Explainable and Contextual Preferences based Decision Making with Assumption-based Argumentation for Diagnostics and Prognostics of Alzheimer's Disease

We present an argumentation-based approach to decision making that can support context-based defeasible preferences and offer dialogical explanations for the decisions made. The proposed approach makes and explains a decision as follows: (1) construct a Contextual Preference Decision Framework (CPDF) to model the problem, (2) use Assumption-based Argumentation as a sound and complete computational mechanism for identifying most-contextual-preferred decisions in the CPDF, and (3) construct explaining dialogues to provide dialogical explanations for identified decisions. We have implemented our approach for two tasks, diagnostics and prognostics of Alzheimer's Disease (AD), and evaluated the performance of our models on the two tasks with real-world datasets.