Fall prevention; Healthy aging; Machine learning; Tai Chi; Wearable sensor; Humans; Aged; Male; Female; Middle Aged; Tai Ji/methods; Machine Learning; Wearable Electronic Devices; Postural Balance/physiology; Accidental Falls; Aged, 80 and over; Postural Balance; Tai Ji; Multidisciplinary
Abstract :
[en] Tai Chi, an Asian martial art, is renowned for its health benefits, particularly in promoting healthy aging among older adults, improving balance, and reducing fall risk. However, methodological challenges hinder the objective measurement of adherence to and proficiency in performing a training protocol, critical for health outcomes. This study introduces a framework using wearable sensors and machine learning to monitor Tai Chi training adherence and proficiency. Data were collected from 32 participants with inertial measurement units (IMUs) while performing six Tai Chi movements evaluated and scored for adherence and proficiency by experts. Our framework comprises a model for identifying the specific Tai Chi movement being performed and a model to assess performance proficiency, both employing Random Forest algorithms and features from IMU signals. The movement identification model achieved a micro F1 score of 90.05%. The proficiency assessment models achieved a mean micro F1 score of 78.64%. This study shows the feasibility of using IMUs and machine learning for detailed Tai Chi movement analysis, offering a scalable method for monitoring practice. This approach has the potential to objectively enhance the evaluation of Tai Chi training protocol adherence, learnability, progression in proficiency, and safety in Tai Chi programs, and thus inform training program parameters that are key to achieving optimal clinical outcomes.
Disciplines :
Human health sciences: Multidisciplinary, general & others
Author, co-author :
Corniani, Giulia; Department of Physical Medicine and Rehabilitation, Harvard Medical School and Spaulding Rehabilitation Hospital, Boston, MA, USA
SAPIENZA, Stefano ; University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > Digital Medicine ; Department of Physical Medicine and Rehabilitation, Harvard Medical School and Spaulding Rehabilitation Hospital, Boston, MA, USA ; Luxembourg Institute of Health (LIH), Strassen, Luxembourg
Vergara-Diaz, Gloria; Department of Physical Medicine and Rehabilitation, Harvard Medical School and Spaulding Rehabilitation Hospital, Boston, MA, USA ; Department of Physical Medicine and Rehabilitation, Virgen del Rocio University Hospital, Seville, Spain
Valerio, Andrea; Department of Electronics and Telecommunications, Politecnico di Torino, Torino, Italy
Vaziri, Ashkan; BioSensics LLC, Newton, MA, USA
Bonato, Paolo; Department of Physical Medicine and Rehabilitation, Harvard Medical School and Spaulding Rehabilitation Hospital, Boston, MA, USA
Wayne, Peter M; Osher Center for Integrative Health, Harvard Medical School and Brigham and Women's Hospital, Boston, MA, USA. pwayne@bwh.harvard.edu
External co-authors :
yes
Language :
English
Title :
Remote monitoring of Tai Chi balance training interventions in older adults using wearable sensors and machine learning.
National Institutes of Health National Center for Complementary and Integrative Health
Funding text :
The study was supported by the grant titled \u201DMobile Tai Chi Platform for Fall Prevention in Older Adults\u201D awarded by National Institutes of Health (award number R42AG059491). Dr. Peter Wayne received the K24 AT009282 from the National Center for Complementary and Integrative Health (NCCIH) and the National Institutes of Health (NIH). The authors would like to acknowledge Francesco P. Bertacchi, Daniel Litrownik, and the whole team at the Motion Analysis Lab at Spaulding Rehabilitation Hospital for the assistance provided during data collection.
R. Lauche P.M. Wayne G. Dobos H. Cramer Prevalence, patterns, and predictors of t’ai chi and qigong use in the united states: Results of a nationally representative survey J. Altern. Complement. Med. 22 336 342 26981616
G.S. Birdee P.M. Wayne R.B. Davis R.S. Phillips G.Y. Yeh T’ai chi and qigong for health: Patterns of use in the united states J. Altern. Complement. Med. 15 969 973 19757974 2852519
T.C. Clarke L.I. Black B.J. Stussman P.M. Barnes R.L. Nahin Trends in the use of complementary health approaches among adults: United states, 2002–2012 Natl. Health Stat. Rep. 1 1 16
B.J. Stussman L.I. Black P.M. Barnes T.C. Clarke R.L. Nahin Wellness-related use of common complementary health approaches among adults: United states, 2012 Natl. Health Stat. Rep. 1 1 12
S.L. Wolf C. Coogler T. Xu Exploring the basis for tai chi chuan as a therapeutic exercise approach Arch. Phys. Med. Rehabil. 78 886 892 1:STN:280:DyaK1c%2Fgt12qtQ%3D%3D 9344312 1396.22005
P.M. Wayne et al. Complexity-based measures inform effects of tai chi training on standing postural control: Cross-sectional and randomized trial studies PLoS ONE 9 2014PLoSO..9k4731W 25494333 4262457 e114731
W. Chen M. Li H. Li Y. Lin Z. Feng Tai chi for fall prevention and balance improvement in older adults: A systematic review and meta-analysis of randomized controlled trials Front. Public Health 11 1236050 37736087 10509476 07735651
A. Hall et al. Effectiveness of tai chi for chronic musculoskeletal pain conditions: Updated systematic review and meta-analysis Phys. Ther. 97 227 238 27634919 07278987
X. Li et al. Effect of tai chi vs aerobic exercise on blood pressure in patients with prehypertension: A randomized clinical trial JAMA Netw. Open 7 38335001 10858403 e2354937
F. Li P. Harmer E. Eckstrom K. Fitzgerald K. Winters-Stone Clinical effectiveness of cognitively enhanced tai ji quan training on global cognition and dual-task performance during walking in older adults with mild cognitive impairment or self-reported memory concerns: A randomized controlled trial Ann. Intern. Med. 176 1498 1507 37903365
Lyu, L., Li, Y., Fan, X., Seo, J. & Oh, E. The effect of tai chi exercise intervention on sleep quality in community residing older adults: A systematic review and meta-analysis. Eur. Geriatr. Med. (2024).
Y. Dong et al. The effects of mind-body exercise on anxiety and depression in older adults: A systematic review and network meta-analysis Front. Psych. 15 1305295
J. Lin et al. The effects of different types of tai chi exercises on preventing falls in older adults: A systematic review and network meta-analysis Aging Clin. Exp. Res. 36 65 38472538 10933200 10.1007/s40520-023-02674-7
C. Sherrington et al. Exercise for preventing falls in older people living in the community: An abridged cochrane systematic review Br. J. Sports Med. 54 885 891 31792067 1194.82002 10.1136/bjsports-2019-101512
S.R. Nyman Tai chi for the prevention of falls among older adults: A critical analysis of the evidence J. Aging Phys. Act. 29 343 352 32839351 1481.16012
Li, F. et al. Effectiveness of tai ji quan vs multimodal and stretching exercise interventions for reducing injurious falls in older adults at high risk of falling: Follow-up analysis of a randomized clinical trial. JAMA Netw. Open 2, e188280. https://doi.org/10.1001/jamanetworkopen.2018.8280 (2019). Erratum in: JAMA Network Open. 2019 Mar 1;2(3). https://doi.org/10.1001/jamanetworkopen.2019.2314.
