Knowledge Representation and Reasoning for Complex Time Expression in Clinical Text

Abstract Temporal information is pervasive and crucial in medical records other clinical text, as it formulates the development process of conditions vital for decision making. However, providing a holistic knowledge representation reasoning framework various time expressions text challenging. In order to capture complex temporal semantics we propose novel Clinical Time Ontology (CTO) an extension from OWL framework. More specifically, identified eight time-related problems created 11 core classes conceptualize fuzzy time, cyclic irregular negations aspects time. Then, extended Allen's TEO's relations defined relation concept description between simple Simultaneously, provided formulaic graphical presentation relationships. We carried out empirical study on expressiveness usability CTO using real-world healthcare datasets. Finally, experiment results demonstrate that could faithfully represent reason over 93% expressions, can cover wider range domain.