KHRESMOI · Knowledge Helper for Medical and Other Information users

In KHRESMOI, we will build a multi-lingual multi-modal search and access system for biomedical information and documents. This will be achieved by:- Effective automated information extraction from biomedical documents, including improvement using crowd sourcing and active learning, and automated estimation of the level of trust and target user expertise- Automated analysis and indexing for medical images in 2D (X-Rays), 3D (MRI, CT), and 4D (fMRI)- Linking information extracted from unstructured or semi-structured biomedical texts and images to structured information in knowledge bases- Support of cross-language search, including multi-lingual queries, and returning machine-translated pertinent excerpts- Adaptive user interfaces to assist in formulating queries and display search results via ergonomic and interactive visualizationsThe research will flow into several open source components, which will be integrated into an innovative open architecture for robust and scalable biomedical information search.The system will be evaluated in use cases by three well-defined user groups:1. Members of the general public want access to reliable and understandable medical information in their own language2. Clinicians and general practitioners need accurate answers rapidly – a search on PubMed requires on average 30 minutes, while clinicians typically have 5 minutes available. Furthermore, over 40% of searches fail to provide relevant information3. Radiologists are drowning in images – at larger hospitals over 100GB (over 100000 images) are produced per dayRepresentative groups of end users are available for sizable evaluations, accessed through a medical search engine with 11000 queries per day, a professional association of 2700 medical doctors, and two radiology departments with 175 radiologists.KHRESMOI is directed at Objective ICT-2009.4.3: Intelligent Information Management. It will focus on target outcome (a) capturing tractable information.