Clinical Trials For Age-related Macular Degeneration Research Articles

Towards the validation of quantitative contrast sensitivity as a clinical endpoint: correlations with vision-related quality of life in bilateral AMD

AimTo investigate if active learning of contrast sensitivity (CS) in bilateral age-related macular degeneration (AMD) correlates better than visual acuity (VA) with vision-related quality of life (VRQoL) using factor analysis-calibrated...

Genome-wide association study-based deep learning for survival prediction.

Informative and accurate survival prediction with individualized dynamic risk profiles over time is critical for personalized disease prevention and clinical management. The massive genetic data, such as SNPs from genome-wide association studies (GWAS), together with well-characterized time-to-event phenotypes provide unprecedented opportunities for developing effective survival prediction models. Recent advances in deep learning have made extraordinary achievements in establishing powerful prediction models in the biomedical field. However, the applications of deep learning approaches in survival prediction are limited, especially with utilizing the wealthy GWAS data. Motivated by developing powerful prediction models for the progression of an eye disease, age-related macular degeneration (AMD), we develop and implement a multilayer deep neural network (DNN) survival model to effectively extract features and make accurate and interpretable predictions. Various simulation studies are performed to compare the prediction performance of the DNN survival model with several other machine learning-based survival models. Finally, using the GWAS data from two large-scale randomized clinical trials in AMD with over 7800 observations, we show that the DNN survival model not only outperforms several existing survival prediction models in terms of prediction accuracy (eg, c-index =0.76), but also successfully detects clinically meaningful risk subgroups by effectively learning the complex structures among genetic variants. Moreover, we obtain a subject-specific importance measure for each predictor from the DNN survival model, which provides valuable insights into the personalized early prevention and clinical management for this disease.

Predicting risk of late age-related macular degeneration using deep learning

By 2040, age-related macular degeneration (AMD) will affect ~288 million people worldwide. Identifying individuals at high risk of progression to late AMD, the sight-threatening stage, is critical for clinical actions, including medical interventions and timely monitoring. Although deep learning has shown promise in diagnosing/screening AMD using color fundus photographs, it remains difficult to predict individuals’ risks of late AMD accurately. For both tasks, these initial deep learning attempts have remained largely unvalidated in independent cohorts. Here, we demonstrate how deep learning and survival analysis can predict the probability of progression to late AMD using 3298 participants (over 80,000 images) from the Age-Related Eye Disease Studies AREDS and AREDS2, the largest longitudinal clinical trials in AMD. When validated against an independent test data set of 601 participants, our model achieved high prognostic accuracy (5-year C-statistic 86.4 (95% confidence interval 86.2–86.6)) that substantially exceeded that of retinal specialists using two existing clinical standards (81.3 (81.1–81.5) and 82.0 (81.8–82.3), respectively). Interestingly, our approach offers additional strengths over the existing clinical standards in AMD prognosis (e.g., risk ascertainment above 50%) and is likely to be highly generalizable, given the breadth of training data from 82 US retinal specialty clinics. Indeed, during external validation through training on AREDS and testing on AREDS2 as an independent cohort, our model retained substantially higher prognostic accuracy than existing clinical standards. These results highlight the potential of deep learning systems to enhance clinical decision-making in AMD patients.

Evaluation of Two Systems for Fundus-Controlled Scotopic and Mesopic Perimetry in Eye with Age-Related Macular Degeneration.

PurposeThe purpose of this study was to evaluate and compare the MP-1S (Nidek Technologies, Padova, Italy) and the S-MAIA (CenterVue, Padova, Italy) for mesopic and scotopic fundus-controlled perimetry (FCP) in age-related macular degeneration (AMD).MethodsEleven eyes from 11 patients underwent mesopic and, after 30 minutes of dark adaptation, scotopic (MP-1S: Goldmann V, 200 ms, background luminance 0.0032 cd/m2; S-MAIA: Goldman III, 200 ms, background luminance <0.0001 cd/m2) FCP. For the S-MAIA device, cyan (505 nm) and red (627 nm) scotopic FCP were performed. For both devices, a grid of 56 stimulus points covering 16° of the central macula was used. Examination time, fixation stability, and threshold values were analyzed.ResultsThe upper end of the dynamic range (≤4 dB of lowest threshold) was frequently reached by the MP-1S for mesopic testing (median 34 of 56 stimuli), while threshold values within the lower 4 dB of the dynamic range were occasionally found with the S-MAIA for scotopic testing (median 3 for cyan, median 2 for red). After correction of the stimulus intensity for the S-MAIA results, the median difference for all stimuli between both devices for mesopic testing was −2.0 dB (interquartile range [−4;0], range –14 to 6).ConclusionsThe results indicate that robust testing of mesopic and scotopic function is feasible with both devices in patients with AMD, although both devices are susceptible to floor and ceiling effects.Translational RelevanceThe interpretation and particularly the comparison of both scotopic and mesopic FCP results between the MP-1S and the S-MAIA in AMD eyes need to consider variable susceptibility of floor and ceiling effects. Further software updates are desirable as FCP captures visual functional loss that is not noted with best-corrected central visual acuity and is important for clinical trials in AMD.

