Development and Clinical Evaluation of a Web-Based Upper Limb Home Rehabilitation System Using a Smartwatch and Machine Learning Model for Chronic Stroke Survivors: Prospective Comparative Study
Open accessPublished version of a preprint
Abstract
BACKGROUND: Recent advancements in wearable sensor technology have shown the feasibility of remote physical therapy at home. In particular, the current COVID-19 pandemic has revealed the need and opportunity of internet-based wearable technology in future health care systems. Previous research has shown the feasibility of human activity recognition technologies for monitoring rehabilitation activities in home environments; however, few comprehensive studies ranging from development to clinical evaluation exist. OBJECTIVE: This study aimed to (1) develop a home-based rehabilitation (HBR) system that can recognize and record the type and frequency of rehabilitation exercises conducted by the user using a smartwatch and smartphone app equipped with a machine learning (ML) algorithm and (2) evaluate the efficacy of the home-based rehabilitation system through a prospective comparative study with chronic stroke survivors. METHODS: The HBR system involves an off-the-shelf smartwatch, a smartphone, and custom-developed apps. A convolutional neural network was used to train the ML algorithm for detecting home exercises. To determine the most accurate way for detecting the type of home exercise, we compared accuracy results with the data sets of personal or total data and accelerometer, gyroscope, or accelerometer combined with gyroscope data. From March 2018 to February 2019, we conducted a clinical study with two groups of stroke survivors. In total, 17 and 6 participants were enrolled for statistical analysis in the HBR group and control group, respectively. To measure clinical outcomes, we performed the Wolf Motor Function Test (WMFT), Fugl-Meyer Assessment of Upper Extremity, grip power test, Beck Depression Inventory, and range of motion (ROM) assessment of the shoulder joint at 0, 6, and 12 months, and at a follow-up assessment 6 weeks after retrieving the HBR system. RESULTS: The ML model created with personal data involving accelerometer combined with gyroscope data (5590/5601, 99.80%) was the most accurate compared with accelerometer (5496/5601, 98.13%) or gyroscope data (5381/5601, 96.07%). In the comparative study, the drop-out rates in the control and HBR groups were 40% (4/10) and 22% (5/22) at 12 weeks and 100% (10/10) and 45% (10/22) at 18 weeks, respectively. The HBR group (n=17) showed a significant improvement in the mean WMFT score (P=.02) and ROM of flexion (P=.004) and internal rotation (P=.001). The control group (n=6) showed a significant change only in shoulder internal rotation (P=.03). CONCLUSIONS: This study found that a home care system using a commercial smartwatch and ML model can facilitate participation in home training and improve the functional score of the WMFT and shoulder ROM of flexion and internal rotation in the treatment of patients with chronic stroke. This strategy can possibly be a cost-effective tool for the home care treatment of stroke survivors in the future. TRIAL REGISTRATION: Clinical Research Information Service KCT0004818; https://tinyurl.com/y92w978t.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Convolutional Neural Network architectures were employed in included works.
“Another ANN architecture that was employed is Convolutional Neural Network (CNN) Architectures [43,45,50,54].”
