SMT solvers can be used efficiently to search for optimal paths across multiple graphs when optimising for certain resources. In the medical context, these graphs can represent treatment plans for chronic conditions where the optimal paths across all plans under consideration are the ones which minimize adverse drug interactions. The SMT solvers, however, work as a black-box model and there is a need to justify the optimal plans in a human-friendly way. We aim to fulfill this need by proposing explanatory dialogue protocols based on computational argumentation to increase the understanding and trust of humans interacting with the system. The protocols provide supporting reasons for nodes in a path and also allow counter reasons for the nodes not in the graph, highlighting any potential adverse interactions during the dialogue.

No abstract

No abstract

No abstract