Automatic identification of upper extremity rehabilitation exercise type and dose using body-worn sensors and machine learning: A pilot study
Open accessPublished version of a preprint
Abstract
BACKGROUND: Prior studies suggest that participation in rehabilitation exercises improves motor function poststroke; however, studies on optimal exercise dose and timing have been limited by the technical challenge of quantifying exercise activities over multiple days. OBJECTIVES: The objectives of this study were to assess the feasibility of using body-worn sensors to track rehabilitation exercises in the inpatient setting and investigate which recording parameters and data analysis strategies are sufficient for accurately identifying and counting exercise repetitions. METHODS: = 13) while the subjects performed 3 preselected arm exercises. Sensor data were then labeled by exercise type and this labeled data set was used to train a machine learning classification algorithm for identifying exercise type. The machine learning algorithm and a peak-finding algorithm were used to count exercise repetitions in non-labeled data sets. RESULTS: We achieved a repetition counting accuracy of 95.6% overall, and 95.0% in patients with upper extremity weakness due to stroke when using both accelerometer and gyroscope data. Accuracy was decreased when using fewer sensors or using accelerometer data alone. CONCLUSIONS: Our exploratory study suggests that body-worn sensor systems are technically feasible, well tolerated in subjects with recent stroke, and may ultimately be useful for developing a system to measure total exercise "dose" in poststroke patients during clinical rehabilitation or clinical trials.
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?
Balestra et al. identified different executed tasks to count repetitions and determine a correlation with the degree of severity of stroke.
“Balestra et.al [64], identified different executed tasks in order to count the number of repetitions and determine a correlation with the degree of severity of stroke.”
From Wearable sensors and machine learning in post-stroke rehabilitation assessment: A systematic review (2022) · cites this paper as [64]
The Introduction and Abstract describe identifying three upper-extremity exercise types and counting repetitions. The Gyro+Accel section reports participants’ arm-strength scores alongside counting accuracy, but does not determine a correlation between the executed tasks or repetitions and stroke severity. (LLM, conf=0.88)
Experimental — accuracy not yet measuredk-Nearest Neighbour was used in three included works.
“k-Nearest Neighbour (kNN) is another algorithm that was used in three included works [64,51,46].”
From Wearable sensors and machine learning in post-stroke rehabilitation assessment: A systematic review (2022) · cites this paper as [64]
In study [64], the Fine KNN model achieved 98.5% accuracy.
“Fine KNN 98.5%”
From Wearable sensors and machine learning in post-stroke rehabilitation assessment: A systematic review (2022) · cites this paper as [64]
A single included paper used the National Institutes of Health Stroke Scale.
“A single included paper [64] used this assessment system.”
From Wearable sensors and machine learning in post-stroke rehabilitation assessment: A systematic review (2022) · cites this paper as [64]
The Methods: Participants and Inclusion/Exclusion Criteria section identifies the Medical Research Council (MRC) strength scale, and the Results: Participants passage reports participants’ mean MRC score (page numbers unavailable). A search for “National Institutes of Health Stroke Scale” and “NIHSS” found no passage saying this study used that assessment. Use of the MRC scale does not rule out use of another scale. (LLM, conf=0.76)
Experimental — accuracy not yet measured
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
