biostudies-literatureUnknown12Li JIntramural NIH HHS<h4>Background</h4>Each day, millions of health consumers seek drug-related information on the Web. Despite some efforts in linking related resources, drug information is largely scattered in a wide variety of websites of different quality and credibility.<h4>Methods</h4>As a step toward providing users with integrated access to multiple trustworthy drug resources, we aim to develop a method capable of identifying drug's dosage form information in addition to drug name recognition. We developed rules and patterns for identifying dosage forms from different sections of full-text drug monographs, and subsequently normalized them to standardized RxNorm dosage forms.<h4>Results</h4>Our method represents a significant improvement compared with a baseline lookup approach, achieving overall macro-averaged Precision of 80%, Recall of 98%, and F-Measure of 85%.<h4>Conclusions</h4>We successfully developed an automatic approach for drug dosage form identification, which is critical for building links between different drug-related resources.BMC medical informatics and decision making9https://www.ebi.ac.uk/biostudies/studies/S-EPMC3305679biostudies-literatureAutomatic identification and normalization of dosage forms in drug monographs.PMC3305679Li JLu ZfalseAutomatic identification and normalization of dosage forms in drug monographs.<h4>Background</h4>Each day, millions of health consumers seek drug-related information on the Web. Despite some efforts in linking related resources, drug information is largely scattered in a wide variety of websites of different quality and credibility.<h4>Methods</h4>As a step toward providing users with integrated access to multiple trustworthy drug resources, we aim to develop a method capable of identifying drug's dosage form information in addition to drug name recognition. We developed rules and patterns for identifying dosage forms from different sections of full-text drug monographs, and subsequently normalized them to standardized RxNorm dosage forms.<h4>Results</h4>Our method represents a significant improvement compared with a baseline lookup approach, achieving overall macro-averaged Precision of 80%, Recall of 98%, and F-Measure of 85%.<h4>Conclusions</h4>We successfully developed an automatic approach for drug dosage form identification, which is critical for building links between different drug-related resources.2012-01-01T00:00:00Z2012 Feb2021-03-05T09:37:48Z2019-03-27T00:51:14ZS-EPMC33056792233643110.1186/1472-6947-12-9