Comparison of randomization techniques for clinical trials with data from the HOMERUS-trial

Background. Several methods of randomization are available to create comparable intervention groups in a study. In the HOMERUS-trial, we compared the minimization procedure with a stratified and a non-stratified method of randomization in order to test which one is most appropriate for use in clinical hypertension trials. A second objective of this article was to describe the baseline characteristics of the HOMERUS-trial. Methods. The HOMERUS population consisted of 459 mild-to-moderate hypertensive subjects (54% males) with a mean age of 55 years. These patients were prospectively randomized with the minimization method to either the office pressure (OP) group, where antihypertensive treatment was based on office blood pressure (BP) values, or to the self-pressure (SP) group, where treatment was based on self-measured BP values. Minimization was compared with two other randomization methods, which were performed post-hoc: (i) non-stratified randomization with four permuted blocks, and (ii) stratified randomization with four permuted blocks and 16 strata. In addition, several factors that could influence outcome were investigated for their effect on BP by 24-h ambulatory blood pressure monitoring (ABPM). Results. Minimization and stratified randomization did not lead to significant differences in 24-h ABPM values between the two treatment groups. Non-stratified randomization resulted in a significant difference in 24-h diastolic ABPM between the groups. Factors that caused significant differences in 24-h ABPM values were: region, centre of patient recruitment, age, gender, microalbuminuria, left ventricular hypertrophy and obesity. Conclusion. Minimization and stratified randomization are appropriate methods for use in clinical trials. Many outcome factors should be taken into account for their potential influence on BP levels. Recommendation. Due to the large number of potential outcome factors that can influence BP levels, minimization should be the preferred method for use in clinical hypertension trials, as it has the potential to randomize more outcome factors than stratified randomization.