The EU-ADR Project: Preliminary Results and Perspective Gianluca TRIFIRO a, b, 1 , Annie FOURRIER-REGLAT c , Miriam C.J.M. STURKENBOOM a , Carlos DÍAZ ACEDO d and Johan VAN DER LEI a , on behalf of the EU-ADR Group a Department of Medical Informatics, Erasmus University Medical Center, Rotterdam, The Netherlands b IRCCS Centro Neurolesi ‘‘Bonino-Pulejo’’, Messina, Italy c Inserm U 657, Pharmacology Department, Bordeaux, France d Fundació IMIM - European Projects Management Office, Barcelona, Spain. Abstract. The EU-ADR project aims to exploit different European electronic healthcare records (EHR) databases for drug safety signal detection. In this paper we describe the project framework and the preliminary results. Methods: As first step we created a ranked list of the events that are deemed to be important in pharmacovigilance as mining on all possible events was considered to unduly increase the number of spurious signals. All the drugs that are potentially associated to these events will be detected via data mining techniques. Data sources are eight 8 databases in four countries (Denmark, Italy, the Netherlands, and the United Kingdom) that are virtually linked through harmonisation of input data followed by local elaboration of input data through custom-built software (Jerboa©). All the identified drug-event associations (signals) will be thereafter biologically substantiated and epidemiologically validated. To date, only Upper gastrointestinal bleeding (UGIB) event has been used to test the ability of the system in signal detection. Results: An initial ranked list comprising 23 adverse events was identified. The top-ranking events were: cutaneous bullous eruptions, acute renal failure, acute myocardial infarction, anaphylactic shock, and rhabdomyolysis. Regarding the UGIB test, a total of 48,016 first-ever episodes were identified. The age-standardized incidence rates of UGIB varied between 40- 100/100,000 person-years depending on country and type of healthcare database. A statistically significant association between use of NSAIDs and UGIB was detected in all of the databases. Conclusion: a dynamic ranked list of 23 adverse drug events judged as important in pharmacovigilance was created to permit focused data mining. Preliminary results on the UGIB event detection demonstrate the feasibility of harmonizing various health care databases in different European countries through a distributed network approach. Keywords: Pharmacovigilance, electronic health records, biomedical knowledge, signal generation, signal substantiation Introduction In pharmacovigilance, a signal is defined by the World Health Organization as information on a possible causal relationship between an adverse event and a drug, 1 Corresponding Author: trifirog@unime.it Detection and Prevention of Adverse Drug Events R. Beuscart et al. (Eds.) IOS Press, 2009 © 2009 The authors and IOS Press. All rights reserved. doi:10.3233/978-1-60750-043-8-43 43