Literature DB >> 26360635

More realistic power estimation for new user, active comparator studies: an empirical example.

Mugdha Gokhale1, John B Buse2, Virginia Pate1, M Alison Marquis3, Til Stürmer1.   

Abstract

PURPOSE: Pharmacoepidemiologic studies are often expected to be sufficiently powered to study rare outcomes, but there is sequential loss of power with implementation of study design options minimizing bias. We illustrate this using a study comparing pancreatic cancer incidence after initiating dipeptidyl-peptidase-4 inhibitors (DPP-4i) versus thiazolidinediones or sulfonylureas.
METHODS: We identified Medicare beneficiaries with at least one claim of DPP-4i or comparators during 2007-2009 and then applied the following steps: (i) exclude prevalent users, (ii) require a second prescription of same drug, (iii) exclude prevalent cancers, (iv) exclude patients age <66 years and (v) censor for treatment changes during follow-up. Power to detect hazard ratios (effect measure strongly driven by the number of events) ≥ 2.0 estimated after step 5 was compared with the naïve power estimated prior to step 1.
RESULTS: There were 19,388 and 28,846 DPP-4i and thiazolidinedione initiators during 2007-2009. The number of drug initiators dropped most after requiring a second prescription, outcomes dropped most after excluding patients with prevalent cancer and person-time dropped most after requiring a second prescription and as-treated censoring. The naïve power (>99%) was considerably higher than the power obtained after the final step (~75%).
CONCLUSIONS: In designing new-user active-comparator studies, one should be mindful how steps minimizing bias affect sample-size, number of outcomes and person-time. While actual numbers will depend on specific settings, application of generic losses in percentages will improve estimates of power compared with the naive approach mostly ignoring steps taken to increase validity.
Copyright © 2015 John Wiley & Sons, Ltd.

Entities:  

Keywords:  bias; new-user design; pharmacoepidemiology; power; sample size

Mesh:

Substances:

Year:  2015        PMID: 26360635      PMCID: PMC4788577          DOI: 10.1002/pds.3872

Source DB:  PubMed          Journal:  Pharmacoepidemiol Drug Saf        ISSN: 1053-8569            Impact factor:   2.890


  10 in total

Review 1.  Indications for propensity scores and review of their use in pharmacoepidemiology.

Authors:  Robert J Glynn; Sebastian Schneeweiss; Til Stürmer
Journal:  Basic Clin Pharmacol Toxicol       Date:  2006-03       Impact factor: 4.080

2.  The tyranny of power: is there a better way to calculate sample size?

Authors:  John Martin Bland
Journal:  BMJ       Date:  2009-10-06

3.  GRADE guidelines 6. Rating the quality of evidence--imprecision.

Authors:  Gordon H Guyatt; Andrew D Oxman; Regina Kunz; Jan Brozek; Pablo Alonso-Coello; David Rind; P J Devereaux; Victor M Montori; Bo Freyschuss; Gunn Vist; Roman Jaeschke; John W Williams; Mohammad Hassan Murad; David Sinclair; Yngve Falck-Ytter; Joerg Meerpohl; Craig Whittington; Kristian Thorlund; Jeff Andrews; Holger J Schünemann
Journal:  J Clin Epidemiol       Date:  2011-08-11       Impact factor: 6.437

4.  Induction and latent periods.

Authors:  K J Rothman
Journal:  Am J Epidemiol       Date:  1981-08       Impact factor: 4.897

5.  Pancreatitis, pancreatic, and thyroid cancer with glucagon-like peptide-1-based therapies.

Authors:  Michael Elashoff; Aleksey V Matveyenko; Belinda Gier; Robert Elashoff; Peter C Butler
Journal:  Gastroenterology       Date:  2011-02-18       Impact factor: 22.682

Review 6.  Do we have enough data to confirm the link between antidiabetic drug use and cancer development?

Authors:  Józef Drzewoski; Agata Drozdowska; Agnieszka Sliwińska
Journal:  Pol Arch Med Wewn       Date:  2011-03

7.  Treatment effects in the presence of unmeasured confounding: dealing with observations in the tails of the propensity score distribution--a simulation study.

Authors:  Til Stürmer; Kenneth J Rothman; Jerry Avorn; Robert J Glynn
Journal:  Am J Epidemiol       Date:  2010-08-17       Impact factor: 4.897

Review 8.  Diabetes medications and cancer risk: review of the literature.

Authors:  Quang T Nguyen; Lindsay Sanders; Anu P Michael; Scott R Anderson; Loida D Nguyen; Zackary A Johnson
Journal:  Am Health Drug Benefits       Date:  2012-07

9.  Dipeptidyl-peptidase-4 inhibitors and pancreatic cancer: a cohort study.

Authors:  M Gokhale; J B Buse; C L Gray; V Pate; M A Marquis; T Stürmer
Journal:  Diabetes Obes Metab       Date:  2014-09-10       Impact factor: 6.577

Review 10.  Systematic review: comparative effectiveness and safety of oral medications for type 2 diabetes mellitus.

Authors:  Shari Bolen; Leonard Feldman; Jason Vassy; Lisa Wilson; Hsin-Chieh Yeh; Spyridon Marinopoulos; Crystal Wiley; Elizabeth Selvin; Renee Wilson; Eric B Bass; Frederick L Brancati
Journal:  Ann Intern Med       Date:  2007-07-16       Impact factor: 25.391

  10 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.