F. Li et al. Effectiveness of a therapeutic tai ji quan intervention vs a multimodal exercise intervention to prevent falls among older adults at high risk of falling: A randomized clinical trial JAMA Intern. Med. 178 1301 1310 2018kepa.book...L 30208396 6233748 1418.11078 10.1001/jamainternmed.2018.3915
Z.-G. Huang Y.-H. Feng Y.-H. Li C.-S. Lv Systematic review and meta-analysis: Tai chi for preventing falls in older adults BMJ Open 7 28167744 5293999 1380.05133 e013661
R. Lomas-Vega E. Obrero-Gaitán F.J. Molina-Ortega R. Del-Pino-Casado Tai chi for risk of falls: A meta-analysis J. Am. Geriatr. Soc. 65 2037 2043 28736853 10.1111/jgs.15008
F. Li et al. Translation of an effective tai chi intervention into a community-based falls-prevention program Am. J. Public Health 98 1195 1198 18511723 2424086 1347.37075
J.L. Teo S.R. Bird X. Wang Z. Zheng Using telehealth to deliver qi gong and tai chi programs: A mixed-methods systematic review on feasibility, acceptability and participant engagement factors Arch. Gerontol. Geriatr. 117 37741135 1520.81163 105203
J. Gravesande et al. Feasibility, usability, and acceptability of online mind-body exercise programs for older adults: A scoping review J. Integr. Complement. Med. 29 538 549 36944159 10.1089/jicm.2022.0822
C. Ritz F. Baty J.C. Streibig D. Gerhard Dose-response analysis using r PLoS ONE 10 26717316 4696819 1426.62008 e0146021
P.M. Wayne T.J. Kaptchuk Challenges inherent to t’ai chi research: Part i-t’ai chi as a complex multicomponent intervention J. Altern. Complement. Med. 14 95 102 18199021
P.M. Wayne T.J. Kaptchuk Challenges inherent to t’ai chi research: Part ii-defining the intervention and optimal study design J. Altern. Complement. Med. 14 191 197 18446928
C. Wang et al. Tai chi on psychological well-being: Systematic review and meta-analysis BMC Complement. Altern. Med. 10 23 20492638 2893078 1206.05045
Y. Ma et al. Long-term tai chi practice in older adults is associated with “younger” functional abilities Aging Cell 23 1:CAS:528:DC%2BB3sXit12ntb%2FF 37905388 e14023
S.Y. Lee et al. Association of tai chi exercise with physical and neurocognitive functions, frailty, quality of life and mortality in older adults: Singapore longitudinal ageing study Age Ageing 51 1 10
C. Man-Ch’ing R.W. Smith T’ai Chi: The “Supreme Ultimate” Exercise for Health, Sport, and Self-Defense Tuttle Publishing
S. Wei Z. Wu The application of wearable sensors and machine learning algorithms in rehabilitation training: A systematic review Sensors 23 7667 2023Senso.23.7667W 37765724 10537628 1380.93123
A.L. Shaver et al. Trends in fall-related mortality and fall risk increasing drugs among older individuals in the united states, 1999–2017 Pharmacoepidemiol. Drug Saf. 30 1049 1056 33534172 8254780 1398.03161 10.1002/pds.5201
S.A. Drake et al. When falls become fatal-clinical care sequence PLoS ONE 16 1:CAS:528:DC%2BB3MXhtlSlsrs%3D 33406164 7787527 10.1371/journal.pone.0244862 e0244862
S.L. James et al. The global burden of falls: Global, regional and national estimates of morbidity and mortality from the global burden of disease study 2017 Inj. Prev. 26 i3 i11 31941758 1334.94010 10.1136/injuryprev-2019-043286
M.E. Tinetti C.S. Williams Falls, injuries due to falls, and the risk of admission to a nursing home N. Engl. J. Med. 337 1279 1284 1:STN:280:DyaK2svnsFyguw%3D%3D 9345078 10.1056/NEJM199710303371806
Hedegaard, H., Minino, A. M. & Warner, M. Drug overdose deaths in the united states, 1999–2018. NCHS Data Brief 1–8 (2020).
