PTOTCohortJournal of neuroengineering and rehabilitation2025

Machine learning techniques for independent gait recovery prediction in acute anterior circulation ischemic stroke.

Jiangping Ma, Yuanjie Xie

PMID 39891212

WHAT IT FOUND

A machine learning model predicted independent walking recovery in stroke patients more accurately than standard statistics.

It relied on the Timed Up and Go test, brain scan markers, and cognitive scores to identify those likely to recover gait by 90 or 180 days.

Key findings

01The Random Survival Forest model predicted gait recovery better than the Cox regression model, with higher accuracy in both the training and validation groups.

02The most important factors for predicting recovery were the Timed Up and Go test score, enlarged perivascular spaces in the basal ganglia, cognitive assessment scores, age, and white matter changes.

03The model successfully stratified patients into low and high risk groups for gait recovery at 90 and 180 days.

STILL TO COME

How it was doneWhat they foundWhat it means for PTsWhat it means for OTs

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.

Already have one?

What it does not show

The study included only patients with mild hemiparesis (lower limb strength grade IV or V-), so the model does not apply to those with severe weakness. It was a single-center study with a relatively small sample size, limiting generalizability. External validation in diverse populations was not performed. The study excluded patients who received intravenous thrombolysis or mechanical thrombectomy, which are common acute treatments.

Declared interests

The authors declared no competing interests. The study was supported by non-U.S. government grants.

The easy way to misread this

Do not assume this model predicts recovery for all stroke patients. It was developed only on those with mild leg weakness (grade IV or V-) and those who did not receive thrombolysis or thrombectomy. Applying it to severe strokes or those treated with reperfusion therapies may yield inaccurate predictions.

Read it on PubMed →