Deep learning algorithms to detect diabetic kidney disease from retinal photographs in multiethnic populations with diabetes

Bjorn Kaijun Betzler, Evelyn Yi Lyn Chee, Feng He, Cynthia Ciwei Lim, Jinyi Ho, Haslina Hamzah, Ngiap Chuan Tan, Gerald Liew, Gareth J McKay, Ruth E Hogg, Ian S Young, Ching-Yu Cheng, Su Chi Lim, Aaron Y Lee, Tien Yin Wong, Mong Li Lee, Wynne Hsu, Gavin Siew Wei Tan, Charumathi Sabanayagam

Research output: Contribution to journalArticlepeer-review

8 Citations (Scopus)

Abstract

OBJECTIVE: To develop a deep learning algorithm (DLA) to detect diabetic kideny disease (DKD) from retinal photographs of patients with diabetes, and evaluate performance in multiethnic populations.

MATERIALS AND METHODS: We trained 3 models: (1) image-only; (2) risk factor (RF)-only multivariable logistic regression (LR) model adjusted for age, sex, ethnicity, diabetes duration, HbA1c, systolic blood pressure; (3) hybrid multivariable LR model combining RF data and standardized z-scores from image-only model. Data from Singapore Integrated Diabetic Retinopathy Program (SiDRP) were used to develop (6066 participants with diabetes, primary-care-based) and internally validate (5-fold cross-validation) the models. External testing on 2 independent datasets: (1) Singapore Epidemiology of Eye Diseases (SEED) study (1885 participants with diabetes, population-based); (2) Singapore Macroangiopathy and Microvascular Reactivity in Type 2 Diabetes (SMART2D) (439 participants with diabetes, cross-sectional) in Singapore. Supplementary external testing on 2 Caucasian cohorts: (3) Australian Eye and Heart Study (AHES) (460 participants with diabetes, cross-sectional) and (4) Northern Ireland Cohort for the Longitudinal Study of Ageing (NICOLA) (265 participants with diabetes, cross-sectional).

RESULTS: In SiDRP validation, area under the curve (AUC) was 0.826(95% CI 0.818-0.833) for image-only, 0.847(0.840-0.854) for RF-only, and 0.866(0.859-0.872) for hybrid. Estimates with SEED were 0.764(0.743-0.785) for image-only, 0.802(0.783-0.822) for RF-only, and 0.828(0.810-0.846) for hybrid. In SMART2D, AUC was 0.726(0.686-0.765) for image-only, 0.701(0.660-0.741) in RF-only, 0.761(0.724-0.797) for hybrid.

DISCUSSION AND CONCLUSION: There is potential for DLA using retinal images as a screening adjunct for DKD among individuals with diabetes. This can value-add to existing DLA systems which diagnose diabetic retinopathy from retinal images, facilitating primary screening for DKD.

Original languageEnglish
JournalJournal of the American Medical Informatics Association
Early online date02 Sept 2023
DOIs
Publication statusEarly online date - 02 Sept 2023

Bibliographical note

© The Author(s) 2023. Published by Oxford University Press on behalf of the American Medical Informatics Association.

Fingerprint

Dive into the research topics of 'Deep learning algorithms to detect diabetic kidney disease from retinal photographs in multiethnic populations with diabetes'. Together they form a unique fingerprint.

Cite this