Management of Neovascular Age-related Macular Degeneration: A Review on Landmark Randomized Controlled Trials.

In the last decade, a number of prospective clinical trials with carefully designed study protocols have been conducted for the treatment of neovascular age-related macular degeneration (AMD). These landmark clinical trials such as ANCHOR and MARINA and, more recently, the Comparison of AMD Treatment Trials and VIEW studies have revolutionized the management of neovascular AMD. While AMD continues to remain a leading cause of severe visual loss worldwide, advances in pharmacotherapeutics have led to substantial improvements in the outcome of these patients. The introduction of anti-vascular endothelial growth factor agents has resulted in improvement of visual outcomes and has had a positive impact on the quality of life among elderly population. While the contemporary management of neovascular AMD has been successful in tremendously reducing the visual morbidity, the financial burden of therapy has increased exponentially. To overcome these challenges, newer pharmacologic agents are evaluated for their efficacy and safety in AMD. Ground-breaking advances in bench to bedside research have led to discovery of new pathways that appear to be viable targets for preventing visual loss in AMD. In this review, study designs and results of landmark clinical trials in AMD from the past decade have been summarized.

Test–Retest Variability of Reading Performance Metrics Using MNREAD in Patients with Age-Related Macular Degeneration

To determine the test-retest variability of reading ability using the MNREAD charts in patients with stable age-related macular degeneration (AMD). In this prospective study, reading ability was measured at two visits in 124 nontreated eyes of 124 patients with AMD, who were enrolled in an ongoing clinical trial using a standardized MNREAD protocol. Only patients with stable AMD who could perform the reading test at 40 cm at both visits were included in the analysis. Different scoring rules were applied to calculate critical print size and maximum reading speed. Data from the 59 patients with a mean (SD) age of 78 (7.6) years who met the study criteria were analyzed at a mean (SD) interval of 43 (6) days between measurements. The 95% coefficient of repeatability (CR) was 0.30 logMAR for reading acuity. The CR for critical print size and maximum reading speed varied depending on the analysis method applied. This is a report of estimates of the intersession test-retest variability of reading performance metrics in patients with stable AMD. The results are helpful both in defining end points in clinical trials for AMD and in distinguishing clinical change from measurement variability in clinical practice.

PUBLICATION RATES OF REGISTERED CLINICAL TRIALS IN MACULAR DEGENERATION

The purpose of this study was to evaluate the rate of publication of registered clinical trials concerning age-related macular degeneration (AMD). The National Institutes of Health's ClinicalTrials.gov registry was searched to identify all trials concerning AMD. Trials that were actively recruiting, not interventional, terminated, or did not actually concern AMD were excluded. Only trials completed 2 or more years before this analysis was started were included, to allow for adequate time to pass before publication was expected to occur. PubMed.gov was then searched to evaluate the publication status of each study. Three hundred and eight-six studies were initially identified, and 64 (16.5%) were included in the final evaluation. Three hundred and twenty-one studies were not included for the following reasons: 171 did not involve AMD or were not interventional; 141 were not completed by January 1, 2007; and 9 trials were terminated. Of the 64 trials included, 35 (54%) were published. Early phase trials were published at a lower rate (41.6% [15/36]) than late-phase trials (71.4% [20/28]). This difference was statistically significant (P = 0.02). The sponsor type, date of study initiation, and location did not influence the publication rate. Using broad study parameters, 54% of registered interventional clinical trials in AMD have been reported in the peer-reviewed literature.

Current Treatment of Age-Related Macular Degeneration

To review proved and experimental treatments for exudative and nonexudative complications of age-related macular degeneration (AMD), to consider the impact of current therapy on the structure of future clinical trials, and to consider the role of improved diagnostic imaging techniques on the effectiveness of current therapy as well as the structure of future clinical trials in AMD patients. Defining the cell biology of choroidal new vessel (CNV) formation and geographic atrophy will lead to identification of different biochemical pathways that are the target of AMD treatment. Many treatments and treatment combinations are under study for AMD, but all work through a finite number of pathways. Currently, the most effective proved therapy for AMD-associated CNVs is administered by repeated intravitreal injection of agents that inhibit vascular endothelial growth factor, e.g., ranibizumab. Improved drug delivery will enhance patient satisfaction and possibly will enhance the effectiveness and reduce the risk of current pharmacotherapy for AMD-associated CNVs. Combination therapy (e.g., verteporfin-photodynamic therapy + ranibizumab) appears to reduce the risk and enhance the effectiveness of CNV treatment compared with monotherapy with currently available agents. Improved noninvasive diagnostic imaging may lead to better visual outcomes with existing therapeutic modalities. Improved imaging also may alter favorably the design of future clinical trials for AMD-associated CNVs and thus reduce cost and increase the diversity of sight-saving treatments. Delineation of the biochemical basis for CNV formation has led to development of pathway-based pharmacotherapy for AMD patients. Areas of investigation that will advance the field further include combination therapy, improved drug delivery, and improved noninvasive, high-resolution diagnostic imaging. The logistics of future clinical trials will be complicated by the need for an active treatment control group, more stringent definition of successful treatment, and the increased numbers of patients required for combination therapy studies.