PTOTCohortJournal of rehabilitation medicine2024

Early functional factors for predicting outcome of independence in daily living after stroke: a decision tree analysis.

Heegoo Kim, Chanmi Lee, Nayeong Kim and 4 others

PMID 38712968

WHAT IT FOUND

A decision tree model predicts independence in daily living after stroke.

Patients who could stand up from sitting and had good balance on admission were most likely to achieve a good outcome at discharge. This helps therapists set early goals based on initial mobility and balance scores.

Key findings

01The ability to perform sitting-to-standing movements was the most influential predictor for independence in daily living on discharge.

02Visuomotor organization scores were the primary cognitive predictor for daily living outcomes.

03The model based on motor function achieved 92.4% overall accuracy in predicting outcomes.

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 did not follow patients after discharge, so it cannot predict long-term outcomes. The sample was relatively small and skewed towards moderate-to-severe stroke, limiting generalizability to milder cases. The data was imbalanced, with more poor outcomes than good outcomes, which the analysis tools could not fully correct. The models were validated only by internal cross-validation, not by testing on a separate group of patients from a different setting.

Declared interests

The authors declared no conflicts of interest. The work was supported by government grants from the Ministry of Health & Welfare and the Ministry of Science and ICT in South Korea.

The easy way to misread this

Do not assume these cut-off scores apply to all stroke patients. The models were built on a specific group with moderate-to-severe stroke in a single centre, and the cognitive model had lower accuracy, so use these predictions as a guide rather than a definitive verdict on a patient's potential.

Read it on PubMed →