Metrics extracted from a single wearable sensor during sit-stand transitions relate to mobility impairment and fall risk in people with multiple sclerosis.

The study had a small sample size of 38 participants, which limits the generalizability of the findings. Participants were ambulatory without assistive devices, so the results do not apply to people with MS who use walkers or wheelchairs. The classification models were cross-validated within the same small cohort, not tested on a new, independent group of patients, so the reported accuracy may be optimistic. The study used a specific type of research-grade sensor; it is unclear if consumer-grade devices or smartphone apps would yield the same metrics. Fall status was determined by self-report over six months, which can be subject to recall bias.

One author reports consulting for EMD Serono, Biogen, and Alexion, and research funding from Biogen. Another author reports stock ownership in MC10, Inc. (the sensor manufacturer) and Impellia, Inc., consulting for HX Innovations Inc. and University of Washington, and research funding from MC10, Inc. and Epicore Biosystems, Inc.

Do not assume that a smartphone app can currently replicate these findings. The study used specific research-grade sensors with defined sampling rates and filtering methods, and the models have not been validated in a new, independent population. The slight improvement in accuracy over counting repetitions is promising but not yet ready for clinical decision-making.