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

Predicting Drug Recalls From Internet Search Engine Queries.

Elad Yom-Tov1

  • 1Microsoft Research Israel.

IEEE Journal of Translational Engineering in Health and Medicine
|August 29, 2017
PubMed
Summary

Monitoring internet search queries can predict pharmaceutical recalls. Analyzing search trends helps detect defective drug batches earlier than traditional reporting methods.

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

Hot flashes linked to linguistic markers of cognitive impairment: observational study of social media posts.

Menopause (New York, N.Y.)·2025
Same author

On the Influence of Apologies on the Likelihood of Lawsuits in Cases of Perceived Medical Negligence: Analysis of Archival and Experimental Data.

Journal of medical Internet research·2025
Same author

Bridging the conversational gap in epilepsy: Using large language models to reveal insights into patient behavior and concerns from online discussions.

Epilepsia·2024
Same author

Effectiveness of a Digital Health Intervention Leveraging Reinforcement Learning: Results From the Diabetes and Mental Health Adaptive Notification Tracking and Evaluation (DIAMANTE) Randomized Clinical Trial.

Journal of medical Internet research·2024
Same author

Can social media encourage diabetes self-screenings? A randomized controlled trial with Indonesian Facebook users.

NPJ digital medicine·2024
Same author

A large-scale observational comparison of antidepressants and their effects.

Journal of psychiatric research·2024

Area of Science:

  • Pharmacovigilance
  • Data Science
  • Public Health

Background:

  • Pharmaceutical recalls occur due to safety issues or defects in specific drug batches.
  • Current detection relies on patient or healthcare provider reports to authorities, often leading to delays.

Purpose of the Study:

  • To test the hypothesis that internet search engine query monitoring can predict pharmaceutical recalls earlier.
  • To assess the feasibility of using search query data for early detection of defective drug batches.

Main Methods:

  • Extracted US Bing search engine queries mentioning 5195 pharmaceutical drugs in 2015.
  • Collected all Food and Drug Administration (FDA) recall notifications for the same period.
  • Utilized state-level query volume changes to predict future recalls within a 1–40 day horizon.
Keywords:
Internet search enginesPharmacovigilancedrug safetyrare classes

Related Experiment Videos

Main Results:

  • Future drug recalls were predicted with an AUC of 0.791 and a lift of approximately 6 for one-day ahead predictions.
  • Prediction performance decreased for longer prediction time horizons.
  • Sudden spikes in state-level query volume for specific medicines were the most indicative predictors.
  • Prescription drugs and medium-risk recalls were more identifiable via search query data.

Conclusions:

  • Aggregated internet search engine data can serve as an early warning system for faulty pharmaceutical batches.
  • This approach offers a complementary method to traditional pharmacovigilance for timely detection of drug safety issues.