Background: Each day, millions of health consumers seek drug-related information on the Web. Despite some\r\nefforts in linking related resources, drug information is largely scattered in a wide variety of websites of different\r\nquality and credibility.\r\nMethods: As a step toward providing users with integrated access to multiple trustworthy drug resources, we aim\r\nto develop a method capable of identifying drug�s dosage form information in addition to drug name recognition.\r\nWe developed rules and patterns for identifying dosage forms from different sections of full-text drug monographs,\r\nand subsequently normalized them to standardized RxNorm dosage forms.\r\nResults: Our method represents a significant improvement compared with a baseline lookup approach, achieving\r\noverall macro-averaged Precision of 80%, Recall of 98%, and F-Measure of 85%.\r\nConclusions: We successfully developed an automatic approach for drug dosage form identification, which is\r\ncritical for building links between different drug-related resources.
Loading....