Post-Acute Concussion-Related Differences in Neuromotor Control Measured Using a Low-Cost Movement Assessment System: A Feasibility Study.
Jacob Thomas, Rebecca Bliss, Caitlin Fields and 2 others
PMID 40041526WHAT IT FOUND
A low-cost movement test classified 81.67% of 22 young adults correctly when sorting people recovering from concussion from controls, within this small feasibility sample.
Balance, gait, and reaction-time patterns mattered together, not one single measure.
Key findings
01The movement assessment model separated the two groups in this sample with 81.67% accuracy.
02The confusion matrix showed 8 concussion participants were predicted as concussion and 10 controls were predicted as controls.
03Much of the group separation came from static balance measures, while gait and reaction-time measures also contributed to the retained components.
STILL TO COME
How it was doneWhat they foundWhat it means for PTs
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
Only 22 participants were assessed, including 10 people 2 weeks to 2 months after concussion and 12 controls, so the model is unlikely to generalize. The authors state that the sample size was limited and the model is not generalizable. The paper reports one testing session, not a longitudinal recovery assessment. The model was trained and tested on the same small group using leave-one-out cross-validation, and the authors say they cannot identify which specific tasks or variables matter most. Participants were aged 18-35 and excluded recent musculoskeletal injury, so it is unclear how this applies to younger athletes or those with other injuries.
The easy way to misread this
Do not use this system to diagnose concussion or clear an athlete for return to play. The model was built and tested on only 22 participants, and the authors state it is not generalizable.