Continuous Assessment of Daily-Living Gait Using Self-Supervised Learning of Wrist-Worn Accelerometer Data
Brand, Y. E.; Buchman, A. S.; Kluge, F.; Palmerini, L.; Becker, C.; Cereatti, A.; Maetzler, W.; Vereijken, B.; Yarnall, A. J.; Rochester, L.; Del Din, S.; Mueller, A.; Hausdorff, J. M.; Perlman, O.
Show abstract
Physical activity and mobility are critical for healthy aging and predict diverse health outcomes. While wrist-worn accelerometers are widely used to monitor physical activity, estimating gait metrics from wrist data remains challenging. We extend ElderNet, a self-supervised deep-learning model previously validated for walking-bout detection, to estimate gait metrics from wrist accelerometry. Validation involved 819 older adults (Rush-Memory- and-Aging-Project) and 85 individuals with gait impairments (Mobilise-D), from six medical centers. In Mobilise-D, ElderNet achieved an absolute error of 8.82 cm/s and an intra-class correlation of 0.87 for gait speed, outperforming state-of-the-art methods (p < 0.001) and models using a lower-back sensor. ElderNet outperformed (percentage error; p < 0.01) competing approaches in estimating cadence and stride length, and better (p < 0.01) classified mobility disability (AUC = 0.80) than conventional gait or physical activity metrics. These results render ElderNet a scalable tool for gait assessment using wrist-worn devices in aging and clinical populations.
Matching journals
The top 2 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- An aging focused unobtrusive and Privacy-Preserving Digital Behaviorome 94%
- Interpretable deep learning approach for extracting cognitive features from hand-drawn images of intersecting pentagons in older adults 93%
- Crowdsourcing digital health measures to predict Parkinson's disease severity: the Parkinson's Disease Digital Biomarker DREAM Challenge 93%
Similar papers in this journal
- An infection prediction model developed from inpatient data can predict out-of-hospital COVID-19 infections from wearable data when controlled for dataset shift 93%
- Gait signature changes with walking speed are similar among able-bodied young adults despite persistent individual-specific differences 92%
- Prediction of vascular ageing based on smartphone acquired PPG signals 92%
Similar papers in this journal
- Using deep learning to predict age from liver and pancreas magnetic resonance images allows the identification of genetic and non-genetic factors associated with abdominal aging 91%
- Identification of a blood test-based biomarker of aging through deep learning of aging trajectories in large phenotypic datasets of mice 90%
- Genome-wide meta-analysis of muscle weakness identifies 15 susceptibility loci in older men and women 90%
Similar papers in this journal
- Hip and knee joint kinematics predict quadriceps hyperreflexia in people with post-stroke Stiff-Knee gait 93%
- Ultrasound-based optimal parameter estimation improves assessment of calf muscle-tendon interaction during walking 90%
- James-Stein estimator improves accuracy and sample efficiency in human kinematic and metabolic data 88%
Similar papers in this journal
- Cohort Profile: Baseline characteristics and design of the McMaster Monitoring My Mobility (MacM3) Study, a prospective digital mobility cohort of community-dwelling older Canadians from Southern Ontario 94%
- Validation of the German version of the Life-Space Assessment LSA-D 89%
- Re-contacting biobank participants: lessons from a pilot study within FinnGen 89%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.