Biomedical Ontologies and Text Mining for Biomedicine and Healthcare: A Survey

Abstract

In this survey paper, we discuss biomedical ontologies and major text mining techniquesapplied to biomedicine and healthcare. Biomedical ontologies such as UMLS are currentlybeing adopted in text mining approaches because they provide domain knowledge for textmining approaches. In addition, biomedical ontologies enable us to resolve many linguisticproblems when text mining approaches handle biomedical literature. As the first example oftext mining, document clustering is surveyed. Because a document set is normally multiple-topic, text mining approaches use document clustering as a preprocessing step to group similardocuments. Additionally, document clustering is able to inform the biomedical literaturesearches required for the practice of evidence-based medicine. We introduce Swanson’sUnDiscovered Public Knowledge (UDPK) model to generate biomedical hypotheses frombiomedical literature such as MEDLINE by discovering novel connections among logically-related biomedical concepts. Another important area of text mining is document classification.Document classification is a valuable tool for biomedical tasks that involve large amounts oftext. We survey well-known classification techniques in biomedicine. As the last example oftext mining in biomedicine and healthcare, we survey information extraction. Informationextraction is the process of scanning text for information relevant to some interest, includingextracting entities, relations, and events. We also address techniques and issues of evaluatingtext mining applications in biomedicine and healthcare.