Natural Language Processing to detect Risk Patterns related to Hospital Acquired Infections
Denys Proux, Pierre Marchal, Frederique Segond, Ivan Kergourlay, Stéfan Damoni, Suzanne Pereira, Quentin Gicquel, Marie Hélène Metzger
Hospital Acquired Infections (HAI) has a major impact on public health and on related healthcare cost. HAI experts are fighting against this issue but they are struggling to access data. Information systems in hospitals are complex, highly heterogeneous, and generally not convenient to perform a real time surveillance. Developing a tool able to parse patient records in order to automatically detect signs of a possible issue would be a tremendous help for these experts and could allow them to react more rapidly and as a consequence to reduce the impact of such infections. Recent advances in Computational Intelligence Techniques such as Information Extraction, Risk Patterns Detection in documents and Decision Support Systems now allow to develop such systems.
RANLP 2009 (International Conference on Recent Advances in Natural Language Processing) Borovets, Bulgaria, 14-16 September, 2009