Post

New research · Physical Medicine & Rehabilitation
International journal of medical informatics · 23h
AI / informaticsInternational journal of medical informatics · 2026

Domain-specific functional outcome prediction in stroke rehabilitation: A multicenter artificial intelligence study.

Dong-Young Kim, Seyoung Shin, Junhyung Moon … Baek Hwan Cho
Read paper
Physical Medicine & RehabilitationAI / informatics

Artificial intelligence models accurately predict activities of daily living outcomes after stroke.

Domain-specific functional outcome prediction in stroke rehabilitation: A multicenter artificial intelligence study.

Dong-Young Kim et al. · International journal of medical informatics · 2026
Background

Stroke is a leading cause of long-term disability worldwide, yet existing clinical decision support tools rely on global disability metrics, such as the modified Rankin Scale, which do not adequately reflect patient-centered rehabilitation or recovery goals.

Purpose

We aimed to develop, validate, and implement artificial intelligence (AI)-based clinical support models for predicting domain-specific functional outcomes after stroke across multiple rehabilitation institutions and timepoints.

Methods

We utilized prospective and retrospective multicenter data collected from patients with stroke across four rehabilitation institutions in South Korea (2017-2024).

Results
how accurately the artificial intelligence model predicted daily living abilities after stroke
“
Conclusion · 1 of 2

Our findings demonstrate the predictive feasibility of AI-based modeling for domain-specific stroke prognosis and present a prototype implementation illustrating the potential clinical applicability of the proposed framework across heterogeneous institutional settings.

Conclusion · 2 of 2

The use of routinely collected clinical variables and the preliminary cross-institutional validation results support further investigation of real-world rehabilitation practices, pending prospective clinical evaluation.

Read paper
0 comments

No comments yet. Be the first.

Related papers

LatestFoundational
Study
117
Veterans Health Administration employs only this many therapists nationwide for veterans' pelvic health needs
Randomized Trial
Δ=+20.58
foot and ankle function improved by this amount with combined platelet-rich plasma and exercise
Cross-sectional
42.5% vs 12.7%
chronic ankle instability patients reported pain more frequently during the lunge test than controls
Review
61.3%
61.3% of implementation barriers are patient-related, like digital literacy and cognitive impairment.
Study
8.8±1.5%
the small average error when estimating Achilles tendon forces