Abstract
Average medical facility produces several gigabytes of data every day. Yet about 80 % of data produced by various Hospital Information Systems (HIS) are so called unstructured data that were previously disregarded from being analysed.
Unstructured data means information that either does not have a pre-defined data model or is not organised in a pre-defined manner. In the past, unstructured data was extremely difficult to analyse, thus mostly ignored.
Unfortunately, this unstructured data presents such a valuable portion of the Electronic Medical Records (EMRs) that cannot be ignored any more. This research will focus on how to deal with unstructured medical data.
From acquisition and processing to final analysis and visualisation. Special regard will be given to medical records text analytics, crucial area in dealing with medical unstructured data.