Self-supervised learning of wrist-worn daily living accelerometer data improves the automated detection of gait in older adults.
Accelerometer
Gait
Machine learning
Older adults
Self-supervised learning
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
06 Sep 2024
06 Sep 2024
Historique:
received:
14
03
2024
accepted:
28
08
2024
medline:
7
9
2024
pubmed:
7
9
2024
entrez:
6
9
2024
Statut:
epublish
Résumé
Progressive gait impairment is common among aging adults. Remote phenotyping of gait during daily living has the potential to quantify gait alterations and evaluate the effects of interventions that may prevent disability in the aging population. Here, we developed ElderNet, a self-supervised learning model for gait detection from wrist-worn accelerometer data. Validation involved two diverse cohorts, including over 1000 participants without gait labels, as well as 83 participants with labeled data: older adults with Parkinson's disease, proximal femoral fracture, chronic obstructive pulmonary disease, congestive heart failure, and healthy adults. ElderNet presented high accuracy (96.43 ± 2.27), specificity (98.87 ± 2.15), recall (82.32 ± 11.37), precision (86.69 ± 17.61), and F1 score (82.92 ± 13.39). The suggested method yielded superior performance compared to two state-of-the-art gait detection algorithms, with improved accuracy and F1 score (p < 0.05). In an initial evaluation of construct validity, ElderNet identified differences in estimated daily walking durations across cohorts with different clinical characteristics, such as mobility disability (p < 0.001) and parkinsonism (p < 0.001). The proposed self-supervised method has the potential to serve as a valuable tool for remote phenotyping of gait function during daily living in aging adults, even among those with gait impairments.
Identifiants
pubmed: 39242792
doi: 10.1038/s41598-024-71491-3
pii: 10.1038/s41598-024-71491-3
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
20854Subventions
Organisme : NIH HHS
ID : R01AG017917
Pays : United States
Organisme : NIH HHS
ID : R01AG056352
Pays : United States
Organisme : NIH HHS
ID : R01AG79133
Pays : United States
Organisme : NIH HHS
ID : R01AT012228
Pays : United States
Organisme : Innovative Medicines Initiative
ID : 820820
Informations de copyright
© 2024. The Author(s).
Références
Cruz-Jimenez, M. Normal changes in gait and mobility problems in the elderly. Phys. Med. Rehabil. Clin. N. Am. 28, 713–725 (2017).
pubmed: 29031338
doi: 10.1016/j.pmr.2017.06.005
Freiberger, E., Sieber, C. C. & Kob, R. Mobility in older community-dwelling persons: A narrative review. Front. Physiol. 11, 881 (2020).
pubmed: 33041836
pmcid: 7522521
doi: 10.3389/fphys.2020.00881
Osoba, M. Y., Rao, A. K., Agrawal, S. K. & Lalwani, A. K. Balance and gait in the elderly: A contemporary review. Laryngosc. Investig. Otolaryngol. 4, 143–153 (2019).
doi: 10.1002/lio2.252
Mirelman, A. et al. Executive function and falls in older adults: New findings from a five-year prospective study link fall risk to cognition. PLoS One 7, e40297 (2012).
pubmed: 22768271
pmcid: 3386974
doi: 10.1371/journal.pone.0040297
Brodie, M. A. et al. Gait as a biomarker? Accelerometers reveal that reduced movement quality while walking is associated with Parkinson’s disease, ageing and fall risk. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. 2014, 5968–5971 (2014).
pubmed: 25571356
Buchman, A. S. et al. Different combinations of mobility metrics derived from a wearable sensor are associated with distinct health outcomes in older adults. J. Gerontol. A Biol. Sci. Med. Sci. 75, 1176–1183 (2020).
pubmed: 31246244
doi: 10.1093/gerona/glz160
Hillel, I. et al. Is every-day walking in older adults more analogous to dual-task walking or to usual walking? Elucidating the gaps between gait performance in the lab and during 24/7 monitoring. Eur. Rev. Aging Phys. Act. 16, 1–12 (2019).
doi: 10.1186/s11556-019-0214-5
Warmerdam, E. et al. Long-term unsupervised mobility assessment in movement disorders. Lancet Neurol. 19, 462–470 (2020).
pubmed: 32059811
doi: 10.1016/S1474-4422(19)30397-7
Feehan, L. M. et al. Accuracy of Fitbit devices: Systematic review and narrative syntheses of quantitative data. JMIR Mhealth Uhealth 6, e10527 (2018).