From Wearable sensors and machine learning in post-stroke rehabilitation assessment: A systematic review (2022) · cites this paper as [45]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Johnson, C. O., Nguyen, M., Roth, G. A., Nichols, E. L., Alam, S., Abate, D., Abd-Allah, F., Abdelalim, A., Abraha, H. N., Abu-Rmeileh, N. M., et al. (2019) · The Lancet Neurology · doi:10.1016/s1474-4422(19)30034-1 · Cited by 3,324 · see citing works
Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition
Ordóñez, F., & Roggen, D. (2016) · Sensors · doi:10.3390/s16010115 · Cited by 2,761 · see citing works
Probability of Regaining Dexterity in the Flaccid Upper Limb
Kwakkel, G., Kollen, B. J., van der Grond, J., & Prevo, A. J. H. (2003) · Stroke · doi:10.1161/01.str.0000087172.16305.cd · Cited by 1,409 · see citing works
Robot-Assisted Therapy for Long-Term Upper-Limb Impairment after Stroke
Lo, A. C., Guarino, P. D., Richards, L. G., Haselkorn, J. K., Wittenberg, G. F., Federman, D. G., Ringer, R. J., Wagner, T. H., Krebs, H. I., Volpe, B. T., et al. (2010) · New England Journal of Medicine · doi:10.1056/nejmoa0911341 · Cited by 1,397 · see citing works
Assessing Wolf Motor Function Test as Outcome Measure for Research in Patients After Stroke
Wolf, S. L., Catlin, P. A., Ellis, M. D., Archer, A. L., Morgan, B., & Reiss, A. (2001) · Stroke · doi:10.1161/01.str.32.7.1635 · Cited by 1,053 · see citing works
Risk and Cumulative Risk of Stroke Recurrence: A Systematic Review and Meta-Analysis
Mohan, K. M., Wolfe, C. D. A., Rudd, A. G., Heuschmann, P. U., Kolominsky-Rabas, P. L., & Grieve, A. P. (2011) · Stroke · doi:10.1161/strokeaha.110.602615 · Cited by 683 · see citing works
Measuring and Influencing Physical Activity with Smartphone Technology: A Systematic Review
Roig, J. B., Gilson, N. D., Puig-Ribera, A. M., Contreras-Espinosa, R. S., & Trost, S. G. (2014) · Sports Medicine · doi:10.1007/s40279-014-0142-5 · Cited by 554 · see citing works
Activity recognition on streaming sensor data
Krishnan, N. C., & Cook, D. J. (2014) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2012.07.003 · Cited by 488 · see citing works
Patrick, H., & Williams, G. C. (2012) · International Journal of Behavioral Nutrition and Physical Activity · doi:10.1186/1479-5868-9-18 · Cited by 481 · see citing works
Economic burden of stroke: a systematic review on post-stroke care
Rajšić, S., Gothe, H., Borba, H. H. L., Sroczynski, G., Vujičić, J., Toell, T., & Siebert, U. (2018) · The European Journal of Health Economics · doi:10.1007/s10198-018-0984-0 · Cited by 479 · see citing works
Systematic review of Kinect applications in elderly care and stroke rehabilitation
Webster, D., & Celik, O. (2014) · Journal of NeuroEngineering and Rehabilitation · doi:10.1186/1743-0003-11-108 · Cited by 436 · see citing works
Health at hand: A systematic review of smart watch uses for health and wellness
Reeder, B., & David, A. (2016) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2016.09.001 · Cited by 412 · see citing works
The effects of socioeconomic status on stroke risk and outcomes
Marshall, I. J., Wang, Y., Crichton, S. L., McKevitt, C., Rudd, A. G., & Wolfe, C. D. A. (2015) · The Lancet Neurology · doi:10.1016/s1474-4422(15)00200-8 · Cited by 408 · see citing works
Neural plasticity and bilateral movements: A rehabilitation approach for chronic stroke
Cauraugh, J. H., & Summers, J. J. (2005) · Progress in Neurobiology · doi:10.1016/j.pneurobio.2005.04.001 · Cited by 405 · see citing works
