| CTRI Number |
CTRI/2024/04/065141 [Registered on: 03/04/2024] Trial Registered Prospectively |
| Last Modified On: |
26/03/2024 |
| Post Graduate Thesis |
No |
| Type of Trial |
Observational |
|
Type of Study
|
Cross Sectional Study |
| Study Design |
Other |
|
Public Title of Study
|
Kidney disease identification using artificial intelligence and retinal photographs in people with diabetes |
|
Scientific Title of Study
|
A deep-learning based tool for prediction of chronic kidney disease from retinal images in people with type 2 diabetes |
| Trial Acronym |
NIL |
|
Secondary IDs if Any
|
| Secondary ID |
Identifier |
| NIL |
NIL |
|
|
Details of Principal Investigator or overall Trial Coordinator (multi-center study)
|
| Name |
Dr Viswanathan Mohan |
| Designation |
Chairman |
| Affiliation |
Madras Diabetes Research Foundation |
| Address |
Madras Diabetes Research Foundation
Department of Diabetology,
No 4, Conran Smith Road, Gopalapuram, Chennai
Chennai
TAMIL NADU
600086
India |
| Phone |
04443968888 |
| Fax |
|
| Email |
drmohans@diabetes.ind.in |
|
Details of Contact Person
Scientific Query
|
| Name |
Dr Viswanathan Mohan |
| Designation |
Chairman |
| Affiliation |
Madras Diabetes Research Foundation |
| Address |
Madras Diabetes Research Foundation
Department of Diabetology,
No 4, Conran Smith Road, Gopalapuram, Chennai
Chennai
TAMIL NADU
600086
India |
| Phone |
04443968888 |
| Fax |
|
| Email |
drmohans@diabetes.ind.in |
|
Details of Contact Person
Public Query
|
| Name |
Dr Viswanathan Mohan |
| Designation |
Chairman |
| Affiliation |
Madras Diabetes Research Foundation |
| Address |
Madras Diabetes Research Foundation,
Department of Diabetology,
No 4, Conran Smith Road, Gopalapuram, Chennai
Chennai
TAMIL NADU
600086
India |
| Phone |
04443968888 |
| Fax |
|
| Email |
drmohans@diabetes.ind.in |
|
|
Source of Monetary or Material Support
|
| European Foundation for the Study of Diabetes (EFSD) |
|
|
Primary Sponsor
|
| Name |
European Foundation for the Study of Diabetes |
| Address |
Rheindorfer Weg 3
40591 Düsseldorf
Germany |
| Type of Sponsor |
Other [Non profit research funding organization ] |
|
|
Details of Secondary Sponsor
|
|
|
Countries of Recruitment
|
India |
|
Sites of Study
|
| No of Sites = 1 |
| Name of Principal
Investigator |
Name of Site |
Site Address |
Phone/Fax/Email |
| DrViswanathan Mohan |
Madras Diabetes Research Foundation |
Department of Diabetology, No 4, Conran Smith Road, Gopalapuram
Chennai
TAMIL NADU |
04443968888
drmohans@diabetes.ind.in |
|
|
Details of Ethics Committee
|
| No of Ethics Committees= 1 |
| Name of Committee |
Approval Status |
| Institutional Ethics Committee of Madras Diabetes Research Foundation |
Approved |
|
|
Regulatory Clearance Status from DCGI
|
|
|
Health Condition / Problems Studied
|
| Health Type |
Condition |
| Patients |
(1) ICD-10 Condition: E112||Type 2 diabetes mellitus with kidney complications, |
|
|
Intervention / Comparator Agent
|
| Type |
Name |
Details |
| Intervention |
NIL |
NIL |
|
|
Inclusion Criteria
|
| Age From |
18.00 Year(s) |
| Age To |
80.00 Year(s) |
| Gender |
Both |
| Details |
1. Data of individuals with type 2 diabetes aged ≥ 18 years who have provided written informed consent for use of their anonymised data.
2. Data of individuals with and without diabetic kidney disease
3. Individuals who have clear retinal images
4. Retinal images with and without diabetic retinopathy changes
|
|
| ExclusionCriteria |
| Details |
1.Unclear retinal images due to media opacities
2.Clinical and image data of those who have not provided consent for use of anonymized data
|
|
|
Method of Generating Random Sequence
|
Not Applicable |
|
Method of Concealment
|
Not Applicable |
|
Blinding/Masking
|
Not Applicable |
|
Primary Outcome
|
| Outcome |
TimePoints |
| Development of deep learning algorithm for prediction of kidney disease using retinal images among type 2 diabetes |
1 year |
|
|
Secondary Outcome
|
| Outcome |
TimePoints |
| Real time validation deep learning algorithm developed for prediction of kidney disease using retinal images |
6 months |
|
|
Target Sample Size
|
Total Sample Size="2400"
Sample Size from India="2400"
Final Enrollment numbers achieved (Total)= "Applicable only for Completed/Terminated trials"
Final Enrollment numbers achieved (India)="Applicable only for Completed/Terminated trials" |
|
Phase of Trial
|
N/A |
|
Date of First Enrollment (India)
|
01/07/2024 |
| Date of Study Completion (India) |
Applicable only for Completed/Terminated trials |
| Date of First Enrollment (Global) |
Date Missing |
| Date of Study Completion (Global) |
Applicable only for Completed/Terminated trials |
|
Estimated Duration of Trial
|
Years="1"
Months="6"
Days="0" |
|
Recruitment Status of Trial (Global)
|
Not Applicable |
| Recruitment Status of Trial (India) |
Not Yet Recruiting |
|
Publication Details
|
N/A |
|
Individual Participant Data (IPD) Sharing Statement
|
Will individual participant data (IPD) be shared publicly (including data dictionaries)?
Response - NO
|
|
Brief Summary
|
Background
The burden of chronic kidney disease
(CKD) is increasing due to exponential increase in diabetes and hypertension
globally. The
association between diabetic retinopathy (DR) and diabetic kidney disease (DKD)
suggests common pathways of microangiopathy. Application of Artificial intelligence (AI) and
deep learning (DL) in medicine aids early detection, disease diagnoses and
predictions and enables appropriate timely intervention/ management. Retinal
colour photography can be a non-invasive approach for identification of early
microvascular alterations of chronic systemic complications especially CKD
prior to the onset of overt clinical presentation.
Objectives:
To develop and validate a
DL based algorithm to detect and prognosticate the risk for development of CKD using
retinal images and clinical data in individuals with type 2 diabetes.
Methods:
Anonymized clinical
metadata and corresponding retinal images of 2000 individuals with type 2
diabetes with and without DR will be utilized for development of DL model to
detect CKD. Systemic parameters such as age, gender, duration of diabetes,
glycated haemoglobin (HbA1c) and hypertension (HT) will be utilized along with
retinal colour photographs for this model. Longitudinal data will be used for
developing the prognostic tool to detect people at risk of stage 3 CKD (defined
as estimated glomerular filtration rate [eGFR] < 60 ml/ min/ 1.73m2).
Convolution neural
network-support vector machine (CNN-SVM) DL model will be used. After the assessment of accuracy (sensitivity and
specificity) of the DL algorithm in individuals with type 2 diabetes, the
external validation will be carried out prospectively among 400 patients.
Expected outcome:
The tool would aid early
detection and prediction of CKD (before it reaches stages 4 or 5), easily
manageable with glycemic control and blood pressure control; hence reduce the
morbidity and healthcare costs due to CKD.
Holistic screening for DR and CKD in individuals
with diabetes would be possible through non-invasive retinal imaging with use
of AI.
|