A Peer to Peer Agent Coordination Framework for IHE based Cross-Community Health Record Exchange Visara Urovi University of Applied Sciences Western Switzerland Sierre, Switzerland visara.urovi@hevs.ch Alex C. Olivieri University of Applied Sciences Western Switzerland Sierre, Switzerland alex.olivieri@students.hevs.ch Stefano Bromuri University of Applied Sciences Western Switzerland Sierre, Switzerland stefano.bromuri@hevs.ch Nicoletta Fornara Università della Svizzera italiana Lugano, Switzerland nicoletta.fornara@usi.ch Michael I. Schumacher University of Applied Sciences Western Switzerland Sierre, Switzerland michael.schumacher@hevs.ch ABSTRACT This paper presents a Peer to Peer (P2P) agent coordination framework for the exchange of Electronic Health Records (EHR) between health organisations that comply with the existing interoperability standards as proposed by the Inte- grating Healthcare Enterprise (IHE). Every health organi- sation represents a community in a P2P network and uses a set of autonomous agents and a set of distributed coordina- tion rules to coordinate the agents in the search of specific health records. To model the interactions among commu- nities, the framework uses the tuple centre agent commu- nication model and semantic web technologies. In order to illustrate the scalability of our approach, we evaluate the proposed solution in distributed settings. Categories and Subject Descriptors H.4 [Information Systems Applications]: Miscellaneous General Terms Design, Experimentation Keywords Document exchange, EHR, IHE, Semantic Interoperability, Coordination, TuCSoN, OWL. 1. INTRODUCTION Electronic Health Records (EHRs) refer to the electronic collection of health information data about individual pa- tients [13]. The advantage of EHRs is that information can Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. To copy otherwise, to republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. SAC’13 March 18-22, 2013, Coimbra, Portugal. Copyright 2013 ACM 978-1-4503-1656-9/13/03 ...$10.00. be quickly transferred and linked to best-practice guidelines to provide decision support [12]. EHR based systems often operate in a closed environment where patient’s EHRs can be exchanged only within one organisation. As the focus of health care delivery shifts from specialist centers to com- munity settings [7], new research approaches are focusing on the integration of such records across the institutional boundaries [26]. Integrating the Healthcare Enterprise (IHE) 1 is an initia- tive focusing on integration of healthcare information sys- tems. IHE makes a major contribution to integration of these systems and enjoys high acceptance due to its practi- cal complement to existing standards such as HL7 CDA 2 ,a standard supporting message-based information exchange of medical data. The significance of the IHE profiles stands on the fact that they are constantly checked against practical experiences and are continuously adapted [26]. Despite this, IHE lacks features to handle dynamic scenarios where care- givers can dynamically connect and exchange data [17], and mechanisms on how patient’s data are found and exchanged are yet to be defined. To address these problems, a system is needed where up- to-date patient’s health records can be shared without prior knowledge of the health organisations that produced the data. In particular, semantic description of content has been recognised as a powerful tool for data sharing [14], that, combined with agent-based computing, can contribute to automate the collection and processing of patient’s EHRs. Agent-based systems can perform distributed communica- tion and reason with semantic knowledge thus enabling EHR sharing between such heterogeneous systems. Furthermore, agent coordination models, such as tuple centres [23], that focus on decoupling the interaction amongst the actors, can contribute on making the different health actors more in- teroperable. On top of coordination models, a Peer to Peer (P2P) [2] solution can link the heterogeneous health organ- isation’s systems as peers, allowing them to interact on top of existing network configurations and remove any central dependency for sharing patient EHR. P2P networks have 1 http://www.ihe.net 2 http://www.hl7.org