A Deep Learning Approach to Human Activity Recognition Based on Single Accelerometer
Chen, Y., & Xue, Y. (2015) · 2015 IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2015.263 · Cited by 378 · see citing works
Interactive wearable systems for upper body rehabilitation: a systematic review
Wang, Q., Markopoulos, P., Yu, B., Chen, W., & Timmermans, A. A. A. (2017) · Journal of NeuroEngineering and Rehabilitation · doi:10.1186/s12984-017-0229-y · Cited by 350 · see citing works
Swayne, O. B. C., Rothwell, J. C., Ward, N., & Greenwood, R. (2008) · Cerebral Cortex · doi:10.1093/cercor/bhm218 · Cited by 308 · see citing works
Telerehabilitation in stroke care – a systematic review
Johansson, T., & Wild, C. (2011) · Journal of Telemedicine and Telecare · doi:10.1258/jtt.2010.100105 · Cited by 288 · see citing works
Legg, L. A., & Langhorne, P. (2004) · The Lancet · doi:10.1016/s0140-6736(04)15434-2 · Cited by 251 · see citing works
Sackley, C. M., Brittle, N., Patel, S., Ellins, J., Scott, M. A., Wright, C., & Dewey, M. E. (2008) · Stroke · doi:10.1161/strokeaha.108.518563 · Cited by 247 · see citing works
Additional Virtual Reality Training Using Xbox Kinect in Stroke Survivors with Hemiplegia
Sin, H., & Lee, G. (2013) · American Journal of Physical Medicine & Rehabilitation · doi:10.1097/phm.0b013e3182a38e40 · Cited by 226 · see citing works
Smartwatch-based activity recognition: A machine learning approach
Weiss, G. M., Timko, J. L., Gallagher, C. M., Yoneda, K., & Schreiber, A. J. (2016) · IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI ...) · doi:10.1109/bhi.2016.7455925 · Cited by 209 · see citing works
Kim, Y., Huang, J., & Emery, S. (2016) · Journal of Medical Internet Research · doi:10.2196/jmir.4738 · Cited by 178 · see citing works
Self-citationDenno, M. S., Gillard, P. J., Graham, G. D., DiBonaventura, M., Goren, A., Varon, S. F., & Zorowitz, R. D. (2013) · Archives of Physical Medicine and Rehabilitation · doi:10.1016/j.apmr.2013.03.014 · Cited by 157 · see citing works
Therapeutic Exercise and Depressive Symptoms After Stroke
Lai, S., Studenski, S. A., Richards, L. G., Perera, S., Reker, D. M., Rigler, S. K., & Duncan, P. W. (2005) · Journal of the American Geriatrics Society · doi:10.1111/j.1532-5415.2006.00573.x · Cited by 151 · see citing works
A Consensus on Stroke: Early Supported Discharge
Fisher, R. J., Gaynor, C., Kerr, M., Langhorne, P., Anderson, C., Bautz-Holter, E., Indredavik, B., Mayo, N. E., Power, M., Rodgers, H., et al. (2011) · Stroke · doi:10.1161/strokeaha.110.606285 · Cited by 148 · see citing works
Optimization of an Accelerometer and Gyroscope-Based Fall Detection Algorithm
Huynh, Q. T., Nguyen, U. D., Irazabal, L. B., Ghassemian, N., & Tran, B. Q. (2015) · Journal of Sensors · doi:10.1155/2015/452078 · Cited by 134 · see citing works
Thorsén, A.-M., Holmqvist, L. W., de Pedro-Cuesta, J., & von Koch, L. (2004) · Stroke · doi:10.1161/01.str.0000152288.42701.a6 · Cited by 132 · see citing works
A Rehabilitation-Internet-of-Things in the Home to Augment Motor Skills and Exercise Training
Dobkin, B. H. (2016) · Neurorehabilitation and neural repair · doi:10.1177/1545968316680490 · Cited by 130 · see citing works
Boysen, G., Krarup, L.-H., Zeng, X., Oskedra, A., Kõrv, J., Andersen, G., Gluud, C. N., Pedersen, A., Lindahl, M., Hansen, L., et al. (2009) · BMJ · doi:10.1136/bmj.b2810 · Cited by 128 · see citing works
