Event Calculus Agent Minds Applied to Diabetes Monitoring

Abstract

The increasing incidence of chronic diseases is a major challenge for the healthcare sector. Personal Health Systems (PHSs) address the self-management of chronic diseases, by decentralizing the health monitoring outside hospitalized environments. Rule based agents allow bringing domain experts’ knowledge into PHSs. However, agents must meet the requirements of real monitoring scenarios, characterized by massive streams of events. Hence, with the aim to monitor the health status of diabetic patients, two logic-based agent minds for an agent-oriented PHS are presented. One agent mind is based on the standard version of jREC, a Prolog-based implementation of Cached Event Calculus, while the other is a customization of the standard jREC mind that exploits an event-indexing technique. Both of them are as well integrated into MAGPIE, a Java agent platform. The paper then compares and analyzes the performances of the proposed agent minds, by computing the time needed to trigger different type of alerts, when the number of recorded events (e.g. values of physiological parameters) increases. The results show that the customized jREC mind performs much better when an high number of events need to be checked, making its use advisable in monitoring scenarios.