AI-driven adaptive segmentation of Timed Up and Go test phases using a smartphone

Rashid, M, Sher, A ORCID: https://orcid.org/0000-0002-0650-0335, Povina, FV and Akanyeti, O, 2025. AI-driven adaptive segmentation of Timed Up and Go test phases using a smartphone. Electronics, 14 (23): 4650. ISSN 2079-9292

Preview

Text 2539264_Sher.pdf - Published version Download (2MB) | Preview

Abstract

The Timed Up and Go (TUG) test is a widely used clinical tool for assessing mobility and fall risk in older adults and individuals with neurological or musculoskeletal conditions. While it provides a quick measure of functional independence, traditional stopwatch-based timing offers only a single completion time and fails to reveal which movement phases contribute to impairment. This study presents a smartphone-based system that automatically segments the TUG test into distinct phases, delivering objective and low-cost biomarkers of lower-limb performance. This approach enables clinicians to identify phase-specific impairments in populations such as individuals with Parkinson's disease, and older adults, supporting precise diagnosis, personalized rehabilitation, and continuous monitoring of mobility decline and neuroplastic recovery. Our method combines adaptive preprocess-ing of accelerometer and gyroscope signals with supervised learning models (Random Forest, Support Vector Machine (SVM), and XGBoost) using statistical features to achieve continuous phase detection and maintain robustness against slow or irregular gait, accommodating individual variability. A threshold-based turn detection strategy captures both sharp and gradual rotations. Validation against video ground truth using group K-fold cross-validation demonstrated strong and consistent performance: start and end points were detected in 100% of trials. The mean absolute error for total time was 0.42 s (95% CI: 0.36-0.48 s). The average error across phases (stand, walk, turn) was less than 0.35 s, and macro F 1 scores exceeded 0.85 for all models, with the SVM achieving the highest score of 0.882. Combining accelerometer and gyroscope features improved macro F1 by up to 12%. Statistical tests (McNemar, Bowker) confirmed significant differences between models, and calibration metrics indicated reliable probabilistic outputs (ROC-AUC > 0.96, Brier score < 0.08). These findings show that a single smartphone can deliver accurate, in-terpretable, and phase-aware TUG analysis without complex multi-sensor setups, enabling practical and scalable mobility assessment for clinical use.

Item Type:	Journal article
Publication Title:	Electronics
Creators:	Rashid, M., Sher, A., Povina, F.V. and Akanyeti, O.
Publisher:	MDPI
Date:	December 2025
Volume:	14
Number:	23
ISSN:	2079-9292
Identifiers:	Number Type 10.3390/electronics14234650 DOI 2539264 Other
Rights:	© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Divisions:	Schools > School of Science and Technology
Record created by:	Laura Borcherds
Date Added:	28 Nov 2025 12:51
Last Modified:	28 Nov 2025 12:51
URI:	https://irep.ntu.ac.uk/id/eprint/54822

Actions (login required)

Edit View

Statistics

Views

Downloads