易误诊为肺结核,除临床表现相似外,X线胸片是导致误诊的重要原因,其多侵袭上叶,呈实变或浓烟样浸润,并可有薄壁空洞 (2cm~7cm)。

例数:

Sample size:

170

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):

The most common type of infection in patients with melioid pneumonia is primary or hematogenous disseminated pneumonia. The former is most likely to be misdiagnosed as pulmonary tuberculosis. In addition to the similar clinical manifestations, chest X-ray is an important cause of misdiagnosis. It mostly invades the

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):

继发性类鼻疽肺炎患者;肿瘤或结核而并发类鼻疽肺炎的患者;细菌性肺炎、病毒性肺炎、真菌性肺炎和肺结核患者

例数:

Sample size:

1548

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

Patients with secondary melioid pneumonia; patients with tumor or tuberculosis complicated by melioid pneumonia; patients with bacterial pneumonia, viral pneumonia, fungal pneumonia and pulmonary tuberculosis

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

四川 

市(区县):

成都 

Country:

China

Province:

Sichuan

City:

Chengdu

单位(医院):

四川大学华西医院 

单位级别:

三级甲等 

Institution
hospital:

West China Hospital of Sichuan University

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

海南 

市(区县):

海口 

Country:

China

Province:

Hainan

City:

Haikou

单位(医院):

海南医学院 

单位级别:

三级甲等 

Institution
hospital:

Hainan Medical College

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

病变体积

指标类型:

主要指标

Outcome:

Lesion volume

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

HU值

指标类型:

主要指标

Outcome:

HU value

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

病灶变化率

指标类型:

主要指标

Outcome:

Lesion change rate

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

年龄

指标类型:

次要指标

Outcome:

age

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

C反应蛋白

指标类型:

次要指标

Outcome:

C reactive protein

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

血清乳酸脱氢酶

指标类型:

次要指标

Outcome:

LDH

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

中性粒细胞/淋巴细胞比值

指标类型:

次要指标

Outcome:

Neutrophil/lymphocyte ratio

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

血氧饱和度

指标类型:

次要指标

Outcome:

blood oxygen saturation

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

白蛋白

指标类型:

次要指标

Outcome:

albumin

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

血小板

指标类型:

次要指标

Outcome:

platelets

Type:

Secondary 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:

征募研究对象情况:

Recruiting status:

结束

/Completed

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):

本研究不需要随机

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

In the study,there is no need for randomization

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:

不适用

Blinding:

N/A

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

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):

上传至四川大学华西医院科研管理系统

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

Upload to the Scientific Research Management System of West China Hospital, Sichuan University

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:

数据采集:在病案室或检验科检索所有Bp感染患者名单,根据影像PACS和电子病例系统明确肺部感染,并纳入本研究,对影像报告和电子病例系统诊断进行修正。数据管理:以DICOM格式存储影像资料(薄层和厚层分别存储),Excel或PDF导出/登记电子病历患者临床信息及检验指标。

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

Data collection: The list of all patients with Bp infection was searched in the medical record room or laboratory department, and the pulmonary infection was identified according to the imaging PACS and electronic medical record system, and included in this study, and the diagnosis of the imaging report and electronic medical record system was revised. Data management: store image data in DICOM format (thin layer and thick layer are stored separately), export/register electronic medical record patient clinical information and test indicators in Excel or PDF.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

有/Yes

注册人:

Name of Registration:

 2022-06-05 20:50:54