pubmed: 30093371
pmcid: 6107736
doi: 10.2196/10527
Brodie, M. A. et al. Big data vs accurate data in health research: Large-scale physical activity monitoring, smartphones, wearable devices and risk of unconscious bias. Med. Hypotheses 119, 32–36 (2018).
pubmed: 30122488
doi: 10.1016/j.mehy.2018.07.015
von Coelln, R. et al. Quantitative mobility metrics from a wearable sensor predict incident parkinsonism in older adults. Parkinsonism Relat. Disord. 65, 190–196 (2019).
doi: 10.1016/j.parkreldis.2019.06.012
Wohlrab, M. et al. The value of walking: A systematic review on mobility and healthcare costs. Eur. Rev. Aging Phys. Act. 19(1), 31 (2022).
pubmed: 36581809
pmcid: 9798720
doi: 10.1186/s11556-022-00310-3
Bonci, T., Keogh, A., Din, S. D., Scott, K. & Mazzà, C. An objective methodology for the selection of a device for continuous mobility assessment. Sensors 20, 6509 (2020).
pubmed: 33202608
pmcid: 7696193
doi: 10.3390/s20226509
Kirk, C. et al. Mobilise-D insights to estimate real-world walking speed in multiple conditions with a wearable device. Sci. Rep. 14, 1754 (2024).
pubmed: 38243008
pmcid: 10799009
doi: 10.1038/s41598-024-51766-5
Doherty, A. et al. Large scale population assessment of physical activity using wrist worn accelerometers: The UK Biobank Study. PLoS One 12, e0169649 (2017).
pubmed: 28146576
pmcid: 5287488
doi: 10.1371/journal.pone.0169649
Chan, L. L. Y., Choi, T. C. M., Lord, S. R. & Brodie, M. A. Development and large-scale validation of the watch walk wrist-worn digital gait biomarkers. Sci. Rep. 12, 16211 (2022).
pubmed: 36217013
pmcid: 9551062
doi: 10.1038/s41598-022-20327-z
Leroux, A. et al. Organizing and analyzing the activity data in NHANES. Stat. Biosci. 11, 262–287 (2019).
pubmed: 32047572
pmcid: 7012355
doi: 10.1007/s12561-018-09229-9
Burq, M. et al. Virtual exam for Parkinson’s disease enables frequent and reliable remote measurements of motor function. npj Digit. Med. 5, 65 (2022).
Lim, A. S. P., Kowgier, M., Yu, L., Buchman, A. S. & Bennett, D. A. Sleep fragmentation and the risk of incident Alzheimer’s disease and cognitive decline in older persons. Sleep 36, 1027–1032 (2013).
pubmed: 23814339
pmcid: 3669060
doi: 10.5665/sleep.2802
Cai, R. et al. Circadian disturbances and frailty risk in older adults. Nat. Commun. 14:, 7219 (2023).
pubmed: 37973796
pmcid: 10654720
doi: 10.1038/s41467-023-42727-z
Lin, W. et al. Can gait characteristics be represented by physical activity measured with wrist-worn accelerometers?. Sensors 23, 8542 (2023).
pubmed: 37896635
pmcid: 10611403
doi: 10.3390/s23208542
Zhao, A., Cui, E., Leroux, A., Lindquist, M. A. & Crainiceanu, C. M. Evaluating the prediction performance of objective physical activity measures for incident Parkinson’s disease in the UK Biobank. J. Neurol. 270, 5913–5923 (2023).
pubmed: 37612539
doi: 10.1007/s00415-023-11939-0
Buchman, A. S. et al. Correlates of person-specific rates of change in sensor-derived physical activity metrics of daily living in the rush memory and aging project. Sensors (Basel) 23, 4152 (2023).
Brand, Y. E. et al. Gait detection from a wrist-worn sensor using machine learning methods: A daily living study in older adults and people with Parkinson’s disease. Sensors 22, 7094 (2022).
pubmed: 36146441
pmcid: 9502704
doi: 10.3390/s22187094
Kluge, F. et al. Real-world gait detection using a wrist-worn inertial sensor: Validation study. JMIR Form Res. 8, e50035 (2024).
pubmed: 38691395
pmcid: 11097052
doi: 10.2196/50035
Mirelman, A. et al. Effects of aging on arm swing during gait: The role of gait speed and dual tasking. PLoS One 10, e0136043 (2015).
pubmed: 26305896
pmcid: 4549059
doi: 10.1371/journal.pone.0136043
Keren, K. et al. Quantification of daily-living gait quantity and quality using a wrist-worn accelerometer in Huntington’s disease. Front. Neurol. 12 (2021).
