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

Misclassification and selection bias in case-control studies using an automated database.

J M Evans1, T M MacDonald

  • 1Medicines Monitoring Unit, Department of Clinical Pharmacology, University of Dundee, UK.

Pharmacoepidemiology and Drug Safety
|April 10, 2004
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

The Functional Medicine Approach to COVID-19: Virus-Specific Nutraceutical and Botanical Agents.

Integrative medicine (Encinitas, Calif.)·2020
Same author

The Functional Medicine Approach to COVID-19: Primer on SARS-CoV-2 Testing.

Integrative medicine (Encinitas, Calif.)·2020
Same author

Cerebral-placental-uterine ratio as novel predictor of late fetal growth restriction: prospective cohort study.

Ultrasound in obstetrics & gynecology : the official journal of the International Society of Ultrasound in Obstetrics and Gynecology·2018
Same author

In response to: 'Thyroid hormone replacement - a counterblast to guidelines'.

The journal of the Royal College of Physicians of Edinburgh·2018
Same author

A multi-method review of home-based chemotherapy.

European journal of cancer care·2015
Same author

Association of DLA-DQB1 alleles with exocrine pancreatic insufficiency in Pembroke Welsh Corgis.

Animal genetics·2015
Same journal

Effectiveness of Metformin in Preventing Colorectal Cancer Among Japanese Patients With Type 2 Diabetes: A Target Trial Emulation.

Pharmacoepidemiology and drug safety·2026
Same journal

Trends in Pharmacist-Prescribed Dispensing Records of HIV Pre-Exposure (2020-2025) and Post-Exposure Prophylaxis (2020-2024) in Brazil: A Time Series Analysis.

Pharmacoepidemiology and drug safety·2026
Same journal

French Consumption of Methylphenidate in Primary Care From 2016 to 2023, Impact of Prescribing Policy Changes-A Time-Series Analysis.

Pharmacoepidemiology and drug safety·2026
Same journal

Uptake and Use of Biologic Therapies in Paediatric Immune-Mediated Inflammatory Diseases: An Australian Population-Based Study.

Pharmacoepidemiology and drug safety·2026
Same journal

Comparative Effectiveness of Oral Fluoropyrimidines Versus FOLFOX as Adjuvant Therapy for Stage III Colon Cancer: A Retrospective Cohort Study Using Overlap-Weighted Restricted Mean Survival Time Analysis.

Pharmacoepidemiology and drug safety·2026
Same journal

Association Between EGFR-TKI-Associated Skin Rash and Recorded Mortality in Non-Small Cell Lung Cancer: A Real-World Analysis Accounting for Immortal Time Bias.

Pharmacoepidemiology and drug safety·2026
See all related articles

Automated databases in pharmacoepidemiology can introduce selection bias when medical records are unavailable. This study found selection bias to be more significant than misclassification bias in case-control studies.

Area of Science:

  • Pharmacoepidemiology
  • Biostatistics
  • Medical Informatics

Background:

  • Automated databases and medical record retrieval are crucial for pharmacoepidemiological research.
  • Case-control studies often exclude patients with missing medical records to minimize misclassification bias.
  • Exclusion of records may introduce selection bias if record availability correlates with exposure status.

Purpose of the Study:

  • To evaluate the relative importance of misclassification bias versus selection bias in pharmacoepidemiological case-control studies.
  • To assess the impact of excluding patients with unavailable medical records on study outcomes.
  • To investigate potential biases in studies using automated databases and manual record validation.

Main Methods:

  • Utilized data from four prior case-control studies on NSAID use and hospitalization for colitis, acute renal failure, appendicitis, and colorectal cancer.

Related Experiment Videos

  • Assessed misclassification bias by comparing odds ratios from studies using all ICD9-identified patients versus validated cases only.
  • Evaluated selection bias by comparing results between studies including patients with available records and those with unavailable records.

    • Main Results:

    • Graphical analysis indicated that misclassification bias was of relatively minor importance.
    • Selection bias was identified as a potentially significant issue when medical records could not be found.
    • The exclusion of patients due to unavailable records can introduce bias into study findings.

    Conclusions:

    • Selection bias, stemming from unavailable medical records, poses a greater threat to the validity of pharmacoepidemiological case-control studies than misclassification bias.
    • Researchers must carefully consider the implications of missing data and its potential to skew results.
    • Strategies to mitigate selection bias in automated database research are warranted.