ChiCTR2300067259 版本V1.0 版本创建时间2023/01/01 22:26:00 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：

 ChiCTR2300067259 

最近更新日期：

Date of Last Refreshed on：

 2023-01-01 22:25:52 

注册时间：

Date of Registration：

 2023-01-01 00:00:00 

注册号状态：

预注册

Registration Status：

Prospective registration

注册题目：

採用基於人工智能的光學相干斷層掃描圖像檢測青光眼視神經病變的隨機對照試驗

Public title：

A Randomized Controlled Trial of Artificial Intelligence Based Glaucomatous Optic Neuropathy Detection from Optical Coherence Tomography

注册题目简写：

English Acronym：

研究课题的正式科学名称：

A Randomized Controlled Trial of Artificial Intelligence Based Glaucomatous Optic Neuropathy Detection from Optical Coherence Tomography

Scientific title：

採用基於人工智能的光學相干斷層掃描圖像檢測青光眼視神經病變的隨機對照試驗

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：

Ms Jennifer Tsoi 

研究负责人：

冉安然博士 

Applicant：

Ms Jennifer Tsoi 

Study leader：

Dr RAN Anran Emma 

申请注册联系人电话：

Applicant telephone：

 +852 39435818

研究负责人电话：

Study leader's
telephone：

+852 3943 5836

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：

 jennifertsoi@cuhk.edu.hk

研究负责人电子邮件：

Study leader's E-mail：

 anranran@cuhk.edu.hk

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：

香港九龍亞皆老街147K號香港眼科醫院3樓

研究负责人通讯地址：

香港九龍亞皆老街147K號香港眼科醫院4樓

Applicant address：

3/F, Hong Kong Eye Hospital, 147K Argyle Street, Kowloon, Hong Kong

Study leader's address：

4/F, Hong Kong Eye Hospital, 147K Argyle Street, Kowloon, Hong Kong

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：

香港中文大學眼科及視覺科學學系

Applicant's institution：

Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong

研究负责人所在单位：

香港中文大學眼科及視覺科學學系

Affiliation of the Leader：

Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong

是否获伦理委员会批准：

是

Approved by ethic committee：

Yes

伦理委员会批件文号：

Approved No. of ethic committee：

 KC/KE-21-0320/ER-1

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：

九龍中及九龍東聯網臨床研究倫理委員會

Name of the ethic committee：

Research Ethics Committee (Kowloon Central / Kowloon East)

伦理委员会批准日期：

Date of approved by ethic committee：

 2022-03-09 00:00:00

伦理委员会联系人：

Ms Lyon Chan

Contact Name of the ethic committee：

Ms Lyon Chan

伦理委员会联系地址：

香港九龍加士居道30號伊利沙伯醫院護士宿舍4樓414室

Contact Address of the ethic committee：

Room 414, Nurse Quarters, Queen Elizabeth Hospital, 30 Gascoigne Road, Kowloon, Hong Kong

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：

香港中文大學眼科及視覺科學學系；醫務衞生局研究處

Primary sponsor：

Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong；Research Office, Health Bureau

研究实施负责（组长）单位地址：

香港九龍亞皆老街147K號香港眼科醫院4樓；香港上環林士街2號林士街多層停車場9樓

Primary sponsor's address：

4/F, Hong Kong Eye Hospital, 147K Argyle Street, Kowloon, Hong Kong；9/F, Rumsey Street Multi-storey Carpark Building, 2 Rumsey Street, Sheung Wan, Hong Kong

试验主办单位(项目批准或申办者)：

Secondary sponsor：

国家：

中国

省(直辖市)：

香港

市(区县)：

Country：

China

Province：

Hong Kong

City：

单位(医院)：

香港中文大學眼科及視覺科學學系

具体地址：

九龍亞皆老街147K號香港眼科醫院4樓

Institution
hospital：

Department of Ophthalmology and Visual Sciences, the Chinese University of Hong Kong

Address：

4/F, Hong Kong Eye Hospital, 147K Argyle Street, Kowloon

经费或物资来源：

醫療衞生研究基金

Source(s) of funding：

Health and Medical Research Fund

研究疾病：

青光眼性視神經病變  

Target disease：

Glaucomatous optic neuropathy (GON)

研究疾病代码：

Target disease code：

研究类型：

干预性研究

Study type：

Interventional study

研究所处阶段：

 其它 

Study phase：

N/A

研究设计：

随机平行对照 

Study design：

Parallel 

研究目的：

在真實世界的臨床環境中比較全自動 AI 平台臨床醫生使用 AI 平台和不使用 AI 平台評估時從 OCT 圖像中實時篩選青光眼視神經病變的準確性  

Objectives of Study：

To conduct a randomized controlled trial to compare the accuracies between a fully automated AI-platform, clinicians’ assessment with an AI-platform, and clinicians’ assessment without an AI-platform for screening GON from OCT images in a real-world clinical setting.

