There has been increasing interest in devising lightweight classifiers of Alzheimer's Disease (AD) as an initial screening for this condition because although existing assessments achieve high accuracies, they tend to be either resource-intensive and time-consuming (e.g., specialized neuroimaging and detailed cognitive assessments), or they are lightweight cognitive screening tools that are not sensitive enough to detect AD or other mild cognitive impairments that can develop into AD. Existing research has shown the potential of classifying AD from eye-tracking (ET) data with classifiers that rely on task-specific engineered features. In this talk, I will discuss how I investigated whether we can improve on existing results by using a Deep Learning classifier trained end-to-end on raw ET data. The classifier (VTNet) uses a GRU and a CNN in parallel to leverage both visual (V) and temporal (T) representations of ET data and was previously used to detect user confusion while processing visual displays. A main challenge in applying VTNet to our target AD classification task is that the available ET data sequences are much longer than those used in the previous confusion detection task, pushing the limits of what is manageable by LSTM-based models. Hence, I will discuss how I addressed this challenge, which led to VTNet outperforming the state-of-the-art approaches in AD classification, providing encouraging evidence on the generality of this model to make predictions from ET data.