Resources and Tools



EU - EN - ES




      es:EXTracción de RElaciones entre Conceptos Médicos en fuentes de información heterogéneas
      eu:Kontzeptu medikoen arteko erlazioen erauzketa askotariko informazio-iturrietatik
      en:Extracting Relations among Medical Concepts from Heteregenous Information Sources

    The overall objective of this project is to address the generation of techniques and tools to allow efficient and intelligent access to the contents of medical documents of multilingual nature such as i) general scientific documents, ii) medical records and iii) general information on the Internet. The project will demonstrate, through a series of use cases, the benefits of the application of language technology in the health sector, using advanced Natural Language Processing techniques such as information retrieval applied to large amounts of resources about medical information on the Internet.

    The main challenge is to address the generation of techniques and tools to allow efficient and reliable access to vast amounts of information which currently are manually accessed by health care professionals. The volume of information that health professionals use in their daily task is enormous and it is growing. We believe that, in addition, the information contained in the web of specialized pages and/or social networks can provide medical content of different types based on the experience of patients. It is important that these professionals have mechanisms to facilitate an "advanced access" to information contained in these millions of documents of heterogeneous nature. By "advanced access" we mean access focusing on the concept and retrieval of the related medical information present in different documents and heterogeneous information sources.

    The project has a multidisciplinary nature and will be addressed through collaboration between research groups expert in information technology and professionals in the health area. This collaboration can help to create synergies between the two parties.

    The groups involved in the project are:

    • UNED Group, with extensive experience in natural language processing, participation in numerous research projects and scientific publications.
    • IXA Group, University of the Basque Country UPV/EHU. Similarly, this group participates in numerous research projects and scientific publications in the area of computational linguistics, including several works on processing medical texts and ontologies.
    • Basurto and Galdakao Hospitals, integrated into the IXA working group, belonging to the Public Health Service. This group is a pioneer in the treatment and implementation of electronic medical records, making it a key partner in this project. They will lend their expertise in the area of detecting adverse effects explicitly or implicitly expressed in medical records (a case use in the project).



Read more IXA