A point of minimal important difference (MID): a critique of terminology and methods

The minimal important difference (MID) is a phrase with instant appeal in a field struggling to interpret health-related quality of life and other patient-reported outcomes. The terminology can be confusing, with several terms differing only slightly in definition (e.g., minimal clinically important difference, clinically important difference, minimally detectable difference, the subjectively significant difference), and others that seem similar despite having quite different meanings (minimally detectable difference versus minimum detectable change). Often, nuances of definition are of little consequence in the way that these quantities are estimated and used. Four methods are commonly employed to estimate MIDs: patient rating of change (global transition items); clinical anchors; standard error of measurement; and effect size. These are described and critiqued in this article. There is no universal MID, despite the appeal of the notion. Indeed, for a particular patient-reported outcome instrument or scale, the MID is not an immutable characteristic, but may vary by population and context. At both the group and individual level, the MID may depend on the clinical context and decision at hand, the baseline from which the patient starts, and whether they are improving or deteriorating. Specific estimates of MIDs should therefore not be overinterpreted. For a given health-related quality-of-life scale, all available MID estimates (and their confidence intervals) should be considered, amalgamated into general guidelines and applied judiciously to any particular clinical or research context.