GaitScreen: a ground reaction force-based framework for prescreening gait abnormalities in orthopaedic populations
- 1School of Engineering, University of Birmingham, Birmingham, United Kingdom
- 2Gait and Motion Analysis Center, Yueyang Hospital of Integrative Medicine, Shanghai University of Traditional Chinese Medicine, Shanghai, China
Abstract
Ground reaction force (GRF) trajectories capture kinetic alterations in stance-phase loading, propulsion, and mediolateral control. This study presents GaitScreen, a GRF-based framework for post-acquisition prioritisation of already recorded healthy-control and pathological-gait trials. GaitScreen converts vertical, anterior–posterior, and mediolateral stance-phase GRF trajectories into a review-prioritisation score and a threshold-dependent review flag. The framework combines a multiscale temporal backbone, a convolutional neural network component, and a logistic regression component to integrate multiscale force patterns, learned convolutional representations, and raw-waveform linear information. It was evaluated using the GaitRec dataset, comprising healthy controls and individuals with lower-limb orthopaedic conditions. Under a subject-exclusive evaluation protocol, GaitScreen achieved consistent trial-level performance across ten matched runs, with an accuracy of 0.8766±0.0025, a macro-F1 score of 0.8757±0.0024, and an AUROC of 0.9425±0.0015. A high-sensitivity operating mode reduced the false-negative rate from 0.1736 to 0.1073, with an increase in false-positive review flags. The full hybrid model had a serialized size of 1.122 MB and a mean CPU inference latency of 0.626±0.010 ms per sample after GRF preprocessing. The compact model size and low inference latency support computationally scalable post-acquisition processing of standardised GRF trials.
Related
- When DL-Based Prescreening Meets Synthon-Based Docking: Target-Adapting PharmacoNet via MEL-Steered Correction
- A Unified Unsupervised Framework for Genome-Wide Association Studies in Heterogeneous Populations
- The evolution of sex for artificial intelligence: a population-genetic framework for multigenerational model populations
- A real-time forecasting framework for emerging infectious diseases affecting animal populations
- Open access route and citation impact in orthopaedic research: A comparison of Gold/hybrid, Green, and Bronze open access within ten high-impact subscription-based journals
BibTeX
@article{bian2026gaitscreen,
title = {{GaitScreen: a ground reaction force-based framework for prescreening gait abnormalities in orthopaedic populations}},
author = {Qingyao Bian and Qing Zhang and Yang Li and Ziyun Ding},
journal = {Frontiers in Bioengineering and Biotechnology},
year = {2026},
month = oct,
doi = {10.3389/fbioe.2026.1947887},
url = {https://doi.org/10.3389/fbioe.2026.1947887},
note = {CC BY},
}
RIS
TY - JOUR
TI - GaitScreen: a ground reaction force-based framework for prescreening gait abnormalities in orthopaedic populations
AU - Qingyao Bian
AU - Qing Zhang
AU - Yang Li
AU - Ziyun Ding
PY - 2026
DA - 2026/10/26
JO - Frontiers in Bioengineering and Biotechnology
DO - 10.3389/fbioe.2026.1947887
UR - https://doi.org/10.3389/fbioe.2026.1947887
AB - Ground reaction force (GRF) trajectories capture kinetic alterations in stance-phase loading, propulsion, and mediolateral control. This study presents GaitScreen, a GRF-based framework for post-acquisition prioritisation of already recorded healthy-control and pathological-gait trials. GaitScreen converts vertical, anterior–posterior, and mediolateral stance-phase GRF trajectories into a review-prioritisation score and a threshold-dependent review flag. The framework combines a multiscale temporal backbone, a convolutional neural network component, and a logistic regression component to integrate multiscale force patterns, learned convolutional representations, and raw-waveform linear information. It was evaluated using the GaitRec dataset, comprising healthy controls and individuals with lower-limb orthopaedic conditions. Under a subject-exclusive evaluation protocol, GaitScreen achieved consistent trial-level performance across ten matched runs, with an accuracy of 0.8766±0.0025, a macro-F1 score of 0.8757±0.0024, and an AUROC of 0.9425±0.0015. A high-sensitivity operating mode reduced the false-negative rate from 0.1736 to 0.1073, with an increase in false-positive review flags. The full hybrid model had a serialized size of 1.122 MB and a mean CPU inference latency of 0.626±0.010 ms per sample after GRF preprocessing. The compact model size and low inference latency support computationally scalable post-acquisition processing of standardised GRF trials.
SN - 2296-4185
ER -