DESIGN: Artificial intelligence (neural network) study.
METHODS: We assessed 1400 OCT scans of patients with neovascular AMD. Fifteen physical features for each eligible OCT, as well as patient age, were used as input data and corresponding recorded visual acuity as the target data to train, validate, and test a supervised neural network. We then applied this network to model the impact on acuity of defined OCT changes in subretinal fluid, subretinal hyperreflective material, and loss of external limiting membrane (ELM) integrity.
RESULTS: A total of 1210 eligible OCT scans were analyzed, resulting in 1210 data points, which were each 16-dimensional. A 10-layer feed-forward neural network with 1 hidden layer of 10 neurons was trained to predict acuity and demonstrated a root mean square error of 8.2 letters for predicted compared to actual visual acuity and a mean regression coefficient of 0.85. A virtual model using this network demonstrated the relationship of visual acuity to specific, programmed changes in OCT characteristics. When ELM is intact, there is a shallow decline in acuity with increasing subretinal fluid but a much steeper decline with equivalent increasing subretinal hyperreflective material. When ELM is not intact, all visual acuities are reduced. Increasing subretinal hyperreflective material or subretinal fluid in this circumstance reduces vision further still, but with a smaller gradient than when ELM is intact.
CONCLUSIONS: The supervised machine learning neural network developed is able to generate an estimated visual acuity value from OCT images in a population of patients with AMD. These findings should be of clinical and research interest in macular degeneration, for example in estimating visual prognosis or highlighting the importance of developing treatments targeting more visually destructive pathologies.
METHODS: Non-interventional multicenter historical cohort study of intravitreal ranibizumab use for nAMD in routine clinical practice between April 2010 and April 2013. Eligible patients were diagnosed with nAMD, received at least one intravitreal ranibizumab injection during the study period, and had been observed for a minimum of 1 year (up to 3 years). Reimbursement scenarios were defined as self-paid, partially-reimbursed, and fully-reimbursed.
RESULTS: More than three-fourths (n = 2521) of the analysis population was partially-reimbursed for ranibizumab, while 16.4% (n = 532) was fully-reimbursed, and 5.8% was self-paid (n = 188). The average annual ranibizumab injection frequency was 4.1 injections in the partially-reimbursed, 4.7 in the fully-reimbursed and 2.6 in the self-paid populations. The average clinical monitoring frequency was estimated to be 6.7 visits/year, with similar frequencies observed across reimbursement categories. On average, patients experienced VA reduction of -0.7 letters and a decrease in CRT of -44.4 μm. The greatest mean CRT change was observed in the self-paid group, with -92.6 μm.
CONCLUSIONS: UNCOVER included a large, heterogeneous ranibizumab-treated nAMD population in real-world settings. Patients in all reimbursement scenarios attained vision stability on average, indicating control of disease activity.