Automatic ontology oriented clinical concept extraction from free-text reports for CSI (Computer Semantic Interoperability)

Abstract

Clinicians develops their own jargon to report about their work. Most EHR systems provide a way to extract reports of their daily activity. In order to formalize an automated acquisition from free-form, natural language texts in Portuguese into a Clinical Practice Ontology an important step that is involved is to develop the ability of “understanding” all the nicknames, acronyms and short-hand forms that each clinician tend to write down in their reports. We present the steps to develop personal clinical vocabularies extracting directly from SOAP clinical reports in Portuguese. All the presented techniques are easily developed for any other natural language or knowledge representation framework with the due adaptations.