Bowden Stephen C, Loring David W
Department of Psychology, The University of Melbourne, Parkville, Victoria, Australia.
J Int Neuropsychol Soc. 2009 Sep;15(5):769-76. doi: 10.1017/S1355617709990373. Epub 2009 Jul 28.
Clinicians are accustomed to interpreting diagnostic test scores in terms of sensitivity and specificity. Many clinicians also appreciate that sensitivity and specificity need to be interpreted in terms of local base rates (i.e., pretest probability). However, most neuropsychological tests contain a wide range of scores. Important diagnostic information may be sacrificed when valid test scores are reduced to the simple dichotomy of "positive" or "negative" diagnosis that underlies sensitivity and specificity analysis. The purpose of this study is to provide an introduction to multiple-level likelihood ratios, a method for preserving the information in a wider range of scores. These statistics are first described using a hypothetical example of dementia screening, then with patient data from an epilepsy surgery sample. Multiple-level likelihood ratios have several advantages over sensitivity and specificity analysis because they are applied across a wider range of diagnostic scores, and generalize to settings with different base rates. We suggest that the diagnostic validity of many psychological tests may be underestimated by relying solely on traditional dichotomous sensitivity and specificity analysis.
临床医生习惯于根据敏感度和特异度来解释诊断测试分数。许多临床医生也认识到，敏感度和特异度需要根据当地的基础概率（即验前概率）来解释。然而，大多数神经心理学测试包含广泛的分数范围。当有效的测试分数被简化为敏感度和特异度分析所基于的“阳性”或“阴性”诊断的简单二分法时，重要的诊断信息可能会被牺牲。本研究的目的是介绍多级似然比，这是一种在更广泛的分数范围内保留信息的方法。首先使用痴呆筛查的假设示例描述这些统计数据，然后使用癫痫手术样本的患者数据进行描述。多级似然比相对于敏感度和特异度分析有几个优点，因为它们适用于更广泛的诊断分数范围，并且可以推广到具有不同基础概率的情况。我们认为，仅依靠传统的二分法敏感度和特异度分析可能会低估许多心理测试的诊断有效性。
