Building research capacity in Botswana: a randomized trial comparing training methodologies in the Botswana ethics training initiative

Background: Little empirical data are available on the extent to which capacity-building programs in research ethics prepare trainees to apply ethical reasoning skills to the design, conduct, or review of research. A randomized controlled trial was conducted in Botswana in 2010 to assess the effectiveness of a case-based intervention using email to augment in-person seminars. Methods: University faculty and current and prospective IRB/REC members took part in a semester-long training program in research ethics. Participants attended two 2-day seminars and were assigned at random to one of two on-line arms of the trial. Participants in both arms completed on-line international modules from the Collaborative Institutional Training Initiative. Between seminars, intervention-arm participants were also emailed a weekly case to analyze in response to set questions; responses and individualized faculty feedback were exchanged via email. Tests assessing ethics knowledge were administered at the start of each seminar. The post-test included an additional section in which participants were asked to identify the ethical issues highlighted in five case studies from a list of multiple-choice responses. Results were analyzed using regression and ANOVA. Results: Of the 71 participants (36 control, 35 intervention) enrolled at the first seminar, 41 (57.7%) attended the second seminar (19 control, 22 intervention). In the intervention arm, 19 (54.3%) participants fully completed and 8 (22.9%) partially completed all six weekly cases. The mean score was higher on the post-test (30.3/40) than on the pre-test (28.0/40), and individual post-and pre-test scores were highly correlated (r = 0.65, p < 0.0001). Group assignment alone did not have an effect on test scores (p > 0.84), but intervention-arm subjects who completed all assigned cases answered an average of 3.2 more questions correctly on the post-test than others, controlling for pre-test scores (p = 0.003). Conclusions: Completion of the case-based intervention improved respondents' test scores, with those who completed all six email cases scoring roughly 10% better than those who failed to complete this task and those in the control arm. There was only suggestive evidence that intensive case work improved ethical issue identification, although there was limited ability to assess this outcome due to a high drop-out rate.