An integrative ambient agent model for unipolar depression relapse prevention

Abstract

One of the challenges for persons with a history of unipolar depression is to stay healthy throughout their lifetime. In principle, having more severe prior onset cases escalates the risk to fall into a relapse. In this article, first a domain model of the process of depression, recovery and relapse is presented, and second an integrative ambient agent model to support persons from relapse is described. Based on several personal characteristics and a representation of events (i.e., life events or daily hassles) the domain model can simulate whether a human that recovered from a depression will fall into a relapse or recurrence. A number of well-known relations between events and the course of depression are summarized from the literature and it is shown that the domain model exhibits those patterns. The domain model has been mathematically analyzed to find out which stable situations exist. Second, by incorporating this domain model into an ambient agent system, the resulting integrative ambient agent model is able to reason about the state of the human and the effect of possible actions. Several simulation experiments have been conducted to illustrate the functioning of the proposed model in different scenarios. In addition, an automated verification method using Temporal Trace Language (TTL) is used to verify that the ambient agent model satisfies a number of relevant properties. Finally, it is pointed out how this model can be used in depression therapy, supported by an ambient agent.