Ada, L., Goddard, E., McCully, J., Stavrinos, T. M., & Bampton, J. (2005) · Archives of Physical Medicine and Rehabilitation · doi:10.1016/j.apmr.2004.02.031 · Cited by 127 · see citing works
Margarito, J., Helaoui, R., Bianchi, A., Sartor, F., & Bonomi, A. (2015) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2015.2471094 · Cited by 118 · see citing works
Cameron, J. I., Cheung, A. M., Streiner, D. L., Coyte, P. C., & Stewart, D. E. (2010) · Stroke · doi:10.1161/strokeaha.110.597963 · Cited by 102 · see citing works
Um, T. T., Babakeshizadeh, V., & Kulić, D. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8206051 · Cited by 89 · see citing works
Chen, P.-M., Kwong, P. W.-H., Lai, C. K. Y., & Ng, S. S. M. (2019) · PLoS ONE · doi:10.1371/journal.pone.0216357 · Cited by 79 · see citing works
Wilkins, K. B., Owen, M., Ingo, C., Carmona, C., Dewald, J. P. A., & Yao, J. (2017) · Frontiers in Neurology · doi:10.3389/fneur.2017.00284 · Cited by 78 · see citing works
Rehabilitation – a new approach. Part four: a new paradigm, and its implications
Wade, D. T. (2015) · Clinical Rehabilitation · doi:10.1177/0269215515601177 · Cited by 76 · see citing works
Visser‐Meily, A., Post, M. W. M., van de Port, I. G. L., Heugten, C. M. V., & van den Bos, T. (2008) · Patient Education and Counseling · doi:10.1016/j.pec.2008.03.011 · Cited by 74 · see citing works
Determining the Single Best Axis for Exercise Repetition Recognition and Counting on SmartWatches
Mortazavi, B. J., Pourhomayoun, M., Alsheikh, G., Alshurafa, N. I., Lee, S. I., & Sarrafzadeh, M. (2014) · Wearable and Implantable Body Sensor Networks · doi:10.1109/bsn.2014.21 · Cited by 67 · see citing works
Hsieh, Y., Chang, K., Hung, J.-W., Wu, C., Fu, M., & Chen, C.-C. (2018) · Archives of Physical Medicine and Rehabilitation · doi:10.1016/j.apmr.2018.03.017 · Cited by 64 · see citing works
Chaiyawat, P., & Kulkantrakorn, K. (2012) · Psychogeriatrics · doi:10.1111/j.1479-8301.2012.00412.x · Cited by 39 · see citing works
Neuro-Behavioral Determinants of Interlimb Coordination
Swinnen, S., & Duysens, J. (2004) · Springer US · doi:10.1007/978-1-4419-9056-3 · Cited by 38 · see citing works
A Deep Learning Approach for Privacy Preservation in Assisted Living
Psychoula, I., Merdivan, E., Singh, D., Chen, L., Chen, F., Hanke, S., Kropf, J., Holzinger, A., & Geist, M. (2018) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomw.2018.8480247 · Cited by 38 · see citing works
Markopoulos, P., Timmermans, A. A. A., Beursgens, L., van Donselaar, R., & Seelen, H. A. M. (2011) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/iembs.2011.6091283 · Cited by 36 · see citing works
Ramezani, R., Zhang, W., Xie, Z., Shen, J., Elashoff, D. A., Roberts, P. S., Stanton, A. L., Eslami, M. S., Wenger, N. S., Sarrafzadeh, M., et al. (2019) · JMIR mhealth and uhealth · doi:10.2196/14090 · Cited by 32 · see citing works
Lee, K.-S., Chae, S. H., & Park, H. (2019) · International Conference on Rehabilitation Robotics · doi:10.1109/icorr.2019.8779475 · Cited by 27 · see citing works
Self-citationWenderoth, N., Debaere, F., & Swinnen, S. P. (2004) · Springer eBooks · doi:10.1007/978-1-4419-9056-3_8 · Cited by 21 · see citing works
Holden, A., McNaney, R., Balaam, M., Thompson, R. J., Hammerla, N., Plötz, T., Jackson, D., Price, C., Brkic, L., & Olivier, P. L. (2015) · British HCI Conference · doi:10.1145/2783446.2783576 · Cited by 17 · see citing works
Citizen centered health and lifestyle management via interactive TV: The PANACEIA-ITV health system.
