Abstract
In pharmaceutical research and development, multiple factors like age, gender, comorbidity, concomitant medication, genetic and environmental factors co-determine the efficacy of the new treatment. In statistical terms we say they interact with the treatment efficacy. It is impossible to estimate all of these factors. Instead, randomized controlled trials are used to ensure that no major imbalances exist regarding these factors, and an overall assessment is made. The limitation of this approach becomes obvious once the new medicine is applied in practice where benefits of new medicines are far less consistent than they are in the trials (Riegelman 2005). Despite this limitation, interaction effects, are not routinely assessed in clinical trials, probably because the statistical methods for identifying and integrating them into the data have low power. Moreover, if we introduce a large number of interaction terms in a regression analysis, the power to demonstrate a statistical significance for the primary endpoint will be reduced. Nonetheless, the assessment of a small number of interaction terms in clinical research can be an important part of the evaluation of new drugs, particularly, if it can be argued that the interaction terms make clinically sense. The current chapter gives some important factors that may interact with the treatment efficacy, and proposes some guidelines for implementing an interaction assessment in the analysis of clinical trials, in order to better predict the efficacy/safety of new medicines in future clinical treatment of individual patients.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Barrett-Connor E (2002) Looking for the pony in the heart and estrogen/progestin replacement study (HERS) data. Circulation 105:902–903
Chalmers I, Altman DG (eds) (1996) Systematic reviews. Br Med J Books, Bristol
De Craen AJM, Westendorp RGJ (2005) The use of age as a variable in clinical research. Ned Tijdschr Geneeskd 149:2958–2963
Hays WL (1998) Random effects and mixed models. In: Statistics, 4th edn. Holt, Rhinehart and Winnston Inc, Chicago, pp 479–543
Jukema AJ, Zwinderman AH, et al. for the REGRESS Study Group (1995) Effects of lipid lowering by pravastatin on progression and regression of coronary artery disease in symptomatic men with normal to moderately elevated serum cholesterol levels. The Regression Growth Evaluation Statin Study (REGRESS). Circulation 91:2528–2540
Riegelman RK (2005) Studying a study and testing a test. Lippincott Williams & Wilkins, Philadelphia
Shlipak MG, Simon JA, Vittinghoff E et al (2000) Estrogen and progestin, lipoprotein (a), and the risk of recurrent coronary heart disease events after menopause. JAMA 283:1845–1852
Svetkey LP, Simons-Morton D, Vollmer WM et al (1999) Effects of dietary patterns on blood pressure: subgroup analysis of the dietary approaches to stop-hypertension (DASH) randomized clinical trial. Arch Intern Med 159:258–293
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer Science+Business Media B.V.
About this chapter
Cite this chapter
Cleophas, T.J., Zwinderman, A.H. (2012). Interaction. In: Statistics Applied to Clinical Studies. Springer, Dordrecht. https://doi.org/10.1007/978-94-007-2863-9_30
Download citation
DOI: https://doi.org/10.1007/978-94-007-2863-9_30
Published:
Publisher Name: Springer, Dordrecht
Print ISBN: 978-94-007-2862-2
Online ISBN: 978-94-007-2863-9
eBook Packages: Biomedical and Life SciencesBiomedical and Life Sciences (R0)