Updated: Feb 1, 97
MENELAS

Project Code:   A2023 Project value:   3411 KECU EC contribution:   2080 KECU No of partners:   12 No of countries:   4 Duration:   36 months

Contact: Pierre Zweigenbaum DIAM - SIM/AP-HP 91, bd de l'Hopital F-75634 Paris Cedex 13, France Tel.: +33 01 45 83 67 28 Fax: +33 01 45 86 80 68 / 01 45 86 56 85 E-mail: pz@biomath.jussieu.fr url : http://www.biomath.jussieu.fr/~pz/Menelas/

Overview

Purpose and objectives

The basis of the project is the design and implementation of a pilot system able to access medical reports through natural languages. This system is able to analyse the contents of medical reports and to store them in a database as a set of conceptual structures; these structures, which may be seen as the core representation of the narrative, may then be consulted to retrieve any specific information contained in the PDS. An index is also produced according to the International Classification of Diseases (ICD-9-CM). Reliance on international nomenclatures will allow information to be exchanged between PDSs written in different European languages. In the project, the partners have addressed the processing of French, English and Dutch PDSs.

Results

A set of components, tools, knowledge bases and methods has also been produced by the project. They include: Language analysis components for French, English and Dutch; an Index generator component parameterised for ICD-9-CM; Information retrieval components; Linguistic knowledge bases; Medical knowledge bases; A methodology for developing ontologies; and System administrator tools.

A first reuse of the MENELAS prototype is taking place at Lille, in Northern France, within the framework of the AIM integration project ISAR . From an experimental point of view the objective is to study the transferability of the MENELAS knowledge bases to another hospital site, and the integration of the system in a different environment. Additionally, a new interface to the system was developed using WWW technology.

A core of project partners, in collaboration with partners from other consortia of both the health care and the language engineering Telematics Community Programmes, have jointly launched a feasibility study, including a market analysis, which has identified how MENELAS-like systems can be integrated into the electronic document processing flow of hospitals. The analysis of user needs, performed by project DOME in hospitals of four European countries, shows that there is a demand for advanced services such as MENELAS-style natural language processing tools can provide, and which help in the daily use and management of the health care record. It has also stressed the importance of integrating natural language processing technology in the context of a hypermedia view of the patient record.

List of Deliverables

Year 1