Human-in-the-loop learning (HITL) allows more accurate models to be trained by augmenting machine learning and deep learning approaches with human input. The goal of this project is twofold: (1) to expand HITL into explanation-based learning by using explainable AI techniques for user interaction to improve model performance, transparency, and trust and (2) to explore novel approaches for the applications of HITL in the important area of the early diagnosis of Alzheimer’s disease.