Unravelling the mystery of the 'minimum important difference' using practical outcome measures in chronic respiratory disease

Abstract

It is important for clinicians and researchers to understand the effects of treatments on their patients, both at an individual and group level. In clinical studies, treatment effects are often reported as a change in the outcome measure supported by a measure of variability; for example, the mean change with 95% confidence intervals and a probability ( p) value to indicate the level of statistical significance. However, a statistically significant change may not indicate a clinically meaningful or important change for clinicians or patients to interpret. The minimum clinically important difference (MCID) or minimally important difference (MID) has therefore been developed to add clinical relevance or patient experience to the reporting of an outcome measure. In this article, we consider the concept of the MID using the example of practical outcome measures in patients with CRD. We describe the various ways in which an MID can be calculated via anchor- and distribution-based methods, looking at practical examples and considering the importance of understanding how an MID was derived when seeking to apply it to a particular situation. The terms MID and MCID are challenging and often used interchangeably. However, we propose all MIDs are described as such, but they could be qualified by a suffix: MIDS (MID - Statistical), MID-C (MID - Clinical outcome), MID-P (MID - Patient determined). However, this type of classification would only work if accepted and adopted. In the meantime, we advise clinicians and researchers to use an MID where possible to aid their interpretation of functional outcome measures and effects of interventions, to add meaning above statistical significance alone.

Keywords: Exercise; MCID; MID; lung disease; outcome assessment; physical function; respiratory disease.

Figure 1.

Example data of the repeatability of the incremental shuttle walk test distance. An example from unpublished data where the mean difference for the two tests is zero, so there is no bias. However, there is significant individual variability described by 2 SD approximately 55 metres for the dataset below. These data can aid clinical interpretation within an individual patient; to be 95% confident that a true change had occurred over time or with an intervention an individual would have to improve by >55 metres.