Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

An algorithm to derive a numerical daily dose from unstructured text dosage instructions.

Anoop D Shah1, Carlos Martinez

  • 1General Practice Research Database Division, Medicines and Healthcare products Regulatory Agency, London, UK.

Pharmacoepidemiology and Drug Safety
|September 20, 2005
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Donor- and unit-specific factors influencing hemolysis in stored canine and feline packed red blood cells.

Frontiers in veterinary science·2026
Same author

Roadmapping stroke healthcare in Colombia: a comprehensive telestroke network evaluation.

BMC medical informatics and decision making·2026
Same author

PARP2 deficiency impairs pancreatic cancer progression by promoting genomic instability and antitumor immunity.

Science advances·2026
Same author

Increasing Kidney Transplant Volume With Higher Kidney Donor Risk Index Kidneys: A Call for Action in the United States.

Transplantation·2026
Same author

Outcomes of Kidney Transplants From Donors With Stage 3 Acute Kidney Injury Requiring Dialysis: A National Cohort Study.

Clinical transplantation·2026
Same author

Exploring metabolomic clues in diabetic retinopathy: a pilot study.

Acta diabetologica·2026

An automated algorithm accurately extracts daily drug doses from general practitioners' free-text instructions. This enhances pharmacoepidemiology research by improving drug exposure duration calculations in large patient databases.

Area of Science:

  • Pharmacoepidemiology
  • Health Informatics
  • Data Science

Background:

  • The General Practice Research Database (GPRD) is a valuable source for pharmacoepidemiology.
  • Extracting daily drug dosage and exposure duration from GPRD has been challenging due to free-text entry by general practitioners.
  • This limitation hinders efficient analysis of drug utilization and patient outcomes.

Purpose of the Study:

  • To develop and validate an automated algorithm for deriving daily drug doses from free-text dosage instructions.
  • To improve the efficiency of pharmacoepidemiology studies using the GPRD.

Main Methods:

  • A computer program was created to extract numerical dosage information from unstructured text.
  • The algorithm was tested on one million prescription entries from the GPRD.

Related Experiment Videos

  • The accuracy of the automated extraction was manually verified on a random sample of 1,000 texts.

    • Main Results:

    • Approximately 74.5% of prescription entries contained text with the daily dose.
    • The automated algorithm correctly interpreted 98.8% of the manually verified daily dose statements.
    • The algorithm demonstrated high accuracy in extracting quantitative daily dose information.

    Conclusions:

    • An automated algorithm can accurately extract daily drug doses from general practitioners' text instructions.
    • This tool significantly enhances the utility of the GPRD and similar prescription databases.
    • Efficient estimation of drug exposure duration is now feasible, advancing pharmacoepidemiological research.