Heart Disease and Stroke Statistics—2019 Update: A Report From the American Heart Association
Benjamin, E. J., Muntner, P., Alonso, A., Bittencourt, M. S., Callaway, C. W., Carson, A. P., Chamberlain, A. M., Chang, A. R., Cheng, S., Das, S. R., et al. (2019) · Circulation · doi:10.1161/cir.0000000000000659 · Cited by 9,036 · see citing works
Heart Disease and Stroke Statistics—2015 Update: A Report From the American Heart Association
Mozaffarian, D., Benjamin, E. J., Go, A. S., Arnett, D. K., Blaha, M. J., Cushman, M., de Ferranti, S., Després, J.-P., Fullerton, H. J., Howard, V. J., et al. (2015) · Circulation · doi:10.1161/cir.0000000000000152 · Cited by 5,797 · see citing works
Winstein, C. J., Stein, J., Arena, R., Bates, B., Cherney, L. R., Cramer, S. C., Deruyter, F., Eng, J. J., Fisher, B., Harvey, R. L., et al. (2016) · Stroke · doi:10.1161/str.0000000000000098 · Cited by 3,293 · see citing works
Effects of Augmented Exercise Therapy Time After Stroke: A Meta-Analysis
Kwakkel, G., van Peppen, R., Wagenaar, R. C., Wood Dauphinee, S., Richards, C., Ashburn, A., Miller, K., Lincoln, N., Partridge, C., Wellwood, I., et al. (2004) · Stroke · doi:10.1161/01.str.0000143153.76460.7d · Cited by 1,081 · see citing works
Physical Human Activity Recognition Using Wearable Sensors
Attal, F., Mohammed, S., Dedabrishvili, M., Chamroukhi, F., Oukhellou, L., & Amirat, Y. (2015) · Sensors · doi:10.3390/s151229858 · Cited by 806 · see citing works
Observation of Amounts of Movement Practice Provided During Stroke Rehabilitation
Lang, C. E., MacDonald, J. R., Reisman, D. S., Boyd, L. A., Kimberley, T. J., Schindler-Ivens, S., Hornby, T. G., Ross, S. A., & Scheets, P. L. (2009) · Archives of Physical Medicine and Rehabilitation · doi:10.1016/j.apmr.2009.04.005 · Cited by 707 · see citing works
Is More Better? Using Metadata to Explore Dose–Response Relationships in Stroke Rehabilitation
Lohse, K. R., Lang, C. E., & Boyd, L. A. (2014) · Stroke · doi:10.1161/strokeaha.114.004695 · Cited by 638 · see citing works
Kwakkel, G., Lannin, N. A., Borschmann, K., English, C., Ali, M., Churilov, L. P., Saposnik, G., Winstein, C. J., van Wegen, E. E. H., Wolf, S. L., et al. (2017) · International Journal of Stroke · doi:10.1177/1747493017711813 · Cited by 598 · see citing works
Comparative study on classifying human activities with miniature inertial and magnetic sensors
Altun, K., Barshan, B., & Tunçel, O. (2010) · Pattern Recognition · doi:10.1016/j.patcog.2010.04.019 · Cited by 564 · see citing works
Birkenmeier, R. L., Prager, E. M., & Lang, C. E. (2010) · Neurorehabilitation and neural repair · doi:10.1177/1545968310361957 · Cited by 295 · see citing works
Physiotherapy after stroke: More is better?
Langhorne, P., WAGENAAR, R. C., & Partridge, C. J. (1996) · Physiotherapy Research International · doi:10.1002/pri.6120010204 · Cited by 287 · see citing works
Dose and timing in neurorehabilitation
Lang, C. E., Lohse, K. R., & Birkenmeier, R. L. (2015) · Current Opinion in Neurology · doi:10.1097/wco.0000000000000256 · Cited by 278 · see citing works
Review of stroke rehabilitation
Young, J. B., & Förster, A. (2007) · BMJ · doi:10.1136/bmj.39059.456794.68 · Cited by 178 · see citing works
Long-Term Outcome Poststroke: Predictors of Activity Limitation and Participation Restriction
Gadidi, V., Leurer, M. K., Carmeli, E., & Bornstein, N. M. (2011) · Archives of Physical Medicine and Rehabilitation · doi:10.1016/j.apmr.2011.06.014 · Cited by 162 · see citing works
Valevicius, A. M., Jun, P. Y., Hebert, J. S., & Vette, A. H. (2018) · Journal of Electromyography and Kinesiology · doi:10.1016/j.jelekin.2018.02.011 · Cited by 116 · see citing works
Arac, A., Zhao, P., Dobkin, B. H., Carmichael, S. T., & Golshani, P. (2019) · Frontiers in Systems Neuroscience · doi:10.3389/fnsys.2019.00020 · Cited by 108 · see citing works
