Artificial intelligence-based predictions in neovascular age-related macular degeneration

Abstract

Purpose of review Predicting treatment response and optimizing treatment regimen in patients with neovascular age-related macular degeneration (nAMD) remains challenging. Artificial intelligence-based tools have the potential to increase confidence in clinical development of new therapeutics, facilitate individual prognostic predictions, and ultimately inform treatment decisions in clinical practice. Recent findings To date, most advances in applying artificial intelligence to nAMD have focused on facilitating image analysis, particularly for automated segmentation, extraction, and quantification of imaging-based features from optical coherence tomography (OCT) images. No studies in our literature search evaluated whether artificial intelligence could predict the treatment regimen required for an optimal visual response for an individual patient. Challenges identified for developing artificial intelligence-based models for nAMD include the limited number of large datasets with high-quality OCT data, limiting the patient populations included in model development; lack of counterfactual data to inform how individual patients may have fared with an alternative treatment strategy; and absence of OCT data standards, impairing the development of models usable across devices. Summary Artificial intelligence has the potential to enable powerful prognostic tools for a complex nAMD treatment landscape; however, additional work remains before these tools are applicable to informing treatment decisions for nAMD in clinical practice.

Latest Development on Genetics of Common Retinal Diseases

“…131 However, responses to treatment have not been reported. 132 AI investigations on OCT images and fundus photos of retinal diseases have advanced phenotyping and refined structural features including minute temporal and microvasculature changes. Attempts have also been to correlate to genotypes.…”

“…Fundus photos can be analyzed by deep learning algorithms with deep convolution and network architectures to predict disease severity130 and differentiate a multitude of retinal complications 131. However, responses to treatment have not been reported 132…”

Clinical and Imaging Biomarkers Associated with Outer Retinal Atrophy Onset in Exudative Age-Related Macular Degeneration: A Real-Word Prospective Study

“…More recently, quantitative optical coherence tomography angiography (OCTA) has also provided promising metrics for determining MNV severity and for stratifying patients in subgroups by different morpho-functional outcome [ 9 – 12 ]. All these parameters have been employed in different settings to assess the risk of AMD stage progression, MNV or geographic atrophy onset, and response to treatments, and also involving artificial intelligence-based approaches [ 6 – 8 , 13 – 16 ]. However, a major unmet need remains the identification of the most relevant imaging metrics to determine the morphological and functional outcome of neovascular AMD.…”

Predicting Systemic Health Features from Retinal Fundus Images Using Transfer-Learning-Based Artificial Intelligence Models

“…Using standalone, high resolution digital fundus and OCT photographs, artificial intelligence models have demonstrated the ability to diagnose a variety of retinal and ophthalmic diseases [ 5 ], including diabetic retinopathy [ 6 , 7 , 8 , 9 , 10 , 11 ], retinopathy of prematurity [ 12 , 13 ], age-related macular degeneration features [ 14 , 15 , 16 , 17 , 18 ], glaucoma [ 19 ], and macular telangiectasia [ 20 ]. Features of retinal disease such as retinal detachment and retinal vein occlusion are identifiable as well [ 21 , 22 ].…”