EN FR
EN FR


Section: Application Domains

Medicine

Participants : Aleksey Buzmakov, Adrien Coulet, Nicolas Jay, Jean Lieber, Amedeo Napoli, Matthieu Osmuk, Chedy Raïssi, Yannick Toussaint, Mickaël Zehren.

Keywords:

knowledge representation, description logics, classification-based reasoning, case-based reasoning, semantic web, formal concept analysis, sequence mining, text mining

We are working on several applications in medicine, mainly in knowledge management and analysis of patient trajectories as sequences. In the first case, the Kasimir research project is about decision support and knowledge management for the treatment of cancer. This is a multidisciplinary research project in which researchers in computer science (Orpailleur) and experts in oncology are participating. For a given cancer localization, a treatment is based on a protocol, which is applied in 70% of the cases and provides a treatment. The 30% remaining cases are “out of the protocol”, e.g. contraindication, treatment impossibility, etc. and the protocol should be adapted, based on discussions among specialists. This adaptation process is modeled in Kasimir thanks to CBR, where the semantic Web technologies are used and adapted in the Kasimir project for several years.

Another work is in concern with the analysis of patient trajectories, i.e. the “path” of a patient during illness (chronic illnesses and cancer), considered as sequences. It is important to understand these sequence data and temporal data mining methods are good candidate tools for that. However, these methods should be adapted for addressing the complex nature of medical events. Thus, there is an ongoing work on the analysis of trajectories with different levels of granularity and w.r.t. external domain ontologies. In addition, it is also important to be able to compare and classify trajectories according to their content. This is why there is also a work on the definition of a similarity measure able to take into account the complex nature of trajectories and that can be efficiently implemented for allowing quick and reliable classifications.