Using ontologies to retrieve health evidence information from clinical notes

Jan Carl Beeck-Pepper, Ivan Luiz Marques Ricarte


Objective: To present a strategy to search evidence databases directly from clinical notes, thus relieving health professionals from performing searches. Method: An ontology related to health domain, specifically for the domain of adult asthma, was developed to illustrate how to extract search terms from clinical notes. Another ontology was developed to describe evidence databases. Results: Synthetic notes, simulating clinical conditions for patients with respiratory diseases, were used to search information from two evidence databases, PubMed and PEDro. SPARQL queries were automatically generated to connect both ontologies. Conclusion: This scenario demonstrated how to search for evidence from electronic health records notes, helping health professionals to receive relevant information while they assist patients.


Evidence-Based Medicine; Health Information Systems; Knowledge Bases; Decision Support Techniques

Texto completo: PDF

Journal of Health Informatics - ISSN 2175-4411
Rua Tenente Gomes Ribeiro, 57 - sala 33 CEP 04038-040 São Paulo - SP - Brasil
Tel./Fax: + 55 11 3791 3343 - E-mail: