Continuous Assessment of Daily-Living Gait Using Self-Supervised Learning of Wrist-Worn Accelerometer Data

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. Competing Interest Statement S. Del Din reports consultancy activity with Hoffmann-La Roche Ltd. outside of this study. Funding Statement This work was supported in part by grants from the NIH (R01AG017917, R01AG056352, R01AG79133, R01AG078256) and by the Mobilise-D project. The Mobilise-D project received funding from the Innovative Medicines Initiative 2 Joint Undertaking (JU) under grant agreement No. 820820. This JU receives support from the European Union's Horizon 2020 research and innovation program and the European Federation of Pharmaceutical Industries and Associations (EFPIA). SDD, AJY, and LR were supported by the IDEA-FAST project that has received funding from the Innovative Medicines Initiative 2 Joint Undertaking (JU) under grant agreement No. 853981. SDD, AJY, and LR were supported by the National Institute for Health Research (NIHR) Newcastle Biomedical Research Centre (BRC) based at The Newcastle upon Tyne Hospital NHS Foundation Trust, Newcastle University, and the Cumbria, Northumberland and Tyne and Wear (CNTW) NHS Foundation Trust. SDD, AJY, and LR were also supported by the NIHR/Wellcome Trust Clinical Research Facility (CRF) infrastructure at Newcastle upon Tyne Hospitals NHS Foundation Trust. SDD was supported by the UK Research and Innovation (UKRI) Engineering and Physical Sciences Research Council (EPSRC) (Grant Ref: EP/X031012/1 and Grant Ref: EP/X036146/1). All opinions are those of the authors and not the funders. The content in this publication reflects the authors' view, and neither IMI nor the European Union, EFPIA, NHS, NIHR, or any associated partners are responsible for any use that may be made of the information contained herein. Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes The details of the IRB/oversight body that provided approval or exemption for the research described are given below: Ethics committee of Rush University Medical Center gave ethical approval for this work as part of the Rush Memory and Aging Project. All participants provided written informed consent prior to participation. For the Mobilise-D study, ethical approval was obtained from the following named ethics oversight bodies: London-Bloomsbury Research Ethics Committee of the United Kingdom Health Research Authority gave ethical approval for this work (reference: 19/LO/1507). Helsinki Committee of Tel Aviv Sourasky Medical Center, Tel Aviv, Israel gave ethical approval for this work (reference: 0551-19TLV). Ethics committee of the medical faculty of the University of Tubingen, Germany gave ethical approval for this work (reference: 647/2019BO2). Ethics committee of the medical faculty of Kiel University, Germany gave ethical approval for this work (reference: D438/18). In all cases, participants gave written informed consent before participating in the study. I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes Data Availability The dataset from the Mobilise-D technical validation study (Dataset 3) can be found on Zenodo: https://doi.org/10.5281/zenodo.13899386. All other data and related algorithms (i.e., Dataset 2) included in these analyses are available via the Rush Alzheimer's Disease Center Research Resource Sharing Hub, which can be found at www.radc.rush.edu. It has descriptions of the studies and available data. Any qualified investigator can create an account and submit requests for de-identified data.