Validation to correct for outcome misclassification bias
Pharmacoepidemiology and Drug Safety · 2023-06 · 32 (6) · 700-703
DOI: 10.1002/pds.5601 ↗At a glance
Journal article in Pharmacoepidemiology and Drug Safety, published online on 2023-02-23. Written by Stephan Lanes and 1 co-authors. Institution: Department of Safety and Epidemiology, HealthCore, Wilmington, Delaware, USA. Major MEDLINE topics: Models, Statistical. Cited 15 times so far (Crossref); 28 references. The full text is freely available (open access, CC BY-NC-ND 4.0).
Abstract (original language)
Key Points1. Outcome validation is often requested by regulators to address misclassification bias in database studies of drug safety and comparative effectiveness.2. Validation studies commonly report only one positive predictive value (PPV) estimate.3. Since a high value of PPV does not imply misclassification bias is negligible, and a low value of PPV does not imply misclassification bias is important, this approach does not adequately address outcome misclassification bias.4. Validation should be designed to inform quantitative bias analysis that corrects results for misclassification bias.5. To correct for misclassification bias, quantitative bias analysis requires parameters for false positive errors and false negative errors in each comparison group.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Department of Safety and Epidemiology, HealthCore, Wilmington, Delaware, USA.
ORCID profiles: Stephan Lanes, Daniel C Beachler
Cite
APA
Lanes, S., & Beachler, D. C. (2023). Validation to correct for outcome misclassification bias. Pharmacoepidemiology and Drug Safety, 32(6), 700-703. https://doi.org/10.1002/pds.5601
Vancouver
Lanes S, Beachler DC. Validation to correct for outcome misclassification bias. Pharmacoepidemiology and Drug Safety. 2023;32(6):700-703. doi:10.1002/pds.5601
BibTeX
@article{Lanes2023,
author = {Lanes, Stephan and Beachler, Daniel C},
title = {Validation to correct for outcome misclassification bias},
journal = {Pharmacoepidemiology and Drug Safety},
year = {2023},
volume = {32},
number = {6},
pages = {700--703},
doi = {10.1002/pds.5601}
}
EUVIMED