To apply a deep learning algorithm for automated, objective, and comprehensive quantification of OCT scans to a large real-world dataset of eyes with neovascular age-related macular degeneration (AMD) and make the raw segmentation output data openly available for further research. Retrospective analysis of OCT images from the Moorfields Eye Hospital AMD Database. A total of 2473 first-treated eyes and 493 second-treated eyes that commenced therapy for neovascular AMD between June 2012 and June 2017. A deep learning algorithm was used to segment all baseline OCT scans. Volumes were calculated for segmented features such as neurosensory retina (NSR), drusen, intraretinal fluid (IRF), subretinal fluid (SRF), subretinal hyperreflective material (SHRM), retinal pigment epithelium (RPE), hyperreflective foci (HRF), fibrovascular pigment epithelium detachment (fvPED), and serous PED (sPED). Analyses included comparisons between first- and second-treated eyes by visual acuity (VA) and race/ethnicity and correlations between volumes. Volumes of segmented features (mm³) and central subfield thickness (CST) (μm). In first-treated eyes, the majority had both IRF and SRF (54.7%). First-treated eyes had greater volumes for all segmented tissues, with the exception of drusen, which was greater in second-treated eyes. In first-treated eyes, older age was associated with lower volumes for RPE, SRF, NSR, and sPED; in second-treated eyes, older age was associated with lower volumes of NSR, RPE, sPED, fvPED, and SRF. Eyes from Black individuals had higher SRF, RPE, and serous PED volumes compared with other ethnic groups. Greater volumes of the majority of features were associated with worse VA. We report the results of large-scale automated quantification of a novel range of baseline features in neovascular AMD. Major differences between first- and second-treated eyes, with increasing age, and between ethnicities are highlighted. In the coming years, enhanced, automated OCT segmentation may assist personalization of real-world care and the detection of novel structure–function correlations. These data will be made publicly available for replication and future investigation by the AMD research community.

Rare eye diseases such as inherited retinal diseases (IRDs) are challenging to diagnose genetically. IRDs are typically monogenic disorders and represent a leading cause of blindness in children and working-age adults worldwide. A growing number are now being targeted in clinical trials, with approved treatments increasingly available. However, access requires a genetic diagnosis to be established sufficiently early. Critically, the timely identification of a genetic cause remains challenging. We demonstrate that a deep learning algorithm, Eye2Gene, trained on a large multimodal imaging dataset of individuals with IRDs (n = 2,451) and externally validated on data provided by five different clinical centres, provides better-than-expert-level top-five accuracy of 83.9% for supporting genetic diagnosis for the 63 most common genetic causes. We demonstrate that Eye2Gene’s next-generation phenotyping can increase diagnostic yield by improving screening for IRDs, phenotype-driven variant prioritization and automatic similarity matching in phenotypic space to identify new genes. Eye2Gene is accessible online (app.eye2gene.com) for research purposes.

To determine the spectrum of glaucoma-associated health care resource utilization among outpatients attending National Health Service (NHS) hospital glaucoma clinics and the costs of managing glaucoma in this setting. Retrospective observational cohort study using electronic medical record data. Patients aged ≥ 18 years attending 5 NHS glaucoma clinics in the United Kingdom (2013‒2018) with ≥ 12 months of continuous electronic medical record data. Deidentified Medisoft Ophthalmology electronic medical record data (January 2013‒December 2018) from 43 742 eligible patients were categorized by year of clinic visit. Extracted information included patient demographics, glaucoma diagnoses, topical glaucoma medication prescription start/stop dates, types/numbers of glaucoma clinic visits, glaucoma investigations (visual acuity, intraocular pressure, visual field, and OCT), and glaucoma procedures received over 12 months after the first ("index") visit of the specified year. Direct glaucoma-related health care costs (clinic visits, investigations, procedures, and ongoing glaucoma medication initiated in the clinic) were estimated from event volumes and unit costs (UK national tariffs) and expressed from the direct-payer perspective. Glaucoma diagnoses and topical glaucoma medication use at the index clinic visit; numbers of glaucoma clinic visits, investigations and procedures; and glaucoma-related health care costs over 12 months postindex. For the 2016 cohort (n = 21 719), the estimated average total cost of NHS-provided glaucoma care over 12 months was £405 per patient (medical staff services £209, glaucoma investigations £126, glaucoma medication £40, glaucoma procedures £26). Among this cohort, 40.8% had ocular hypertension/suspected glaucoma, 70% had 0-to-mild visual field impairment, and 14% had undergone a glaucoma procedure. Over 12 months, patients received (mean) 2.0 glaucoma clinic visits and 1.5 visual field tests, and 7% underwent glaucoma procedure(s). Results were similar for the other years examined. Cost estimates for managing patients with glaucoma in the UK are required for effective service planning. Appreciable proportions of patients managed in NHS glaucoma clinics may be considered at low risk of blindness (glaucoma suspects and those with ocular hypertension with mild visual field loss) and may be more appropriately managed with alternative, more affordable models of care.

Purpose: Neovascular age-related macular degeneration (nAMD) is a major global cause of blindness. Whilst anti-vascular endothelial growth factor (anti-VEGF) treatment is effective, response varies considerably between individuals. Thus, patients face substantial uncertainty regarding their future ability to perform daily tasks. In this study, we evaluate the performance of an automated machine learning (AutoML) model which predicts visual acuity (VA) outcomes in patients receiving treatment for nAMD, in comparison to a manually coded model built using the same dataset. Furthermore, we evaluate model performance across ethnic groups and analyse how the models reach their predictions. Methods: Binary classification models were trained to predict whether patients’ VA would be ‘Above’ or ‘Below’ a score of 70 one year after initiating treatment, measured using the Early Treatment Diabetic Retinopathy Study (ETDRS) chart. The AutoML model was built using the Google Cloud Platform, whilst the bespoke model was trained using an XGBoost framework. Models were compared and analysed using the What-if Tool (WIT), a novel model-agnostic interpretability tool. Results: Our study included 1631 eyes from patients attending Moorfields Eye Hospital. The AutoML model (area under the curve [AUC], 0.849) achieved a highly similar performance to the XGBoost model (AUC, 0.847). Using the WIT, we found that the models over-predicted negative outcomes in Asian patients and performed worse in those with an ethnic category of Other. Baseline VA, age and ethnicity were the most important determinants of model predictions. Partial dependence plot analysis revealed a sigmoidal relationship between baseline VA and the probability of an outcome of ‘Above’. Conclusion: We have described and validated an AutoML-WIT pipeline which enables clinicians with minimal coding skills to match the performance of a state-of-the-art algorithm and obtain explainable predictions.