Mining Drug Properties for Decision Support in Dental Clinics.

The rise of polypharmacy requires from health providers an awareness of a patient’s drug profile before prescribing. Existing methods to extract information on drug interactions do not integrate with the patient’s medical history. This paper describes state-of-the-art approaches in extracting the term frequencies of drug properties and combining this knowledge with consideration of the patient’s drug allergies and current medications to decide if a drug is suitable for prescription. Experimental evaluation of our models association of the similarity ratio between two drugs (based on each drug’s term frequencies) with the similarity between them yields a superior accuracy of 79%. Similarity to a drug the patient is allergic to or is currently taking are important considerations as to the suitability of a drug for prescription. Hence, such an approach, when integrated within the clinical workflow, will reduce prescription errors thereby increasing the health outcome of the patient.