Toward Improving the Prediction of Functional Ambulation After Spinal Cord Injury Through the Inclusion of Limb Accelerations During Sleep and Personal Factors.
Stephanie K Rigot, Michael L Boninger, Dan Ding and 5 others
PMID 33839107WHAT IT FOUND
In 27 adults with chronic spinal cord injury, adding overnight limb movement measures to clinical information more accurately grouped participants by walking speed and endurance than clinical information alone, but the model is not for direct patient prognosis.
Key findings
01The model using limb accelerations during sleep and clinical and demographic features had the highest overall classification accuracy for the 10-meter Walk Test, 0.704, compared with 0.593 for clinical and demographic features alone.
02For the 6-minute Walk Test, the model using limb accelerations during sleep and clinical and demographic features had the highest overall classification accuracy, 0.815.
03Measures of movement smoothness were the most commonly selected limb acceleration features for both walking outcomes.
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
The analysis included 27 participants. The sample was mostly male, non-Hispanic White, Veterans, high school graduates, with paraplegia, and manual wheelchair users. Participants had chronic, non-progressive spinal cord injury with voluntary lower limb movement, and motor complete injuries were excluded. The study was cross-sectional, so it does not show how the models would predict walking after acute injury or over time. The authors state the results are not intended to be used directly for longitudinal prediction. The demographics may not represent all people with spinal cord injury. The outcomes were categories from the 10-meter Walk Test and 6-minute Walk Test, not long-term mobility outcomes. Some groups were frequently misclassified, especially household and community ambulators on the 10-meter Walk Test. Data were partly collected at sporting events, although only typical nights and daily logs were used.
Declared interests
The authors declared no conflicts of interest. The article lists U.S. government and NIH extramural research support.
The easy way to misread this
Do not use these models to tell a patient how much they will walk after spinal cord injury. The study was cross-sectional, analyzed 27 participants, and the authors say it is not intended for direct longitudinal prediction.