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) Subjects above 18 years old, and
(2) Subjects referred by primary care settings due to glaucoma-related suspicious findings, such as increased cup-to-disc ratio, high intraocular pressure, and disc haemorrhage, or
(3) Subjects referred by primary care settings for regular eye check-ups, or
(4) Subjects with a family history of glaucoma, or
(5) Subjects with diabetes mellitus.

Inclusion criteria

(1) Subjects above 18 years old, and
(2) Subjects referred by primary care settings due to glaucoma-related suspicious findings, such as increased cup-to-disc ratio, high intraocular pressure, and disc haemorrhage, or
(3) Subjects referred by primary care settings for regular eye check-ups, or
(4) Subjects with a family history of glaucoma, or
(5) Subjects with diabetes mellitus.

排除标准：

Subjects have already confirmed diagnosis of glaucoma by ophthalmologists.

Exclusion criteria：

Subjects have already confirmed diagnosis of glaucoma by ophthalmologists.

研究实施时间：

Study execute time：

从 From 2023-01-01 00:00:00至 To 2026-03-31 00:00:00  

征募观察对象时间：

Recruiting time：

从 From 2023-01-01 00:00:00 至 To 2026-03-31 00:00:00

干预措施：

Interventions：

组别：

全自動AI組

样本量：

 284

Group：

Fully automated AI group

Sample size：

干预措施：

全自动視網膜成像檢查

干预措施代码：

Intervention：

Retinal imaging using OCT and AI-based image analysis

Intervention code：

组别：

半自動AI組

样本量：

 284

Group：

Semi-automated AI group

Sample size：

干预措施：

半自动視網膜成像檢查

干预措施代码：

Intervention：

Clinicians will review the OCT images and printed-out AI reports for subjects

Intervention code：

组别：

對照組

样本量：

 284

Group：

Control group

Sample size：

干预措施：

无AI辅助視網膜成像檢查

干预措施代码：

Intervention：

Retinal imaging using OCT and AI-based image analysis

Intervention code：

研究实施地点：

Countries of recruitment and research settings：

国家：

 中国

省(直辖市)：

 香港 

市(区县)：

  

Country：

China

Province：

Hong Kong

City：

单位(医院)：

 香港眼科醫院 

单位级别：

  

Institution
hospital：

Hong Kong Eye Hospital

Level of the institution：

国家：

 中国

省(直辖市)：

 香港 

市(区县)：

  

Country：

China

Province：

Hong Kong

City：

单位(医院)：

 威爾斯親王醫院 

单位级别：

  

Institution
hospital：

Prince of Wales Hospital

Level of the institution：

国家：

 中国

省(直辖市)：

 香港 

市(区县)：

  

Country：

China

Province：

Hong Kong

City：

单位(医院)：

 香港中文大學眼科中心 

单位级别：

  

Institution
hospital：

CUHK Eye Centre

Level of the institution：

测量指标：

Outcomes：

指标中文名：

受试者工作特征曲线下面积（AUROC）值

指标类型：

主要指标

Outcome：

Area under receiver operating characteristic curve (AUROC) value

Type：

Primary indicator

测量时间点：

测量方法：

基於/不基於人工智能的光學相干斷層掃描圖像分析

Measure time point of outcome：

Measure method：

OCT image analysis based/not based on AI

指标中文名：

平均掃瞄和報告時間

指标类型：

次要指标

Outcome：

The average time of imaging and generating reports in each arm

Type：

Secondary indicator

测量时间点：

测量方法：

基於/不基於人工智能的光學相干斷層掃描圖像分析

Measure time point of outcome：

Measure method：

OCT image analysis based/not based on AI

指标中文名：

平均醫生解讀時間

指标类型：

次要指标

Outcome：

The average time of clinicians' interpretation in each arm

Type：

Secondary indicator

测量时间点：

测量方法：

醫生進行的光學相干斷層掃描圖像分析

Measure time point of outcome：

Measure method：

OCT image analysis performed by clinicians

指标中文名：

錯誤分析的對應原因和數量

指标类型：

次要指标

Outcome：

Misclassification analysis including reasons and corresponding numbers

Type：

Secondary indicator

测量时间点：

测量方法：

基於/不基於人工智能的光學相干斷層掃描圖像分析

Measure time point of outcome：

Measure method：

OCT image analysis based/not based on AI

指标中文名：

醫生對AI系統的接受程度

指标类型：

次要指标

Outcome：

Clinicians' acceptance of AI-platform assistance and a fully automated AI-platform

