Intelligent prediction of dynamic characteristics during exercise in patients with stroke.
Qinghua Meng, Nan Zhang, Chunyu Bao and 4 others
PMID 41024103WHAT IT FOUND
A computer model using wearable sensors estimated hip, knee and ankle joint moments during walking and stairs in people after stroke, with small errors in the tested data.
It has not been checked on new patients.
Key findings
01The model predicted affected-side hip, knee and ankle joint moments during walking and stair tasks, and the predicted mean moment curves were very similar to the calculated curves.
02The predicted affected-side joint moments showed strong agreement with the calculated moments, with reported correlations of at least 0.94.
03The model was validated only on subsets from the same participants, not on entirely new subjects.
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 participants had to be able to walk 20 m independently and were at Brunnstrom stage IV, so the findings may not apply to patients who cannot walk independently. The model was validated only on subsets from the same participants, not on entirely new subjects. There was no direct comparison with optical motion capture, so its accuracy relative to the usual laboratory method is unknown. The reference values for coronal and transverse plane joint moments may be less accurate than sagittal plane values, which could affect the evaluation.
Declared interests
Funders named were the National Natural Science Foundation of China, Scientific research projects of Tianjin Sports Bureau, Tianjin Natural Science Foundation of China, and Scientific research projects of the General Administration of Sport of China. The supplied text does not report other conflict-of-interest statements.
The easy way to misread this
Do not treat this as a validated clinical gait assessment. The model was tested on data from the same participants, not on new patients, so it may not work outside this study.
Summarised by AI from the full paper, without a clinician reviewing it. Check it against the source before it changes what you do. Read it on PubMed →