2014 | OriginalPaper | Buchkapitel
Retrieval of Drug-Drug Interactions Information from Biomedical Texts: Use of TF-IDF for Classification
verfasst von : Mikhail P. Melnikov, Pavel N. Vorobkalov
Erschienen in: Knowledge-Based Software Engineering
Verlag: Springer International Publishing
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Detection of drug-drug interactions (DDIs) is an important practical challenge. Information about DDIs can help doctors to avoid potentially dangerous interactions. Text mining of articles can solve the problem of DDI databases actuality, thus reducing time of detecting new articles related to drug-drug interaction. There are databases containing large amount of biomedical articles, therefore computational performance of classification method used for identification of documents with DDIs become a valuable factor. In this article, we propose a fast text mining approach to DDI articles classification using term frequency–inverse document frequency (tf-idf) statistic. As a result our approach was able to achieve F1 score value 0.69 (precision = 0.89, recall = 0.57) in DDI articles classification while still keeping short run-time.