Premium
Drug product dispensing and estimates of use in a general population survey as a signal detection problem
Author(s) -
Black Joshua C.,
Forber Alyssa,
Severtson S. Geoff,
Rockhill Karilynn,
May K. Patrick,
Amioka Elise,
Schwarz John,
Iwanicki Janetta,
Dart Richard C.
Publication year - 2021
Publication title -
pharmacoepidemiology and drug safety
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.023
H-Index - 96
eISSN - 1099-1557
pISSN - 1053-8569
DOI - 10.1002/pds.5260
Subject(s) - medicine , medical prescription , pharmacoepidemiology , population , reliability (semiconductor) , inference , statistics , epidemiology , cross sectional study , prescription drug , environmental health , pharmacology , mathematics , computer science , power (physics) , physics , pathology , quantum mechanics , artificial intelligence
Purpose Understanding potential bias due to rarity of the outcome is important when monitoring newly approved drugs and drugs with low availability to the general public. Although there is an increasing use of online surveys to investigate health outcomes, the limits of inference due to drug availability have not been studied. The goal of this study was to quantify the relationship between dispensing of prescription drugs and estimates of use in an online general population survey. Methods An online repeated, cross‐sectional survey from 2018 to 2020 was used to estimate the number of adults in the United States who used prescription drugs in the general population and compared to estimated number of prescriptions dispensed over an equivalent time period. Joinpoint regression was used to quantify thresholds. A sample of respondents was retested to estimate reliability statistics. Results A model with a single threshold was the best fit, with the estimated threshold of 565 000 (95% CI: 9500‐11 600 000) prescriptions dispensed per year. Above the threshold, there was a significant association between dispensing and estimates ( p < 0.001); below the threshold, the relationship was not significant ( p = 0.912). Above the threshold, responses were more reliable than random chance, and reliability steadily increased with increased dispensing. Conclusions These results suggest the threshold demarcates two distinct pharmacoepidemiological paradigms when investigating drug use in general population surveys. Dispensing can be used as a guide to determine the epidemiological paradigm that is best suited.