Ontology Driven Controlled Natural Language Clinical Decision Support System for the Cardiovascular Specialty

Abstract

We present an end to end Question and Answering system to help the clinical practitioners in a cardiovascular healthcare environment. We introduce our proposed ontology framework, Ontology for General Clinical Practice, that we developed enhancing the currently available state-of-the-art ontologies for medical science and for the cardiovascular specialty, extending upon the OBO Foundry principles. It's shown the scientific and philosophical reasons of its present dual structure with a deeply expressive terminological base (TBox) and a highly computable assertions knowledge base (ABox). The knowledge base is automatically populated by means of a tutored acquisition from clinical reports using Controlled Natural Language rendering an ontology driven question answering system with high recall, precision and F-Measure that competes in its specific sub-domain with the more advanced current NLP systems developed in general for the healthcare domain.