- ICH GCP
- US Clinical Trials Registry
- Clinical Trial NCT07940205
Machine-learning Algorithm for Prediction of CKD From Retinal Images (healthy route)
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.
Study Overview
Status
Intervention / Treatment
Study Type
Enrollment (Estimated)
Contacts and Locations
Study Contact
- Name: Mohamed Khalis, Professor
- Phone Number: +212 628-245023
- Email: mkhalis@um6ss.ma
Participation Criteria
Eligibility Criteria
Ages Eligible for Study
Accepts Healthy Volunteers
Genders Eligible for Study
Sampling Method
Study Population
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.
Description
Inclusion Criteria
Participants are eligible to be included in the study only if all of the following criteria apply:
- Participant must be ≥ 18 years of age, at the time of signing the informed consent.
- Previously documented eGFR ≥ 3months
- Any participant with a positive dipstick result for proteinuria of at least trace
- 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:
- 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.
- Any known eye condition that may preclude clear imaging of the retina for example; cataracts
- Individuals with hypertensive emergencies and hyperglycemic or hypoglycemic emergencies
- Involvement in the planning and/or conduct of the study (applies to HHA/ AstraZeneca staff and/or staff at the study site).
- 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.
Study Plan
How is the study designed?
Design Details
- Observational Models: CASE_CONTROL
- Time Perspectives: CROSS_SECTIONAL
Cohorts and Interventions
Group / Cohort |
Intervention / Treatment |
|---|---|
|
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 |
What is the study measuring?
Primary Outcome Measures
Outcome Measure |
Measure Description |
Time Frame |
|---|---|---|
|
The accuracy of a machine-learning based algorithm to predict high risk CKD from digital retinal images
Time Frame: 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
|
Secondary Outcome Measures
Outcome Measure |
Measure Description |
Time Frame |
|---|---|---|
|
Accuracy of the Machine Learning Algorithm for Detection of Hypertension and T2DM
Time Frame: 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
|
Collaborators and Investigators
Collaborators
Study record dates
Study Major Dates
Study Start (Estimated)
Primary Completion (Estimated)
Study Completion (Estimated)
Study Registration Dates
First Submitted
First Submitted That Met QC Criteria
First Posted (Actual)
Study Record Updates
Last Update Posted (Actual)
Last Update Submitted That Met QC Criteria
Last Verified
More Information
Terms related to this study
Additional Relevant MeSH Terms
- Urogenital Diseases
- Endocrine System Diseases
- Vascular Diseases
- Cardiovascular Diseases
- Pathologic Processes
- Male Urogenital Diseases
- Kidney Diseases
- Urologic Diseases
- Female Urogenital Diseases
- Female Urogenital Diseases and Pregnancy Complications
- Chronic Disease
- Disease Attributes
- Metabolic Diseases
- Glucose Metabolism Disorders
- Diabetes Mellitus
- Renal Insufficiency
- Pathological Conditions, Signs and Symptoms
- Nutritional and Metabolic Diseases
- Hypertension
- Diabetes Mellitus, Type 2
- Renal Insufficiency, Chronic
Other Study ID Numbers
- CKD-AI-2026-07
Drug and device information, study documents
Studies a U.S. FDA-regulated drug product
Studies a U.S. FDA-regulated device product
This information was retrieved directly from the website clinicaltrials.gov without any changes. If you have any requests to change, remove or update your study details, please contact register@clinicaltrials.gov. As soon as a change is implemented on clinicaltrials.gov, this will be updated automatically on our website as well.