Methods of sample size calculation in descriptive retrospective burden of illness studies

Karissa M Johnston,Bonnie M K Donato,Shelagh M Szabo,Pardis Lakzadeh

doi:10.1186/s12874-018-0657-9

Abstract

BackgroundObservational burden of illness studies are used in pharmacoepidemiology to address a variety of objectives, including contextualizing the current treatment setting, identifying important treatment gaps, and providing estimates to parameterize economic models. Methodologies such as retrospective chart review may be utilized in settings for which existing datasets are not available or do not include sufficient clinical detail. While specifying the number of charts to be extracted and/or determining whether the number that can feasibly extracted will be clinically meaningful is an important study design consideration, there is a lack of rigorous methods available for sample size calculation in this setting. The objective of this study was to develop recommended sample size calculations for use in such studies.MethodsCalculations for identifying the optimal feasible sample size calculations were derived, for studies characterizing treatment patterns and medical costs, based on the ability to comprehensively observe treatments and maximize precision of resulting 95% confidence intervals. For cost outcomes, if the standard deviation is not known, the coefficient of variation cv can be used as an alternative. A case study of a chart review of advanced melanoma (MELODY) was used to characterize plausible values for cv in a real-world example.ResultsAcross sample sizes, any treatment given with greater than 1% frequency has a high likelihood of being observed. For a sample of size 200, and a treatment given to 5% of the population, the precision of a 95% confidence interval (CI) is expected to be ±0.03. For cost outcomes, for the median cv value observed in the MELODY study (0.72), a sample size of approximately 200 would be required to generate a 95% CI precise to within ±10% of the mean.ConclusionThis study presents a formal guidance on sample size calculations for retrospective burden of illness studies. The approach presented here is methodologically rigorous and designed for practical application in real-world retrospective chart review studies.

Highlights

IntroductionBurden of illness studies can contextualize the current treatment setting, identify important treatment gaps and their associated consequences, With the increased availability of “big data”, methodological considerations for observational research often focus on the use of large databases – while challenges remain in this setting, available sample size and power do not tend to be problematic given the large pool of individuals from which to draw [4]
Observational burden of illness studies are used in pharmacoepidemiology to address a variety of objectives, including contextualizing the current treatment setting, identifying important treatment gaps, and providing estimates to parameterize economic models
For a sample of size 200, and a treatment given to 5% of the population, the precision of a 95% confidence interval (CI) is expected to be ±0.03; i.e. the expected 95% CI would be (0.02–0.08)

Summary

Introduction

Burden of illness studies can contextualize the current treatment setting, identify important treatment gaps and their associated consequences, With the increased availability of “big data”, methodological considerations for observational research often focus on the use of large databases – while challenges remain in this setting, available sample size and power do not tend to be problematic given the large pool of individuals from which to draw [4]. Such databases are not able to answer all burden of illness research questions, due to insufficient clinical detail. Researchers may know at the outset how many charts are available to be extracted, and must consider the expected value of the information, before deciding whether to perform chart extraction

Objectives

Methods

Results

Discussion

Conclusion