Addressing Risk Assessment for Patient Safety in Hospitals through Information Extraction in Medical Reports Denys Proux, Frédérique Segond 1 , Solweig Gerbier and Marie Hélène Metzger 2 1 Xerox Research Centre Europe 6,Chemin de Maupertuis, Meylan 38240, France Denys.proux@xrce.xerox.com, Frederique.Segond@xrce.xerox.com 2 Service d‘hygiène, épidémiologie et prévention des Hospices Civils de Lyon Hôpital Henry Gabrielle - Villa Alice, 20 Route de Vourles BP 57, 69 230 Saint-Genis Laval cedex, France solweig.gerbier@chu-lyon.fr, marie-helene.metzger@chu-lyon.fr Abstract: Hospital Acquired Infections (HAI) is a real burden for doctors and risk surveillance experts. The impact on patients’ health and related healthcare cost is very significant and a major concern even for rich countries. Furthermore required data to evaluate the threat is generally not available to experts and that prevents from fast reaction. However, recent advances in Computational Intelligence Tech- niques such as Information Extraction, Risk Patterns Detection in documents and Decision Support Systems allow now to address this problem. Keywords: Hospital Acquired Infections, Natural language Processing, Informa- tion Extraction, Risk Pattern. 1. Introduction Patient’s security is a key issue in hospitals and monitoring adverse events is a preliminary step of a corrective or preventive action. Only a qualitative and quan- titative estimate of observed adverse events in hospital can help in deciding which measures to implement. For example, in France, the incidence of adverse events was estimated [1] to 6.6 per 1000 hospital days in 2004, from which 24.1% were Hospital Acquired Infections (HAI). Please use the following format when citing this chapter: Proux, D., Segond, F., Gerbier, S. and Metzger, M.H., 2008, in IFIP International Federation for Information Processing, Volume 288; Intelligent Information Processing IV; Zhongzhi Shi, E. Mercier-Laurent, D. Leake; (Boston: Springer), pp. 230–239.