Minimal detectable change and meaningful change in motor function in Duchenne muscular dystrophy
Abstract
Evaluations of treatment efficacy in Duchenne muscular dystrophy (DMD), a rare genetic disease that results in progressive muscle wasting, require an understanding of the ‘meaningfulness’ of changes in functional measures. We estimated the minimal detectable change (MDC) for selected motor function measures in ambulatory DMD, i.e., the minimal degree of measured change needed to be confident that true underlying change has occurred rather than transient variation or measurement error. MDC estimates were compared across multiple data sources, representing >1000 DMD patients in clinical trials and real-world clinical practice settings. Included patients were ambulatory, aged ≥4 to <18 years and receiving steroids. Minimal clinically important differences (MCIDs) for worsening were also estimated. Estimated MDC thresholds for >80% confidence in true change were 2.8 units for the North Star Ambulatory Assessment (NSAA) total score, 1.3 seconds for the 4-stair climb (4SC) completion time, 0.36 stairs/second for 4SC velocity and 36.3 meters for the 6-minute walk distance (6MWD). MDC estimates were similar across clinical trial and real-world data sources, and tended to be slightly larger than MCIDs for these measures. The identified thresholds can be used to inform endpoint definitions, or as benchmarks for monitoring individual changes in motor function in ambulatory DMD.
My Take
When we measure change in a patient’s motor function, how do we know whether that change is real or just noise? This seemingly simple question has profound implications for clinical practice and drug development. In this study, we tackled it head-on by rigorously estimating the minimal detectable change for the North Star Ambulatory Assessment—the most widely used functional outcome in Duchenne muscular dystrophy trials.
What we found was more nuanced than a single threshold number. The MDC varies depending on where a patient starts on the functional spectrum. A patient with a high baseline score needs a larger absolute change to exceed measurement error than a patient with lower baseline function. This makes intuitive sense when you think about the structure of the assessment, but it has real consequences for how we interpret trial results and individual patient trajectories. Ignoring this heterogeneity can lead to misclassifying patients as responders or non-responders.
The broader contribution here is methodological rigor in an area where it’s often lacking. By combining distribution-based approaches with anchor-based methods tied to meaningful clinical benchmarks, we provide a more complete picture of what constitutes a real signal versus noise. For the field, this means better-powered trials and more honest conversations about whether an intervention is working. For patients and families, it means greater confidence that the changes their clinicians are tracking actually mean something.