Minimally Important Differences Do Not Identify Responders to Treatment
Ron D Hays1* and John D Peipert2
1UCLA Division of General Internal Medicine & Health Services Research, USA
2Department of Medical Social Sciences, Feinberg School of Medicine, Northwestern University, USA
Submission: February 23, 2018; Published: April 06, 2018
*Corresponding author: Ron D Hays, UCLA Division of General Internal Medicine & Health Services Research, Los Angeles, CA, USA, Tel: +1-310-794-2294; Email: drhays@ucla.edu
How to cite this article: Ron D H, John D P. Minimally Important Differences Do Not Identify Responders to Treatment. JOJ scin. 2018; 1(1): 555552. DOI: 10.19080/JOJS.2018.01.555552
Keywords
Keywords: Minimally important differences; Significance of individual change; Responders
Introduction
The minimally important difference (MID) is "the average change in the domain of interest on the target measure among the subgroup of people deemed to change a minimal (but important) amount according to an 'anchor'" [1]. The MID is used to determine if statistically significant group change is also large enough to be clinically meaningful. It is an additional consideration when interpreting group differences because very trivial differences can be statistically significant when the sample size is large.
It has been suggested that the MID be used to identify "responders" to treatment [2]. For example, the 2009 FDA guidance document recommended identifying responders using empirical evidence from anchor-based methods and suggested that the "difference in the PRO score for persons who rate their condition the same and better or worse can be used to define responders to treatment" [3]. Using group-level change to identify responders would lead to misclassification of patients as responders when they have not actually changed. In comparison to group change, much larger change is needed for statistically significant change in an individual's score, because of the much larger standard errors for estimates of individual change [1,4].
Thus, responders need to be identified based on the significance of individual change using indices such as the reliable change index (RCI) or the equivalent coefficient of repeatability (CR) [5] = 1.9* SQR (2)*SEM = 2.77*SEM, where SEM = standard error of measurement = SD ( SQR (1 - reliability)).
Acknowledgment
This commentary was supported by the National Institute on Aging's Resource Center on Minority Aging Research (RCMAR) P30-AG021684.
References
- McLeod LD, Coon CD, Martin SA, Fehnel SE, Hays RD (2011) Interpreting patient-reported outcome results: US FDA guidance and emerging methods. Expert Rev Pharmacoecon Outcomes Res 11(2): 163-169.
- Coon CD, Cook KF (2018) Moving from significant to real-world meanings: Methods for interpreting change in clinical outcome assessment scores. Qual Life Res 27: 33-40.
- Food and Drug Administration (2009) Guidance for Industry: Patient- reported outcome measures: Use in medical product development to support labeling claims. U.S. Department of Health and Human Services, Rockville, USA.
- Hays RD, Brodsky M, Johnston MF, Spritzer KL, Hui KK (2005) Evaluating the statistical significance of health-related quality of life change in individual patients. Eval Health Prof 28(2): 160-171.
- Jacobson NS, Truax P (1991) Clinical significance: A statistical approach to defining meaningful change in psychotherapy research. J Consult Clin Psychol 59: 12-19.