A Lightweight Semantic-Based Medical Document Retrieval

摘要

Medical information is valuable for a health care professional to empower diagnosis and clinical decision process. In addition, it can also support communities with health knowledge to support healthy living. Ontology-based information retrieval supports the retrieval of such information with the semantically better result. In this paper, we propose a framework of lightweight semantic-based medical document retrieval in Bahasa Indonesia. The medical information is focused on diagnosis, etiology, epidemiology, clinical manifestation, and guidelines. The framework firstly annotates queries' by using the ontology, analyse the information networks within the ontology and extracts the context of the queries. When a query falls within one context of disease information, a modified search query will be then generated and passed to an existing keyword-based search result. The framework is evaluated using a case study in infectious tropical disease domain. The evaluation results show that the framework could perform well with precision equals or more than 0.9 to find the relevant medical document through the semantic networks and the enhancement process.