The accurate prediction and identification of Alzheimer’s disease and Choroidal Neovascularization using Optical Coherence Tomography and Optical Coherence Tomography Angiography images. Advanced methods employed for early prediction and classifying sub types of Alzheimer’s disease and Choroidal Neovascularization, by leveraging a Hierarchical Convolutional Neural Network model from Optical Coherence Tomography and Optical Coherence Tomography Angiography images for Age-related macular degeneration. In Hierarchical Convolutional Neural Network, the U-Net model is used for segmenting the Optical Coherence Tomography and Optical Coherence Tomography Angiography images, and the Convolutional Neural Network-1 model is used for identifying Choroidal Neovascularization, the Convolutional Neural Network-2 model is used for predicting the types of Choroidal Neovascularization as Type-1, Type-2, and Type-3, and Convolutional Neural Network − 3 model is used for predicting the Alzheimer’s disease in Optical Coherence Tomography and Optical Coherence Tomography Angiography images. Each model of Hierarchical Convolutional Neural Network is implemented in Python software, used 65,000 AMED image and the results are verified against the existing methods, and Hierarchical Convolutional Neural Network model’s has superior accuracy 99.36% and reliability in classifying and detecting the Alzheimer’s disease and Choroidal Neovascularization. Type-1 CNVs are the most common, followed by Type-2 and Type-3. The suggested model for CNV types had an accuracy rate of over 99%. The approach significantly advances the early disease detection and diagnostic accuracy by improving the patient outcomes and efficient treatment plans.