Artificial Intelligence System for the Detection and Prediction of Kidney Diseases Using Ocular Information

Status

UNKNOWN

Phases

Unknown

Study type

Observational

Source

ClinicalTrials.gov

Registry ID

NCT05223712

Enrollment

4000

Registered

2022-02-04

Start date

2021-08-28

Completion date

2022-12-31

Last updated

2022-02-04

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Artificial Intelligence, Kidney Diseases, Ophthalmology

Keywords

Kidney Diseases, Artificial Intelligence, Eye information

Brief summary

This is an retrospective and prospective multicenter study to develop and validate an artificial intelligent (AI) aided diagnosis, therapeutic effect assessment model including chronic kidney disease (CKD) and dialysis patients starting from April 2009, which is based on ophthalmic examinations (e.g. retinal fundus photography, slit-lamp images, OCTA, etc.) and CKD diagnostic and therapeutic data (routine clinical evaluations and laboratory data), to provide a reliable basis and guideline for clinical diagnosis and treatment.

Interventions

OTHERDiagnostic Test: Chronic Kidney Diseases

The development datasets were used to train the deep learning model, which was validated and tested by the other 4 datasets.

Study design

Observational model

COHORT

Time perspective

OTHER

Eligibility

Sex/Gender

ALL

Age

18 Years to No maximum

Healthy volunteers

Yes

Inclusion criteria

* Patients previously received kidney biopsy, ophthalmic examinations and routine examinations of the department of nephrology during in-hospital period with BCVA\>0.5.

Exclusion criteria

* Patients without retinal fundus images or kidney diseases. * The quality of the retinal fundus images can not meet the requirement for furthur analysis. * Severe loss of results of routine examinations of the department of nephrology.

Design outcomes

Primary

Measure	Time frame	Description
Area under the receiver operating characteristic curve of the deep learning system	baseline	The investigators will calculate the area under the receiver operating characteristic curve of deep learning system and compare this index between deep learning system and human doctors

Secondary

Measure	Time frame	Description
Sensitivity and specificity of the deep learning system	baseline	The investigators will calculate the sensitivity and specifity of deep learning system and compare this index between deep learning system and human doctors

Countries

China

Contacts

Primary ContactHaotian Lin, Ph. D

gddlht@aliyun.com13802793086

Outcome results

None listed

Source: ClinicalTrials.gov · Data processed: Feb 4, 2026