Maglaveras, N., Chouvarda, I., Koutkias, V. G., et al. (2003) · PubMed · Cited by 12 · see citing works
Home-Based Physical Therapy for Individuals With Stroke in Thailand
Hiengkaew, V., & Vongsirinavarat, M. (2016) · Home Health Care Management & Practice · doi:10.1177/1084822316630278 · Cited by 9 · see citing works
Flagged first, then by citations
Research works printed but not linked: 4
- [20]Miyoshi H Kimura Y Tamura T Sekine M Okabe I Hara K Smart Living - Home Rehabilitation Training System Using an Interactive Television 2015 6th European Conference of the International Federation for Medical and Biological Engineering September 7-11, 2014 Dubrovnik, Croatia 661 665
- [27]Singh D Human Activity Recognition Using Recurrent Neural Networks Machine Learning and Knowledge Extraction 2017 International Cross-Domain Conference for Machine Learning and Knowledge Extraction 29 August-1 September Reggio, Italy 267 274
- [48]Holden A McNaney R Balaam M Thompson R Hammerla N Ploetz T CueS: cueing for upper limb rehabilitation in stroke 2015 British HCI 2015: 2015 British Human Computer Interaction Conference July 2015 Lincoln Lincolnshire, United Kingdom
- [49]Singh D Users’ Perceptions and Attitudes Towards Smart Home Technologies 2018 16th International Conference, ICOST 2018 July 10-12, 2018 Singapore
Cited by
Sorted by citations
Wearable sensors and machine learning in post-stroke rehabilitation assessment: A systematic review
Boukhennoufa, I., Zhai, X., Utti, V., Jackson, J., & McDonald-Maier, K. D. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.103197 · Cited by 180 · see citing works
“The US, is the country with most publications with thirteen papers [46,47,49,52,54,58, 64–67,69,70,73] followed by china with four papers [41,51,53,68], three papers for South Korea [45,61,74] and Italy [55–57], two papers for the UK [50,71] and Thailand [59,60] and finally a single study for France [42], India [43],…”
BackgroundMethodResultInfluentialKhoshrounejad, F., Hamednia, M., Mehrjerd, A., Pichaghsaz, S., Jamalirad, H., Sargolzaei, M., Hoseini, B., & Aalaei, S. (2021) · Frontiers in Public Health · doi:10.3389/fpubh.2021.711762 · Cited by 174 · see citing works
- Authors
- Chae, S. H., Kim, Y., Lee, K.-S., & Park, H.-S.
- Affiliations
- Korea Advanced Institute of Science and Technology (KR)
- Cheongju University (KR)
- Corresponding author
- Park, Hyung-Soon
- Venue
- JMIR mHealth and uHealth
- Publisher
- JMIR Publications Inc.
- Published
- 2020-07-09
- Volume
- 8
- Issue
- 7
- Pages
- e17216
- ISSN
- 2291-5222 (ISSN-L)
- PMC
- PMC7380903
- OpenAlex
- W3024384408
- Cited by
- 235
- References
- 50
- Citations by year
- 2026: 31 · 2025: 41 · 2024: 52 · 2023: 51 · 2022: 43 · 2021: 16 · 2020: 1
- FWCI
- 15.38
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- Locations
- JMIR mhealth and uhealth (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Health Sciences › Medicine › Rehabilitation › Stroke Rehabilitation and Recovery
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Health Sciences › Health Professions › General Health Professions › Mobile Health and mHealth Applications
- Keywords
- home-based rehabilitation, chronic stroke, upper limb rehabilitation, smartwatches, wearable sensors, activity recognition, exercise detection, convolutional neural networks, remote physical therapy, mobile application, stroke survivors, motor recovery, depression, patient dropout, telemedicine, COVID-19 pandemic, Wolf Motor Function Test, Fugl-Meyer Assessment of the Upper Extremity
- MeSH terms
- Telerehabilitation, Machine Learning, Stroke Rehabilitation, Wearable Electronic Devices, Aged, Chronic Disease, Exercise Therapy, Home Care Services, Humans, Middle Aged, Models, Theoretical, Prospective Studies, Treatment Outcome, Survivors, Internet, Stroke, Upper Extremity, Mobile Applications
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
