Concept extraction from unstructured documents is a sensitive step in the knowledge extraction process. The transformation of the unstructured documents into structured data and further into structured information that can be exploited by predictive modules implies a sequence of steps related to data preparation, concept extraction and data organization, filtering and selection. Along with the adoption of the Electronic Health Records a step forward has been taken in the healthcare domain allowing for faster and easier knowledge discovery and utilization of data. While the ultimate goal for structuring EHRs is knowledge extraction for building assistive medical diagnosis systems, the correct identification of terms in documents is essential. The current paper covers an original complete solution for automatically structuring medical documents and extracting relevant medical concepts via the PreNex [1] and MedCIM [2] strategies while our vision for the Knowledge Extraction and Prediction solutions is being argued and is under development
hybrid algorithm, prediction, recommendation, Electronic Health Records, Data Mining, Text Mining
© Association for Information and Communication Technologies www.ict-act.org Developed by tdelev