Project : acacia
Section: Contracts and Grants with Industry
Ligne de Vie
The ACI Ligne de Vie project in collaboration with the SARL Nautilus and SPIM (Service de Santé Publique et d'Informatique médicale de la Faculté de Médecine Broussais-Hôtel Dieu) aims at building a knowledge management tool for a health care network, so as to ensure continuity of healthcares and co-operative work in such a health care network. The Acacia team had the following contributions :
State of the art
We made an analysis of the needs in a health care network by relying on literature and discussions with medical actors (a doctor of Lenval Hospital and a nurse). We also made a state of the art on medical ontologies.
Extensions of Nautilus ontology
The Nautilus medical ontology is in fact a database and currently contains a nomenclature (the lexicon). The lexicon terms are connected with relations such as "is a", "is situated on" and "is measured by". In addition to the medical terms already present in Nautilus ontology, we extended this ontology with concepts useful for healthcare networks (for example, concepts on various types of network, on actors, on documents) and we linked them to the other concepts already existing. This extension partially relied on the analysis of the candidate terms extracted by a linguistic tool applied on a corpus of texts on healthcare networks.
In order to rely on a semantic Web standard, we translated the Nautilus Ontology from the database format into RDF. We wrote a program in Java which can take the files of Nautilus and transform them into a RDF code .
Construction of (possibly multi-viewpoints) annotations
We studied the various possibilities to conceptualize the notion of point of view: for the ontology's developer, for the patient's dossier developer and for the user. We studied how to build a base of annotations on the documents associated with the patient's life line: these annotations will enable for example to specify the type of a document, as well as medical comments, with various levels of confidentiality and possibly according to various points of focus and view angles, etc. We showed how to represent these annotations in RDF and how to use them with CORESE to get information relevant for healthcare networks.
Specifications and implementation of Virtual Staff
We have proposed a first specification of the future collaborative tool "Virtual Staff". This tool should be able to represent diagnotic and therapeutic assumptions with a conceptual graph using the vocabulary defined in Nautilus ontology. We study how such graphs can be represented in the SOAP model (Subjective, Objective, Assessment, Plan) used by the medical community and in the QOC model (Option, Question, Criteria) used in CSCW community. Presently, we are programming the Virtual Staff with Java language.