Statistical reporting of clinical pharmacology research

Abstract

Research in clinical pharmacology covers a wide range of experiments, trials and investigations: clinical trials, systematic reviews and meta-analyses of drug usage after market approval, the investigation of pharmacokinetic-pharmacodynamic relationships, the search for mechanisms of action or for potential signals for efficacy and safety using biomarkers. Often these investigations are exploratory in nature, which has implications for the way the data should be analysed and presented. Here we summarize some of the statistical issues that are of particular importance in clinical pharmacology research. Descriptive vs. confirmatory investigationsThe development of drugs is generally based on sequential phases, aiming first to learn and subsequently to confirm the mechanisms of efficacy and safety [1]. Although early clinical pharmacology investigations often benefit from extensive preclinical results, there is still much to be learned during the first human trials when the first clinical data are obtained, described and interpreted. Learning can often be achieved by quantifying how measurements that we make are changed by the treatments we give. Such changes are best described using standard descriptive statistics of the data, such as the mean and standard deviation (as well as median, minimum, quartiles and maximum values).Inferential statistical analyses are performed to draw conclusions about general (patient) populations. Those analyses might involve statistical models (e.g. analysis of covariance), and the results would be reported using estimates of population parameters (such as means or proportions) and their standard errors or confidence intervals, which quantify the variability and uncertainty of the reported estimates. Confidence intervals vs. P-valuesWhen comparing treatment outcomes, confidence intervals for parameters of interest (such as the difference between treatment means) provide insight into the potential clinical relevance of a treatment effect in a clinical trial or observational study. Confidence intervals are on the same scale with the same units as the mean, which makes them a preferred choice for reporting results.In contrast, P-values can be used to demonstrate whether or not the difference between two treatments is statistically significant, but statements of statistical significance alone do not necessarily indicate the clinical relevance of an effect and hence might not adequately address the objectives of a clinical pharmacology trial. P-values do not measure the size of an effect or the importance of a result, and do not provide a good measure of evidence regarding a hypothesis [2]. These limitations hold in particular for comparisons that had not been adequately powered.Consequently, P-values that indicate the rejection of hypotheses should be reported only sparsely. Instead, use of confidence intervals is recommended for reporting trial results.

Cefuroxime plasma and tissue concentrations in patients undergoing elective cardiac surgery: Continuous vs bolus application. A pilot study

“…In addition, statistical significance alone, which either confirms or rejects the underlying hypothesis, does not necessarily indicate clinical relevance especially when small groups are studied. The degree of uncertainty of the estimates and thus the potential clinical impact may better be appreciated in Figures and that incorporate IQRs . Nevertheless, larger studies need to be performed to test for clinical outcome.…”

“…Apart from the primarily intended more descriptive presentation of the data we additionally employed t test for normally distributed variables, the Wilcoxon signed rank test for non‐normally distributed variables and the χ 2 test for categorical data. P values were not corrected for multiple comparisons, which is considered to be acceptable in exploratory pharmacological trials …”

Cardiac effects of 6 months' dietary nitrate and spironolactone in patients with hypertension and with/at risk of type 2 diabetes, in the factorial design, double‐blind, randomized controlled VaSera trial

“…This was a prespecified/prospectively conducted, hypothesis-generating, exploratory mechanistic part of the main study. Thus, we present the least squares mean changes from baseline and differences between drugs and between juices, averaged over both follow-up visits for each outcome, with 95% CIs, rather than as hypothesis-testing P-values, in accordance with the recent editorial by Ring et al [39].…”

Warfarin dose requirement in patients having severe thrombosis or thrombophilia

“…The limitations of this study include the restricted sample size of 50 patients due to the single‐site nature of this study. The study was exploratory without power calculations, but significant differences between algorithms were identified . The findings need to be confirmed in a larger patient population to enable firmer conclusions.…”