Biswas, D., Cranny, A., Gupta, N., Maharatna, K., Achner, J., Klemke, J., Jöbges, M., & Ortmann, S. (2014) · Human Movement Science · doi:10.1016/j.humov.2014.11.013 · Cited by 102 · see citing works
Measuring functional arm movement after stroke using a single wrist-worn sensor and machine learning
Bochniewicz, E. M., Emmer, G., McLeod, A., Barth, J., Dromerick, A. W., & Lum, P. (2017) · Journal of Stroke and Cerebrovascular Diseases · doi:10.1016/j.jstrokecerebrovasdis.2017.07.004 · Cited by 73 · see citing works
Galvin, R., Murphy, T. B., Cusack, T., & Stokes, E. (2008) · Topics in Stroke Rehabilitation · doi:10.1310/tsr1504-365 · Cited by 72 · see citing works
Lum, P. S., Shu, L., Bochniewicz, E. M., Tran, T., Chang, L., Barth, J., & Dromerick, A. W. (2020) · Neurorehabilitation and neural repair · doi:10.1177/1545968320962483 · Cited by 60 · see citing works
Bernhardt, J. A., Hayward, K. S., Dancause, N., Lannin, N. A., Ward, N., Nudo, R. J., Farrin, A. J., Churilov, L. P., Boyd, L. A., Jones, T. A., et al. (2019) · Neurorehabilitation and neural repair · doi:10.1177/1545968319888642 · Cited by 49 · see citing works
Characterization of a wearable system for automatic supervision of fitness exercises
Crema, C., Depari, A., Flammini, A., Sisinni, E., Haslwanter, T., & Salzmann, S. (2019) · Measurement · doi:10.1016/j.measurement.2019.07.038 · Cited by 30 · see citing works
Guerra, J., Uddin, J., Nilsen, D. M., Mclnerney, J., Fadoo, A., Omofuma, I., Hughes, S., Agrawal, S. K., Allen, P., & Schambra, H. M. (2017) · International Conference on Rehabilitation Robotics · doi:10.1109/icorr.2017.8009305 · Cited by 26 · see citing works
Biswas, D., Corda, D., Baldus, G., Cranny, A., Maharatna, K., Achner, J., Klemke, J., Jöbges, M., & Ortmann, S. (2014) · Physiological Measurement · doi:10.1088/0967-3334/35/9/1751 · Cited by 23 · see citing works
Template matching based motion classification for unsupervised post-stroke rehabilitation
Zhang, Z., Fang, Q., Wang, L., et al. (2011) · doi:10.1109/isbb.2011.6107680 · Cited by 20 · see citing works
Upper limb motion capturing and classification for unsupervised stroke rehabilitation
Zhang, Z., Fang, Q., & Ferry, F. (2011) · Proceedings of the Annual Conference of the IEEE Industrial Electronics Society · doi:10.1109/iecon.2011.6119934 · Cited by 20 · see citing works
Flagged first, then by citations
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
“9 to filter sensor data [43,44] or used different statistical tools to interpolate the missing data points [64].”
BackgroundMethodInfluential
- Authors
- Balestra, N., Sharma, G., Riek, L. M., & Busza, A.
- Affiliations
- University of Rochester Medicine (US)
- Nazareth College (US)
- Corresponding author
- Busza, Ania
- Venue
- Digital Biomarkers
- Publisher
- S. Karger AG
- Published
- 2021-07-02
- Volume
- 5
- Issue
- 2
- Pages
- 158-166
- ISSN
- 2504-110X (ISSN-L)
- PMC
- PMC8339513
- OpenAlex
- W3193715283
- Cited by
- 13
- References
- 26
- Citations by year
- 2025: 5 · 2024: 2 · 2023: 4 · 2021: 2
- FWCI
- 0.72
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Digital Biomarkers (publishedVersion, cc-by-nc)
- medRxiv (acceptedVersion)
- Research Square (acceptedVersion, cc-by)
- PubMed Central (publishedVersion)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- University of Rochester
- National Institutes of Health
- Medical Center, University of Rochester
- Eunice Kennedy Shriver National Institute of Child Health and Human Development
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Health Sciences › Medicine › Rehabilitation › Stroke Rehabilitation and Recovery
- Health Sciences › Medicine › Physiology › Physical Activity and Health
- Keywords
- upper limb rehabilitation, stroke, wearable sensors, accelerometer, gyroscope, exercise repetition counting, peak finding algorithm, inpatient rehabilitation, motor recovery
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
