Imaging-Enhanced Prediction of Upper Limb Motor Function After Stroke Using Automated Segmentation and Cluster Analysis.
- 1Department of Rehabilitation Medicine, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea.
- 2Artificial Intelligence Research Center, JLK Inc., Seoul, Korea.
- 3Department of Rehabilitation Medicine, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea. [email protected].
Abstract
Background
Stroke is a leading cause of long-term disability, and early prediction of motor outcomes is critical for guiding individualized rehabilitation strategies. Although neuroimaging offers prognostic insights, its clinical integration remains limited. This study aimed to evaluate whether explainable imaging-derived features can improve the prediction of upper limb motor impairment and to identify distinct recovery profiles through cluster analysis.Methods
We retrospectively analyzed 242 patients with acute ischemic stroke who underwent brain magnetic resonance imaging and motor function assessment. Clinical and imaging variables-including infarct volume, motor tract involvement, and subtype classification-were extracted using automated software. Predictive models for Fugl-Meyer Assessment upper extremity (FMA-UE) scores were developed using hierarchical regression, and K-means clustering was applied to standardized baseline data. Cluster characteristics were compared, and recovery profiles were visualized.Results
Incorporating imaging variables improved prediction of FMA-UE scores (adjusted R²: 0.595), with motor tract lesion volume emerging as a key predictor. Cluster analysis revealed three distinct patient subgroups: Cluster 1 (mild impairments, younger age), Cluster 2 (older patients with multiple comorbidities), and Cluster 3 (severe neurological deficits, large infarcts). Functional outcomes differed significantly across clusters, with Cluster 3 showing the greatest disability (76% with follow-up modified Rankin Scale 4-6, P < 0.001).Conclusion
Imaging-derived features from early magnetic resonance imaging improve the prediction of upper limb motor outcomes after stroke. Cluster-based stratification identifies clinically meaningful subgroups, supporting precision rehabilitation through personalized care planning and targeted secondary prevention.
Related
- An automated ranking platform for machine learning regression models for meat spoilage prediction using multi-spectral imaging and metabolic profiling
- Automated optic chiasm segmentation in magnetic resonance imaging of multiple sclerosis patients using a multi-view, multi-class U-Net with limited annotated data
- Multiparametric MRI-based habitat and peritumoral radiomics integrating semi-automated segmentation for preoperative prediction of high-grade prostate cancer: a dual-center study
- Dynamic Xenon-Enhanced Spectral CT Imaging to Evaluate Regional Lung Function in an In Vivo Rabbit Model
- Laboratory indicators combined with liver function scores for predicting suboptimal hepatobiliary phase imaging during gadoxetic acid-enhanced MRI
BibTeX
@article{cha2026imagingenhanced,
title = {{Imaging-Enhanced Prediction of Upper Limb Motor Function After Stroke Using Automated Segmentation and Cluster Analysis.}},
author = {Seungwoo Cha and Wi-Sun Ryu and Bokgi Hwang and Dae Yul Kim and Seung Hak Lee},
journal = {Journal of Korean medical science},
year = {2026},
month = oct,
doi = {10.3346/jkms.2026.41.e263},
url = {https://europepmc.org/article/MED/42901496},
note = {CC BY-NC},
}
RIS
TY - JOUR
TI - Imaging-Enhanced Prediction of Upper Limb Motor Function After Stroke Using Automated Segmentation and Cluster Analysis.
AU - Seungwoo Cha
AU - Wi-Sun Ryu
AU - Bokgi Hwang
AU - Dae Yul Kim
AU - Seung Hak Lee
PY - 2026
DA - 2026/10/19
JO - Journal of Korean medical science
DO - 10.3346/jkms.2026.41.e263
UR - https://europepmc.org/article/MED/42901496
AB - Background Stroke is a leading cause of long-term disability, and early prediction of motor outcomes is critical for guiding individualized rehabilitation strategies. Although neuroimaging offers prognostic insights, its clinical integration remains limited. This study aimed to evaluate whether explainable imaging-derived features can improve the prediction of upper limb motor impairment and to identify distinct recovery profiles through cluster analysis.Methods We retrospectively analyzed 242 patients with acute ischemic stroke who underwent brain magnetic resonance imaging and motor function assessment. Clinical and imaging variables-including infarct volume, motor tract involvement, and subtype classification-were extracted using automated software. Predictive models for Fugl-Meyer Assessment upper extremity (FMA-UE) scores were developed using hierarchical regression, and K-means clustering was applied to standardized baseline data. Cluster characteristics were compared, and recovery profiles were visualized.Results Incorporating imaging variables improved prediction of FMA-UE scores (adjusted R²: 0.595), with motor tract lesion volume emerging as a key predictor. Cluster analysis revealed three distinct patient subgroups: Cluster 1 (mild impairments, younger age), Cluster 2 (older patients with multiple comorbidities), and Cluster 3 (severe neurological deficits, large infarcts). Functional outcomes differed significantly across clusters, with Cluster 3 showing the greatest disability (76% with follow-up modified Rankin Scale 4-6, P < 0.001).Conclusion Imaging-derived features from early magnetic resonance imaging improve the prediction of upper limb motor outcomes after stroke. Cluster-based stratification identifies clinically meaningful subgroups, supporting precision rehabilitation through personalized care planning and targeted secondary prevention.
SN - 1598-6357
ER -