Automated large-scale prediction of exudative AMD progression using machine-read OCT biomarkers

Abstract

Age-related Macular Degeneration (AMD) is a major cause of irreversible vision loss in individuals over 55 years old in the United States. One of the late-stage manifestations of AMD, and a major cause of vision loss, is the development of exudative macular neovascularization (MNV). Optical Coherence Tomography (OCT) is the gold standard to identify fluid at different levels within the retina. The presence of fluid is considered the hallmark to define the presence of disease activity. Anti-vascular growth factor (anti-VEGF) injections can be used to treat exudative MNV. However, given the limitations of anti-VEGF treatment, as burdensome need for frequent visits and repeated injections to sustain efficacy, limited durability of the treatment, poor or no response, there is a great interest in detecting early biomarkers associated with a higher risk for AMD progression to exudative forms in order to optimize the design of early intervention clinical trials. The annotation of structural biomarkers on optical coherence tomography (OCT) B-scans is a laborious, complex and time-consuming process, and discrepancies between human graders can introduce variability into this assessment. To address this issue, a deep-learning model (SLIVER-net) was proposed, which could identify AMD biomarkers on structural OCT volumes with high precision and without human supervision. However, the validation was performed on a small dataset, and the true predictive power of these detected biomarkers in the context of a large cohort has not been evaluated. In this retrospective cohort study, we perform the largest-scale validation of these biomarkers to date. We also assess how these features combined with other EHR data (demographics, comorbidities, etc) affect and/or improve the prediction performance relative to known factors. Our hypothesis is that these biomarkers can be identified by a machine learning algorithm without human supervision, in a way that they preserve their predictive nature. The way we test this hypothesis is by building several machine learning models utilizing these machine-read biomarkers and assessing their added predictive power. We found that not only can we show that the machine-read OCT B-scan biomarkers are predictive of AMD progression, we also observe that our proposed combined OCT and EHR data-based algorithm outperforms the state-of-the-art solution in clinically relevant metrics and provides actionable information which has the potential to improve patient care. In addition, it provides a framework for automated large-scale processing of OCT volumes, making it possible to analyze vast archives without human supervision.

Fig 1. Exudative AMD prediction performance.

Left: Areas Under the Receiver Operating Characteristic (ROC) curve. Right: Areas Under the Precision-Recall (PR) curve. Each bar represents the performance utilizing a different set of features (see legend). Error lines represent the 95% confidence intervals, computed using bootstrapping.

Fig 2. Prediction of exudative AMD Conversion by the 2-year model, evaluated at different time frames.

Left. Area under the ROC curve (AUROC) as a function of prediction time frame. Right. Area under the Precision-Recall curve (AUPRC) as a function of prediction time frame. 95% Confidence intervals were computed using bootstrapping.

Fig 3. Model weights for all features in the fitted combined model.

Black error bars indicate standard deviation of values obtained by fitting the model to bootstrapped subsets of the cohort.

Fig 4. Automated diagnosis of exudative AMD. Curves correspond to models trained on different feature sets (see legend).

Left. Receiver Operating Characteristics (ROC). Right. Precision-Recall curve (PRC). 95% Confidence intervals were computed using bootstrapping. Baseline model utilizes EHR-derived features and risk factors, the biomarker model includes machine-read OCT biomarkers too.