Willetts, M., Hollowell, S., Aslett, L., Holmes, C. & Doherty, A. Statistical machine learning of sleep and physical activity phenotypes from sensor data in 96,220 UK Biobank participants. Sci. Rep. 8, 7961 (2018).
pubmed: 29784928
pmcid: 5962537
doi: 10.1038/s41598-018-26174-1
Soltani, A., Paraschiv-Ionescu, A., Dejnabadi, H., Marques-Vidal, P. & Aminian, K. Real-world gait bout detection using a wrist sensor: An unsupervised real-life validation. IEEE Access 8, 102883–102896 (2020).
doi: 10.1109/ACCESS.2020.2998842
Mazzà, C. et al. Technical validation of real-world monitoring of gait: A multicentric observational study. BMJ Open 11 (2021).
Ronneberger, O., Fischer, P. & Brox, T. U-Net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention—MICCAI 2015. 234–241 (Springer, 2015).
Chen, T., Kornblith, S., Norouzi, M. & Hinton, G. A simple framework for contrastive learning of visual representations. In Proceedings of the International Conference on Machine Learning. 1597–1607 (PMLR, 2020).
Saeed, A., Ozcelebi, T. & Lukkien, J. Multi-task self-supervised learning for human activity detection. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 3, 1–30 (2019).
doi: 10.1145/3328932
Tang, C. I., Perez-Pozuelo, I., Spathis, D. & Mascolo, C. Exploring Contrastive Learning in Human Activity Recognition for Healthcare. Preprint at https://arxiv.org/abs/2011.11542 (2020).
Haresamudram, H., Essa, I. & Plötz, T. Assessing the state of self-supervised human activity recognition using wearables. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 6 (2022).
Haresamudram, H., Essa, I. & Plötz, T. Contrastive predictive coding for human activity recognition. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 5 (2021).
Sridhar, N. & Myers, L. Human Activity Recognition on Wrist-Worn Accelerometers Using Self-Supervised Neural Networks. Preprint at https://arxiv.org/abs/2112.12272 (2021).
Yuan, H. et al. Self-supervised learning for human activity recognition using 700,000 person-days of wearable data. npj Digit. Med. 7, 91 (2024).
Small, S. R. et al. Development and validation of a machine learning wrist-worn step detection algorithm with deployment in the UK Biobank. Preprint at https://doi.org/10.1101/2023.02.20.23285750 (2023).
Bennett, A., Schneider, A., Arvanitakis, J. & Wilson, S. Overview and findings from the religious orders study. Curr. Alzheimer Res. 9, 628–645 (2012).
pubmed: 22471860
pmcid: 3409291
doi: 10.2174/156720512801322573
Bennett, D. A. et al. Religious orders study and rush memory and aging project. J. Alzheimer’s Dis. 64, S161–S189 (2018).
doi: 10.3233/JAD-179939
Bennett, A. et al. Overview and findings from the rush Memory and Aging Project. Curr. Alzheimer Res. 9, 646–663 (2012).
pubmed: 22471867
pmcid: 3439198
doi: 10.2174/156720512801322663
Guralnik, J. M., Ferrucci, L., Simonsick, E. M., Salive, M. E. & Wallace, R. B. Lower-extremity function in persons over the age of 70 years as a predictor of subsequent disability. N. Engl. J. Med. 332, 556–562 (1995).
pubmed: 7838189
pmcid: 9828188
doi: 10.1056/NEJM199503023320902
Latham, N. K. et al. Performance-based or self-report measures of physical function: Which should be used in clinical trials of hip fracture patients?. Arch. Phys. Med. Rehabil. 89, 2146–2155 (2008).
pubmed: 18996244
doi: 10.1016/j.apmr.2008.04.016
Koudouna, S. et al. Rehabilitation prognostic factors following hip fractures associated with patient’s pre-fracture mobility and functional ability: A prospective observation study. Life 13, 1748 (2023).
pubmed: 37629604
pmcid: 10455283
doi: 10.3390/life13081748
Micó-Amigo, M. E. et al. Assessing real-world gait with digital technology? Validation, insights and recommendations from the Mobilise-D consortium. J. NeuroEng. Rehabil. 20, 78. https://doi.org/10.1186/s12984-023-01108-5 (2023).
doi: 10.1186/s12984-023-01108-5
pubmed: 37316858
pmcid: 10265910
Salis, F. et al. A multi-sensor wearable system for the assessment of diseased gait in real-world conditions. Front. Bioeng. Biotechnol. 11 (2023).
