Archive | BioInfoMed’2022 ⬛ Prof. Guy De Tré: “Efficiently Handling Textual Data in Medical Applications: A Novel Approach”

Abstract

A considerable part of medical information is available as textual data. This textual data can have different manifestations including medical reports, prescriptions, emails, scientific publications, spreadsheet data, patient enquiries, and so on. Medical decision making and data analysis could benefit enormously if the right data, independent of its format, would be available for the decision maker at the right time. Conventional information management mainly focusses on structured data that are stored in relational databases. Efficiently integrating and including textual data in such systems is challenging because of the lack of a fixed common structure and the complexity of written language. In this presentation we will introduce a novel approach to handle and include medical textual data in decision making. This approach avoids information loss, efficiently copes with context and provides a common meta-level structure, which is based on Who-What-When-Where (4W) component identification. This proposed model supports SQL-based querying, exploration, integration, analysis and summarization of large heterogeneous medical data collections. Furthermore, open challenges related to the handling of data imperfections and data veracity are illustrated and perspectives for further research are proposed.

Curriculum Vitae

Guy De Tré is full professor at the Department of Telecommunications and Information Processing of the Faculty of Engineering and Architecture of Ghent University where he is heading the research group on Database, Document, and Content Management (DDCM).
His research activities are centred on computational intelligence in information management systems, including fundamental research on uncertainty handling, multi-valued logics and spatio-temporal modelling and applied research on, among others, big data (NoSQL databases), information fusion, flexible querying, decision support, data quality, and unstructured data. He is (co)author of more than 280 scientific publications. He is area editor of the ‘International Journal of Computational Intelligence Systems’, board member of the European Society for Fuzzy Logic and Technology (EUSFLAT) and steering committee member of Flexible Querying Answering (FQAS).