Automated Algorithm Predicts Retinopathy Progression in Diabetic Patients
According to a study published in JAMA Ophthalmology, researchers from the Chinese University of Hong Kong, led by Dawei Yang, Ph.D., investigated the prognostic value of an automated binary diabetic macular ischemia (DMI) algorithm using optical coherence tomography angiography (OCTA) images in patients with diabetes.
The cohort study aimed to determine if the algorithm could predict diabetic retinopathy (DR) progression, diabetic macular edema (DME) development, and deterioration of visual acuity (VA). They utilized a deep learning algorithm to assess DMI using OCTA images of the superficial capillary plexus and deep capillary plexus.
The study included 321 eyes from 178 patients, and the findings revealed that during a median follow-up period of 50.41 months, 32.71% of eyes experienced diabetic retinopathy (DR) progression, 10.28% developed diabetic macular edema (DME), and 21.18% had a deterioration of visual acuity (VA).
The presence of superficial capillary plexus-DMI and deep capillary plexus-DMI at baseline showed a significant association with DR progression (hazard ratios of 2.69 and 3.21, respectively). Additionally, the presence of deep capillary plexus-DMI was linked to the development of DME and VA deterioration (hazard ratios of 4.60 and 2.12, respectively) after adjusting for various confounding variables.
"Our findings might provide insights for incorporating both OCTA and artificial intelligence to early detect DMI and further enhance DR management," the authors write.
Reference
Dawei Yang et al, Assessment of Parafoveal Diabetic Macular Ischemia on Optical Coherence Tomography Angiography Images to Predict Diabetic Retinal Disease Progression and Visual Acuity Deterioration, JAMA Ophthalmology (2023). DOI: 10.1001/jamaophthalmol.2023.1821
Amir H. Kashani et al, Optical Coherence Tomography Angiography, Artificial Intelligence, and the Missing Capillaries, JAMA Ophthalmology (2023). DOI: 10.1001/jamaophthalmol.2023.1829
