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

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

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.

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.