Type：

Secondary indicator

测量时间点：

测量方法：

問卷調查

Measure time point of outcome：

Measure method：

Questionnaire

指标中文名：

安全指標

指标类型：

次要指标

Outcome：

Safety outcomes

Type：

Secondary indicator

测量时间点：

测量方法：

基於/不基於人工智能的光學相干斷層掃描圖像分析

Measure time point of outcome：

Measure method：

OCT image analysis based/not based on AI

指标中文名：

敏感性、特异性、准确性

指标类型：

主要指标

Outcome：

Sensitivity, specificity, accuracy

Type：

Primary indicator

测量时间点：

测量方法：

基於/不基於人工智能的光學相干斷層掃描圖像分析

Measure time point of outcome：

Measure method：

OCT image analysis based/not based on AI

指标中文名：

阳性预测值、阴性预测值

指标类型：

主要指标

Outcome：

Positive predictive value and negative predictive value

Type：

Primary indicator

测量时间点：

测量方法：

基於/不基於人工智能的光學相干斷層掃描圖像分析

Measure time point of outcome：

Measure method：

OCT image analysis based/not based on AI

采集人体标本：

Collecting sample(s)
from participants：

标本中文名：

无

组织：

Sample Name：

None

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 18 岁 years
最大 Max age 岁 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）：

A random number generating program will conduct the randomization with no stratification factors to avoid selection bias. In addition, we will involve eight clinicians in different training stages, i.e., two first-year trainees in ophthalmology, two final-year trainees in ophthalmology, two first-year trainees in glaucoma,

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

Eligible subjects will be randomly assigned into 3 groups on subject-level (1:1:1 allocation) with one control group and two intervention groups using different assessment methods. A random number generating program will conduct the randomization with no stratification factors to avoid selection bias. In addition, we wi

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：

The study subjects, investigators involving in data management and analysis, glaucoma specialists providing the reference standard will be blinded to the group assignments to prevent ascertainment bias. The technicians conducting OCT imaging and randomization, clinicians reviewing either OCT conventional reports or AI reports will not be masked.

Blinding：

The study subjects, investigators involving in data management and analysis, glaucoma specialists providing the reference standard will be blinded to the group assignments to prevent ascertainment bias. The technicians conducting OCT imaging and randomization, clinicians reviewing either OCT conventional reports or AI reports will not be masked.

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）：

N/A

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

N/A

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：

Patient data will be handled with utmost care so as not to breach patient privacy in any form. The data will be stored in secure cabinets and/or computers which will be password operated. To protect patient privacy, all research data will be handled in line with HA / Hospital’s policy in handling / storage / destruction of patients’ medical records. Electronic data will be saved in secured computers with restricted access. USB Device will not be used for patient information nor personal data. Personal data (name, HKID, OPD / hospital numbers, address and any other personal identifiable information) will not be recorded on the project’s data sheets or electronic files. A non-recognizable study code will be used for each patient instead. The document of electronic file containing the linkage information between the study code and the identity of the patient will not contain any other information and will be kept separate from the study data files or data sheets with the same stringent security as the medical record. Any documents or electronic files containing personal identifiable information will be considered as part of the medical record and will be dealt with the same stringent regulations of security according to the hospital policies. All of the investigators will be responsible for data handling and protection.

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

Patient data will be handled with utmost care so as not to breach patient privacy in any form. The data will be stored in secure cabinets and/or computers which will be password operated. To protect patient privacy, all research data will be handled in line with HA / Hospital’s policy in handling / storage / destruction of patients’ medical records. Electronic data will be saved in secured computers with restricted access. USB Device will not be used for patient information nor personal data. Personal data (name, HKID, OPD / hospital numbers, address and any other personal identifiable information) will not be recorded on the project’s data sheets or electronic files. A non-recognizable study code will be used for each patient instead. The document of electronic file containing the linkage information between the study code and the identity of the patient will not contain any other information and will be kept separate from the study data files or data sheets with the same stringent security as the medical record. Any documents or electronic files containing personal identifiable information will be considered as part of the medical record and will be dealt with the same stringent regulations of security according to the hospital policies. All of the investigators will be responsible for data handling and protection.

数据与安全监察委员会：

Data and Safety Monitoring Committee：

有/Yes

注册人：

Name of Registration：

  2023-01-01 22:25:52