Accelerometry and the Capacity–Performance Gap: Case Series Report in Upper-Extremity Motor Impairment Assessment Post-Stroke

Journal article

Estevan M. Nieto, Edaena Lujan, Crystal A. Mendoza, Yazbel Arriaga, Cecilia Fierro, Tan Tran, Lin-Ching Chang, Alvaro N. Gurovich, Peter S. Lum, Shashwati Geed
Bioengineering, 2025

Semantic Scholar DOI PubMedCentral PubMed

Cite

APA Click to copy
Nieto, E. M., Lujan, E., Mendoza, C. A., Arriaga, Y., Fierro, C., Tran, T., … Geed, S. (2025). Accelerometry and the Capacity–Performance Gap: Case Series Report in Upper-Extremity Motor Impairment Assessment Post-Stroke. Bioengineering.

Chicago/Turabian Click to copy
Nieto, Estevan M., Edaena Lujan, Crystal A. Mendoza, Yazbel Arriaga, Cecilia Fierro, Tan Tran, Lin-Ching Chang, Alvaro N. Gurovich, Peter S. Lum, and Shashwati Geed. “Accelerometry and the Capacity–Performance Gap: Case Series Report in Upper-Extremity Motor Impairment Assessment Post-Stroke.” Bioengineering (2025).

MLA Click to copy
Nieto, Estevan M., et al. “Accelerometry and the Capacity–Performance Gap: Case Series Report in Upper-Extremity Motor Impairment Assessment Post-Stroke.” Bioengineering, 2025.

BibTeX Click to copy

@article{estevan2025a,
  title = {Accelerometry and the Capacity–Performance Gap: Case Series Report in Upper-Extremity Motor Impairment Assessment Post-Stroke},
  year = {2025},
  journal = {Bioengineering},
  author = {Nieto, Estevan M. and Lujan, Edaena and Mendoza, Crystal A. and Arriaga, Yazbel and Fierro, Cecilia and Tran, Tan and Chang, Lin-Ching and Gurovich, Alvaro N. and Lum, Peter S. and Geed, Shashwati}
}

Abstract

This case series investigates whether traditional machine learning (ML) and convolutional neural network (CNN) models trained on wrist-worn accelerometry data collected in a laboratory setting can accurately predict real-world functional hand use in individuals with chronic stroke. Participants (N = 4) with neuroimaging-confirmed chronic stroke completed matched activity scripts—comprising instrumental and basic activities of daily living—in-lab and at-home. Participants wore ActiGraph CenterPoint Insight watches on the impaired and unimpaired wrists; concurrent video recordings were collected in both environments. Frame-by-frame annotations of the video, guided by the FAABOS scale (functional, non-functional, unknown), served as the ground truth. The results revealed a consistent capacity–performance gap: participants used their impaired hand more in-lab than at-home, with the largest discrepancies in patients with moderate to severe impairment. Random forest ML models trained on in-lab accelerometry accurately classified at-home hand use, with the highest performance in mildly and severely impaired limbs (accuracy = 0.80–0.90) and relatively lower performance (accuracy = 0.62) in moderately impaired limbs. CNN models showed comparable accuracy to random forest classifiers. These pilot findings demonstrate the feasibility of using lab-trained ML models to monitor real-world hand use and identify emerging patterns of learned non-use—enabling timely, targeted interventions to promote recovery in outpatient stroke rehabilitation.