Automated Machine Learning Classification of Optical Coherence Tomography Images of Retinal Conditions Using Google Cloud Vertex AI

Purpose: Automated machine learning (AutoML) is an artificial intelligence (AI) tool that streamlines image recognition model development. This study evaluates the diagnostic performance of Google VertexAI AutoML in differentiating age-related macular degeneration (AMD), diabetic macular edema (DME), epiretinal membrane (ERM), retinal vein occlusion (RVO), and healthy controls using optical coherence tomography (OCT) images. Methods: A publicly available, validated OCT dataset of 1965 de-identified images from 759 patients was used. Images were labeled and uploaded to VertexAI. A single-label classification model was trained, validated, and tested using an 80%-10%-10% split. Diagnostic metrics included area under the precision-recall curve (AUPRC), sensitivity, specificity, and positive and negative predictive value (PPV, NPV). A sub-analysis evaluated neovascular versus non-neovascular AMD. Results: The AutoML model achieved high accuracy (AUPRC = 0.991), with sensitivity, specificity, and PPV of 95.9%, 96.9%, and 95.9%, respectively. AMD classification performed best (AUPRC = 0.999, precision = 98.4%, recall = 99.2%). ERM (AUPRC = 0.978, precision = 92.9%, recall = 86.7%) and DME (AUPRC = 0.895, precision = 81.3%, recall = 86.7%) followed. RVO recall was 80% despite 100% precision. Neovascular AMD outperformed non-neovascular AMD (AUPRC = 0.963 vs. 0.915). Conclusion: Our AutoML model accurately classifies OCT images of retinal conditions, demonstrating performance comparable or superior to traditional ML methods. Its user-friendly design supports scalable AI-driven clinical integration.