Applying results of randomised trials to clinical practice: impact of losses before randomisation

Abstract

The problem of generalisability in randomised clinical trials was highlighted by studies that entered only 10-14% of screened patients. To determine the magnitude and source of prerandomisation losses in clinical trials a survey was conducted of 41 trials listed in the 1979 inventory of the National Institute of Health. Two thirds of the trials maintained screening logs, but only half maintained any records of the number of patients who met the eligibility criteria but were not entered into the trial. Among 21 trials (51%) that kept data on the number of patients who were eligible but not entered, losses of eligible subjects were attributable to refusals by patients in 25% and refusals by physicians in 29%. Other protocol requirements accounted for the remaining losses of eligible patients. Only a few trials documented the characteristics of patients who were eligible but not entered; in those trials the patients who were not entered were similar demographically but differed clinically from those enrolled. Thus minimising prerandomisation losses of eligible patients requires the use of less restrictive criteria for entering patients. Twenty four of the trials achieved 75% or more of their recruitment goals, eight between 25% and 74%, and six less than 25%. Among trials that screened less than twice their projected sample size, only three out of 13 (23%) achieved 75% or more of their recruitment goal. By contrast, 12 out of 16 trials (75%) that screened more than twice their projected sample size achieved 75% or more of their recruitment goal. Screening large numbers of patients appears to be a pragmatic requirement for success in achieving recruitment goals; therefore, trials should not be criticised as lacking generalisability on that basis alone. The number and characteristics of eligible patients who were not entered, however, were documented by only a few trials; these data are critical in the assessment of generalisability. Additionally, the number of patients with the index disease who did not meet the eligibility criteria should also be documented. Together, these two types of data characterise the population to whom the trial results may be applied.