此页面是自动翻译的,不保证翻译的准确性。请参阅 英文版 对于源文本。

Machine-learning Algorithm for Prediction of CKD From Retinal Images (healthy route)

2026年11月10日 更新者:Mohamed Khalis、Centre Mohammed VI de la Recherche et de l'Innovation (CM6RI)

A Validation Study to Assess Performance Accuracy of a Machine-Learning Algorithm for the Prediction of Chronic Kidney Disease (CKD) From Digital Retinal Images

This is a non-interventional study being conducted to validate the performance of a machine learning algorithm for prediction of eGFR from digital retinal images in a target population for future intended use as a populated-based screening tool. Secondary objectives will include prediction of blood pressure (> or ≤ 140/90 mmHg) and presence or absence of T2DM as determined by glycated haemoglobin (HbA1c >6.5%) or on the basis of clinical history. Once validated, the methodology will be deployed for health screening to improve access to healthcare.

研究概览

研究类型

观察性的

注册 (估计的)

500

联系人和位置

本节提供了进行研究的人员的详细联系信息,以及有关进行该研究的地点的信息。

学习联系方式

  • 姓名:Mohamed Khalis, Professor
  • 电话号码:+212 628-245023
  • 邮箱:mkhalis@um6ss.ma

参与标准

研究人员寻找符合特定描述的人,称为资格标准。这些标准的一些例子是一个人的一般健康状况或先前的治疗。

资格标准

适合学习的年龄

18年 及以上 (成人、年长者)

接受健康志愿者

是的

有资格学习的性别

全部

取样方法

非概率样本

研究人群

The study population consists of adult patients diagnosed with chronic kidney disease (CKD), hypertension, diabetes mellitus, or without these conditions, attending routine outpatient clinics at Hôpital Universitaire International Cheikh Khalifa Ibn Zaid in Casablanca and Centre Hospitalier Universitaire Hassan II in Fez, Morocco.

描述

Inclusion Criteria

Participants are eligible to be included in the study only if all of the following criteria apply:

  1. Participant must be ≥ 18 years of age, at the time of signing the informed consent.
  2. Previously documented eGFR ≥ 3months
  3. Any participant with a positive dipstick result for proteinuria of at least trace
  4. Capable of giving signed informed consent as described in Appendix A which includes compliance with the requirements and restrictions listed in the informed consent form and in this protocol

Exclusion Criteria:

  • Participants are excluded from the study if any of the following criteria apply:

    1. As judged by the investigator, any evidence of a condition which in the investigator's opinion makes it undesirable for the participant to participate in the study.
    2. Any known eye condition that may preclude clear imaging of the retina for example; cataracts
    3. Individuals with hypertensive emergencies and hyperglycemic or hypoglycemic emergencies
    4. Involvement in the planning and/or conduct of the study (applies to HHA/ AstraZeneca staff and/or staff at the study site).
    5. Judgment by the investigator that the participant should not participate in the study if the participant is unlikely to comply with study procedures, restrictions and requirements.

学习计划

本节提供研究计划的详细信息,包括研究的设计方式和研究的衡量标准。

研究是如何设计的?

设计细节

  • 观测模型:CASE_CONTROL
  • 时间观点:CROSS_SECTIONAL

队列和干预

团体/队列
干预/治疗
CKD Cases

350 participants (cases) with diabetes and/or hypertension and/or CKD with previously documented eGFR < 60 ml/min/1.73m2 ≥3 months

A machine learning-based algorithm analyzes retinal images to assess its ability to detect chronic kidney disease

Controls

150 (controls) with previously documented eGFR ≥ 60 ml/min/1.73m2 ≥ 3 months

A machine learning-based algorithm analyzes retinal images to assess its ability to detect chronic kidney disease

研究衡量的是什么?

主要结果指标

结果测量
措施说明
大体时间
The accuracy of a machine-learning based algorithm to predict high risk CKD from digital retinal images
大体时间:Baseline

To quantify the discrimination of the machine-learning algorithm for identifying the binary target condition of persistent eGFR <60 mL/min/1.73 m², using standard-of-care serum creatinine as the reference standard and the AUROC with a 95% confidence interval as the primary performance measure

Baseline

次要结果测量

结果测量
措施说明
大体时间
Accuracy of the Machine Learning Algorithm for Detection of Hypertension and T2DM
大体时间:Baseline

To quantify the sensitivity, specificity, and discriminative performance of a machine-learning-based algorithm for identifying SBP >140 mmHg from digital retinal images, using standard-of-care assessment as the reference standard and the AUROC with a 95% confidence interval as the primary performance measure

Baseline

合作者和调查者

在这里您可以找到参与这项研究的人员和组织。

研究记录日期

这些日期跟踪向 ClinicalTrials.gov 提交研究记录和摘要结果的进度。研究记录和报告的结果由国家医学图书馆 (NLM) 审查,以确保它们在发布到公共网站之前符合特定的质量控制标准。

研究主要日期

学习开始 (估计的)

2027年1月1日

初级完成 (估计的)

2027年6月30日

研究完成 (估计的)

2027年10月31日

研究注册日期

首次提交

2026年7月16日

首先提交符合 QC 标准的

2026年11月10日

首次发布 (实际的)

2026年11月16日

研究记录更新

最后更新发布 (实际的)

2026年11月16日

上次提交的符合 QC 标准的更新

2026年11月10日

最后验证

2026年7月1日

更多信息

此信息直接从 clinicaltrials.gov 网站检索,没有任何更改。如果您有任何更改、删除或更新研究详细信息的请求,请联系 register@clinicaltrials.gov. clinicaltrials.gov 上实施更改,我们的网站上也会自动更新.

订阅