Hill Faith, Kendall Kathleen, Galbraith Kevin, Crossley Jim
School of Medicine, University of Southampton, Southampton, UK.
Med Educ. 2009 Apr;43(4):326-34. doi: 10.1111/j.1365-2923.2008.03275.x.
The mini-clinical evaluation exercise (mini-CEX) is widely used in the UK to assess clinical competence, but there is little evidence regarding its implementation in the undergraduate setting. This study aimed to estimate the validity and reliability of the undergraduate mini-CEX and discuss the challenges involved in its implementation.
A total of 3499 mini-CEX forms were completed. Validity was assessed by estimating associations between mini-CEX score and a number of external variables, examining the internal structure of the instrument, checking competency domain response rates and profiles against expectations, and by qualitative evaluation of stakeholder interviews. Reliability was evaluated by overall reliability coefficient (R), estimation of the standard error of measurement (SEM), and from stakeholders' perceptions. Variance component analysis examined the contribution of relevant factors to students' scores.
Validity was threatened by various confounding variables, including: examiner status; case complexity; attachment specialty; patient gender, and case focus. Factor analysis suggested that competency domains reflect a single latent variable. Maximum reliability can be achieved by aggregating scores over 15 encounters (R = 0.73; 95% confidence interval [CI] +/- 0.28 based on a 6-point assessment scale). Examiner stringency contributed 29% of score variation and student attachment aptitude 13%. Stakeholder interviews revealed staff development needs but the majority perceived the mini-CEX as more reliable and valid than the previous long case.
The mini-CEX has good overall utility for assessing aspects of the clinical encounter in an undergraduate setting. Strengths include fidelity, wide sampling, perceived validity, and formative observation and feedback. Reliability is limited by variable examiner stringency, and validity by confounding variables, but these should be viewed within the context of overall assessment strategies.
迷你临床评估演练(mini-CEX)在英国被广泛用于评估临床能力,但在本科阶段实施该评估的相关证据较少。本研究旨在评估本科迷你临床评估演练的效度和信度,并探讨其实施过程中所涉及的挑战。
共完成了3499份迷你临床评估演练表格。通过估计迷你临床评估演练分数与多个外部变量之间的关联、检查评估工具的内部结构、对照预期检查能力领域的应答率和概况以及对利益相关者访谈进行定性评估来评估效度。通过总体信度系数(R)、测量标准误(SEM)的估计以及利益相关者的看法来评估信度。方差成分分析考察了相关因素对学生分数的贡献。
效度受到各种混杂变量的威胁,包括:考官身份;病例复杂性;实习专科;患者性别以及病例重点。因子分析表明,能力领域反映了一个单一的潜在变量。通过汇总15次评估的分数可实现最大信度(R = 0.73;基于6分评估量表的95%置信区间[CI]为±0.28)。考官的严格程度对分数变异的贡献为29%,学生的实习适应性贡献为13%。利益相关者访谈揭示了员工发展需求,但大多数人认为迷你临床评估演练比之前的长病例评估更可靠、更有效。
迷你临床评估演练在评估本科临床接触方面具有良好的总体效用。优点包括逼真度、广泛抽样、公认的效度以及形成性观察和反馈。信度受到考官严格程度变化的限制,效度受到混杂变量的限制,但应在整体评估策略的背景下看待这些问题。