American Geriatrics Society Pharmacological management of persistent pain in older persons J. Am. Geriatr. Soc. 57 1331 1346 1213.35388 10.1111/j.1532-5415.2009.02376.x
M. Liu et al. Fear of falling is as important as multiple previous falls in terms of limiting daily activities: A longitudinal study BMC Geriatr. 21 350 34098904 8185919 1483.93687 10.1186/s12877-021-02305-8
M. Montero-Odasso et al. New horizons in falls prevention and management for older adults: A global initiative Age Ageing 34038522 1122.60059 10.1093/ageing/afab076
G.A. Zijlstra et al. Prevalence and correlates of fear of falling, and associated avoidance of activity in the general population of community-living older people Age Ageing 36 304 309 1:STN:280:DC%2BD2s3ls1OgtQ%3D%3D 17379605 0511.90067 10.1093/ageing/afm021
K. Delbaere G. Crombez G. Vanderstraeten T. Willems D. Cambier Fear-related avoidance of activities, falls and physical frailty: A prospective community-based cohort study Age Ageing 33 368 373 15047574 10.1093/ageing/afh106
C.S. Florence et al. Medical costs of fatal and nonfatal falls in older adults J. Am. Geriatr. Soc. 66 693 698 29512120 6089380 0885.60015 10.1111/jgs.15304
Centers for Disease Control and Prevention. What you can do to prevent falls. Accessed 22 July 2024.
A. Haleem M. Javaid R.P. Singh R. Suman Telemedicine for healthcare: Capabilities, features, barriers, and applications Sens. Int. 2 34806053 8590973 100117
R. Lauche et al. The effects of tai chi and neck exercises in the treatment of chronic nonspecific neck pain: A randomized controlled trial J. Pain 17 1013 1027 27345663 1352.14008
Li, F. et al. Effectiveness of tai ji quan vs multimodal and stretching exercise interventions for reducing injurious falls in older adults at high risk of falling: Follow-up analysis of a randomized clinical trial. JAMA Network Open 2, e188280. https://doi.org/10.1001/jamanetworkopen.2018.8280 (2019). Erratum in: JAMA Network Open. 2019 Mar 1;2(3):e192314. https://doi.org/10.1001/jamanetworkopen.2019.2314.
S.R. Nyman Tai chi for the prevention of falls among older adults: A critical analysis of the evidence J. Aging Phys. Activity 29 343 352 1481.16012 10.1123/japa.2020-0155
S. Subramaniam et al. Grand challenges at the interface of engineering and medicine IEEE Open J. Eng. Med. Biol. 5 1 13 4700138 38415197 07969453
C. Zheng et al. Deep learning-based human pose estimation: A survey ACM Comput. Surv. 56 1 37 1517.74056
Bonato, P., Feipel, V., Corniani, G., Arin-Bal, G. & Leardini, A. Position paper on how technology for human motion analysis and relevant clinical applications have evolved over the past decades: Striking a balance between accuracy and convenience. Gait and Posture (2024).
Zhang, S. et al. Deep learning in human activity recognition with wearable sensors: A review on advances. Sensors22 (2022).
Crema, C. et al. Imu-based solution for automatic detection and classification of exercises in the fitness scenario. In booktitle2017 IEEE Sensors Applications Symposium (SAS), 1–6 (IEEE, 2017).
J. McGrath J. Neville T. Stewart J. Cronin Upper body activity classification using an inertial measurement unit in court and field-based sports: A systematic review Proc. Inst. Mech. Eng. P 235 83 95 1470.53047
Airaksinen, M., Vanhatalo, S. & Räsänen, O. Comparison of end-to-end neural network architectures and data augmentation methods for automatic infant motility assessment using wearable sensors. Sensors23 (2023).
H. Peng F. Long C. Ding Feature selection based on mutual information: Criteria of max-dependency, max-relevance, and min-redundancy IEEE Trans. Pattern Anal. Mach. Intell. 27 1226 1238 16119262 1399.05059
L. Breiman Random forests Mach. Learn. 45 5 32 1007.68152
S. Patel et al. A novel approach to monitor rehabilitation outcomes in stroke survivors using wearable technology Proc. IEEE 98 450 461 1475.34003
F. Parisi et al. Motor assessment of x-linked dystonia parkinsonism via machine-learning-based analysis of wearable sensor data Sci. Rep. 14 13229 2024NatSR.1413229P 1:CAS:528:DC%2BB2cXhsVahu7nM 38853162 11162996
