Abstract
BackgroundFree-text medication prescriptions contain detailed instruction information that is key when preparing drug data for analysis. The objective of this study was to develop a novel model and automated text-mining method to extract detailed structured medication information from free-text prescriptions and explore their variability (e.g. optional dosages) in primary care research databases.MethodsWe introduce a prescription model that provides minimum and maximum values for dose number, frequency and interval, allowing modelling variability and flexibility within a drug prescription. We developed a text mining system that relies on rules to extract such structured information from prescription free-text dosage instructions. The system was applied to medication prescriptions from an anonymised primary care electronic record database (Clinical Practice Research Datalink, CPRD).ResultsWe have evaluated our approach on a test set of 220 CPRD prescription free-text directions. The system achieved an overall accuracy of 91 % at the prescription level, with 97 % accuracy across the attribute levels. We then further analysed over 56,000 most common free text prescriptions from CPRD records and found that 1 in 4 has inherent variability, i.e. a choice in taking medication specified by different minimum and maximum doses, duration or frequency.ConclusionsOur approach provides an accurate, automated way of coding prescription free text information, including information about flexibility and variability within a prescription. The method allows the researcher to decide how best to prepare the prescription data for drug efficacy and safety analyses in any given setting, and test various scenarios and their impact.Electronic supplementary materialThe online version of this article (doi:10.1186/s12911-016-0255-x) contains supplementary material, which is available to authorized users.
Highlights
Free-text medication prescriptions contain detailed instruction information that is key when preparing drug data for analysis
Gold-standard evaluation The initial set of 200 free-text Clinical Practice Research Datalink (CPRD) prescription instructions was used to develop and tune the system, and these were not used for the evaluation
Following the development of the system and in order to create a gold standard for the evaluation, a new set of 100 medication prescriptions was randomly selected from the CPRD dataset of 56,000 free-text prescriptions, and manually and independently annotated by the authors: a clinical consultant (WGD), a health informatician (GN) and a health informatician with medical background (GK)
Summary
Free-text medication prescriptions contain detailed instruction information that is key when preparing drug data for analysis. The objective of this study was to develop a novel model and automated text-mining method to extract detailed structured medication information from free-text prescriptions and explore their variability (e.g. optional dosages) in primary care research databases. Manual efforts have been undertaken to identify and extract key information, but such approaches are extremely time consuming and often inconsistent and incomplete [5,6,7] In this manuscript we present an automated methodology to extract and represent prescription instruction information in a structured form, capturing, in particular, the variability and flexibility of dosage information. Our main motivation is to support researchers in making transparent decisions when preparing prescription data for further processing
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
