08.Latent variable modeling07.Minimal clinically important difference - sporedata/researchdesigneR GitHub Wiki

• Is used when determining how many patients to enroll in a study.
• Used to interpret if a difference in outcomes between groups might be clinically meaningful.

• Most of the times, prospective studies will make use of previously existing MCID estimates

• The calculation of MCID depends on the type of MCID design being used [1]

• Variations in terminology:

Minimal clinically important difference (MCID) Guyatt and colleagues [2] discussed the term in 1987, while Jaeschke and colleagues provided the MCID concept and early approaches in 1989. In their analysis, Wells and colleagues [3] discovered that MCID terminology was frequently connected to significant change from the perspective of patients (perception).

Minimal important difference (MID) Currently, it is the most often used vocabulary in literature (although MCID is still used). The "clinical" component of MCID is omitted in MID, as the anchor employed in the derivation of the change is not based on clinical judgment (e.g., perceptions of clinicians or patients described in earlier MCID literature). As a result, MID might be based on a change in a laboratory marker or a functional test like the lung function test or the 5-minute walk test. The notion of change was also broadened to cover both helpful and detrimental key changes.

Minimal important change (MIC) is used to highlight the distinction in language between "change" and "difference," where "change" refers to longitudinal changes within persons and "difference" refers to crosssectional differences across groups. Because MIC is a change that a patient perceives significant, it should be calculated using patient-perspective anchor-based methods.

Subjectively significant difference (SSD) Osoba and colleagues [4] introduced it in 1998 to stress patient-centered anchoring.

Clinically important difference (CID) CID signifies a clinically significant change that is not always minor. The terminology is also used to distinguish itself from Clinically important responder (CIR), which refers to a between-group difference that is regarded clinically relevant (i.e., in a clinical intervention study).

Clinically important responder (CIR) The amount of change that an individual must disclose in order to be considered to have made a significant improvement. The proposed terminology is more aligned with the development criteria for patient-reported outcome measures.

Minimal detectable change (MDC) The degree of individual change required to distinguish from measurement error (random variation); it was claimed that this should not be used in place of significant change.

To measure the MCID, a variety of methodologies have been developed and applied, all of which may be generally classified into two categories: anchor-based approaches and distribution-based approaches.

Anchor-based approaches employ an external, concrete marker of change, referred to as the anchor, to determine if a change in the target notion of interest occurred, such as a change in pain, function, or quality of life.

Distribution-based approaches make use of internal quantifications of statistical variability in the sample and magnitude of effect as a proxy to MCID quantification in the target measure of interest.

The minimal clinically important difference (MCID) is a metric that attempts to provide a minimum score value that would be considered to be a positive by a patient. Although the concept is very appealing, the underlying methods to derive such a metric are often flawed, either not taking patients' opinion into consideration or, when they do, creating designs that are either psychometrically unreliable.

1. Books *

2. Articles

   • Minimal clinically important difference: Defining what really matters to patients [5].
   • Common references for latent variable
   • Minimal Clinically Important Difference: A Review of Outcome Measure Score Interpretation [6].
   • Understanding the Minimal Clinically Important Difference (MCID) of Patient-Reported Outcome Measures [7].
   • Minimal important difference to infer changes in health-related quality of life-a systematic review [8].
   • How is the minimal clinically important difference established in health-related quality of life instruments? Review of anchors and methods [9].

[1] Johnson, Sindhu. Advanced Epidemiologic Methods for the Study of Rheumatic Diseases.

[2] Guyatt G, Walter S, Norman G. Measuring change over time: assessing the usefulness of evaluative instruments. J Chronic Dis 1987;40(2):171-8.

[3] Wells G, Beaton D, Shea B, et al. Minimal clinically important differences: review of methods. J Rheumatol 2001;28(2):406-12.

[4] Osoba D, Rodrigues G, Myles J, et al. Interpreting the significance of changes in health-related quality-of-life scores. J Clin Oncol 1998;16(1):139-44

[5] McGlothlin AE, Lewis RJ. Minimal clinically important difference: Defining what really matters to patients. Jama. 2014 Oct 1;312(13):1342-3.

[6] Engel L, Beaton DE, Touma Z. Minimal clinically important difference: a review of outcome measure score interpretation. Rheumatic Disease Clinics. 2018 May 1;44(2):177-88.

[7] Sedaghat AR. Understanding the Minimal Clinically Important Difference (MCID) of Patient-Reported Outcome Measures. Otolaryngology–head and neck surgery. 2019 Oct;161(4):551-60.

[8] Jayadevappa R, Cook R, Chhatre S. Minimal important difference to infer changes in health-related quality of life-a systematic review. Journal of clinical epidemiology. 2017 Sep 1;89:188-98.

[9] Mouelhi Y, Jouve E, Castelli C, Gentile S. How is the minimal clinically important difference established in health-related quality of life instruments? Review of anchors and methods. Health and quality of life outcomes. 2020 Dec;18:1-7.