Salis, F. et al. A method for gait events detection based on low spatial resolution pressure insoles data. J. Biomech. 127, 110687 (2021).
pubmed: 34455233
doi: 10.1016/j.jbiomech.2021.110687
Soltani, A., Dejnabadi, H., Savary, M. & Aminian, K. Real-world gait speed estimation using wrist sensor: A personalized approach. IEEE J. Biomed. Health Inform. 24, 658–668 (2020).
pubmed: 31059461
doi: 10.1109/JBHI.2019.2914940
Hausdorff, J. M. et al. Everyday stepping quantity and quality among older adult fallers with and without mild cognitive impairment: Initial evidence for new motor markers of cognitive deficits?. J. Gerontol. A Biol. Sci. Med. Sci. 73, 1078–1082 (2018).
pubmed: 29394317
doi: 10.1093/gerona/glx187
Studenski, S. Gait speed and survival in older adults. JAMA 305, 50–58 (2011).
pubmed: 21205966
pmcid: 3080184
doi: 10.1001/jama.2010.1923
Schalkamp, A. K., Peall, K. J., Harrison, N. A. & Sandor, C. Wearable movement-tracking data identify Parkinson’s disease years before clinical diagnosis. Nat. Med. 29, 2048–2056 (2023).
Del Din, S. et al. Falls risk in relation to activity exposure in high-risk older adults. J. Gerontol. Ser. A Biol. Sci. Med. Sci. 75, 1198–1205 (2020).
doi: 10.1093/gerona/glaa007
Fortes Rey, V., Nshimyimana, D. & Lukowicz, P. Don’t freeze: Finetune encoders for better self-supervised HAR. In Adjunct Proceedings of the 2023 ACM International Joint Conference on Pervasive and Ubiquitous Computing and the 2023 ACM International Symposium on Wearable Computing. 195–196 (2023).
van Hees, V. T. et al. Estimation of daily energy expenditure in pregnant and non-pregnant women using a wrist-worn tri-axial accelerometer. PLoS One 6, e22922 (2011).
pubmed: 21829556
pmcid: 3146494
doi: 10.1371/journal.pone.0022922
Sabia, S. et al. Association between questionnaire- and accelerometer-assessed physical activity: The role of sociodemographic factors. Am. J. Epidemiol. 179, 781–790 (2014).
pubmed: 24500862
pmcid: 3939851
doi: 10.1093/aje/kwt330
Bianchini, E. et al. Four days are enough to provide a reliable daily step count in mild to moderate Parkinson’s disease through a commercial smartwatch. Sensors 23, 8971 (2023).
pubmed: 37960670
pmcid: 10649244
doi: 10.3390/s23218971
Buchman, A. S., Boyle, P. A., Leurgans, S. E., Evans, D. A. & Bennett, D. A. Pulmonary function, muscle strength, and incident mobility disability in elders. Proc. Am. Thorac. Soc. 6, 581–587 (2009).
pubmed: 19934353
pmcid: 3132218
doi: 10.1513/pats.200905-030RM
Buchman, A. S. et al. Incident parkinsonism in older adults without Parkinson disease. Neurology 87, 1036–1044 (2016).
pubmed: 27488597
pmcid: 5027813
doi: 10.1212/WNL.0000000000003059
Mhyre, T. R., Boyd, J. T., Hamill, R. W. & Maguire-Zeiss, K. A. Parkinson’s disease. Subcell Biochem. 65, 389–455 (2012).
pubmed: 23225012
pmcid: 4372387
doi: 10.1007/978-94-007-5416-4_16
Buchman, A. S. et al. Associations between quantitative mobility measures derived from components of conventional mobility testing and Parkinsonian gait in older adults. PLoS One 9, e86262 (2014).
pubmed: 24465997
pmcid: 3899223
doi: 10.1371/journal.pone.0086262