摘要：Little is known regarding the psychometric properties of computerized long-menu formats in comparison to classic formats. We compared single-best-answer (Type A) and long-menu formats using identical question stems during the computer-based, summative, intermediate clinical-clerkship exams for nine disciplines. In this randomised sequential trial, we assigned the examinees for every summative exam to either the Type A or long-menu format (four different experimental questions, otherwise identical). The primary outcome was the power of discrimination. The study was carried out at the Faculty of Medicine, University of Geneva, Switzerland, and included all the students enrolled for the exams that were part of the study. Examinees were surveyed about the long-menu format at the end of the trial. The trial was stopped for futility (p = 0.7948) after 22 exams including 88 experimental items. The long-menu format had a similar discriminatory power but was more difficult than the Type A format (71.45% vs 77.80%; p = 0.0001). Over half of the options (54.4%) chosen by the examinees in long-menu formats were not proposed as distractors in the Type A formats. Most examinees agreed that their reasoning strategy was different. In a non-selected population of examinees taking summative exams, long-menu questions have the same discriminatory power as classic Type A questions, but they are slightly more difficult. They are perceived to be closer to real practice, which could have a positive educational impact. We would recommend their use in the final years of the curriculum, within realistic key-feature problems, to assess clinical reasoning and patient management skills.
