{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T13:47:28Z","timestamp":1776779248160,"version":"3.51.2"},"reference-count":51,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T00:00:00Z","timestamp":1776729600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Bioengineering"],"abstract":"<jats:p>Rotator cuff injuries are among the most common musculoskeletal conditions that affect shoulder function and can ultimately impact quality of life. While physical therapy is essential in the care of rotator cuff injuries, the ideal dose of therapeutic exercises continues to be a significant clinical dilemma because of the generalized nature of rehabilitation protocols. This pilot study proposes a machine learning approach to personalize rehabilitation using surface electromyography (sEMG) data collected from eight healthy individuals by testing four key shoulder movements: scaption, internal rotation, external rotation, and external rotation at 90\u00b0 abduction. In this research, the XGBoost algorithm was used to model muscle activation patterns by achieving a high predictive accuracy (R2 = 0.5325; MSE = 0.0084 \u03bcV2). Because sEMG reliably measures superficial muscle activity, a linear programming model was used to divide a 60 min therapy session in a way that increases activation of superficial muscles (such as deltoid and trapezius) while reducing strain on deep muscles (such as supraspinatus and infraspinatus). Three optimization scenarios were tested by reflecting a different clinical goal: prioritizing superficial muscles, minimizing deep muscle strain, or balancing both. Optimized time allocations assigned more time to external rotation at 90\u00b0 abduction and scaption. This research demonstrates the potential for data-driven methods to transform rotator cuff rehabilitation through personalized and evidence-based treatment plans. The results enhance clinical practice by enabling adaptive rehabilitation planning and show that machine learning can support decision-making in complex muscle activation analysis with strong performance and low latency.<\/jats:p>","DOI":"10.3390\/bioengineering13040483","type":"journal-article","created":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T11:42:45Z","timestamp":1776771765000},"page":"483","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Toward Personalized Rotator Cuff Physical Therapy Dosage Using a Machine Learning-Based Pilot Study with EMG"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3524-338X","authenticated-orcid":false,"given":"AmirHossein","family":"MajidiRad","sequence":"first","affiliation":[{"name":"Department of Engineering Technology, Purdue University Northwest, Hammond, IN 46323, USA"},{"name":"Mayo Clinic, Jacksonville, FL 32224, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Iram","family":"Azam","sequence":"additional","affiliation":[{"name":"Department of Computer Information Technology, Purdue University Northwest, Hammond, IN 46323, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Japp","family":"Adhikari","sequence":"additional","affiliation":[{"name":"Department of Computer Information Technology, Purdue University Northwest, Hammond, IN 46323, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mehrnoosh","family":"Damircheli","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, York College of Pennsylvania, York, PA 17403, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"335","DOI":"10.26603\/ijspt20180335","article-title":"Exercise therapy in the non-operative treatment of full-thickness rotator cuff tears: A systematic review","volume":"13","author":"Jeanfavre","year":"2018","journal-title":"Int. J. Sport. Phys. Ther."},{"key":"ref_2","first-page":"279","article-title":"Exercise rehabilitation in the non-operative management of rotator cuff tears: A review of the literature","volume":"11","author":"Edwards","year":"2016","journal-title":"Int. J. Sport. Phys. Ther."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1007\/s12178-018-9464-5","article-title":"Management of rotator cuff injuries in the elite athlete","volume":"11","author":"Weiss","year":"2018","journal-title":"Curr. Rev. Musculoskelet. Med."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"403","DOI":"10.4172\/2329-9096.1000403","article-title":"Metrics for performance evaluation of patient exercises during physical therapy","volume":"5","author":"Vakanski","year":"2017","journal-title":"Int. J. Phys. Med. Rehabil."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"e21374","DOI":"10.2196\/21374","article-title":"Adherence patterns and dose response of physiotherapy for rotator cuff pathology: Longitudinal cohort study","volume":"8","author":"Burns","year":"2021","journal-title":"JMIR Rehabil. Assist. Technol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"e70010","DOI":"10.1002\/brx2.70010","article-title":"Occupational therapy-based rehabilitation of sciatic nerve pain","volume":"2","author":"Thakur","year":"2024","journal-title":"Brain-X"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Cooke, E.V., Mares, K., Clark, A., Tallis, R.C., and Pomeroy, V.M. (2010). The effects of increased dose of exercise-based therapies to enhance motor recovery after stroke: A systematic review and meta-analysis. BMC Med., 8.","DOI":"10.1186\/1741-7015-8-60"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"105721","DOI":"10.1016\/j.cmpb.2020.105721","article-title":"Shoulder muscle activation pattern recognition based on sEMG and machine learning algorithms","volume":"197","author":"Jiang","year":"2020","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"22934","DOI":"10.1109\/JSEN.2024.3406138","article-title":"Classification of shoulder rehabilitation exercises by using wearable systems and machine learning algorithms","volume":"24","author":"Sassi","year":"2024","journal-title":"IEEE Sens. J."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1016\/j.procs.2017.11.259","article-title":"Electromyogram (EMG) signal detection, classification of EMG signals and diagnosis of neuropathy muscle disease","volume":"120","author":"Sadikoglu","year":"2017","journal-title":"Procedia Comput. Sci."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Belli, I., Joshi, S., Prendergast, J.M., Beck, I., Santina, C.D., Peternel, L., and Seth, A. (2023). Does enforcing glenohumeral joint stability matter? A new rapid muscle redundancy solver highlights the importance of non-superficial shoulder muscles. PLoS ONE, 18.","DOI":"10.1101\/2023.07.11.548542"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Xu, K., Feng, H., He, G., and Li, M. (2024, January 25\u201327). Research on rehabilitation assessment methods for patients after rotator cuff surgery based on attitude sensors and XGBoost algorithm. Proceedings of the 2024 3rd International Conference on Computing, Communication, Perception and Quantum Technology (CCPQT), Zhuhai, China.","DOI":"10.1109\/CCPQT64497.2024.00067"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"931","DOI":"10.2519\/jospt.2017.7271","article-title":"A systematic review of electromyography studies in normal shoulders to inform postoperative rehabilitation following rotator cuff repair","volume":"47","author":"Edwards","year":"2017","journal-title":"J. Orthop. Sport. Phys. Ther."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1590\/1517-8692202127032021_0082","article-title":"Rehabilitation of neuromuscular function by physical exercise","volume":"27","author":"Li","year":"2021","journal-title":"Rev. Bras. Med. Esporte"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1016\/j.jseint.2021.09.005","article-title":"A comparison of teres minor and infraspinatus muscle activation in the prone position","volume":"6","author":"Tsuruike","year":"2022","journal-title":"JSES Int."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1109\/86.895950","article-title":"EMG-based prediction of shoulder and elbow kinematics in able-bodied and spinal cord injured individuals","volume":"8","author":"Au","year":"2000","journal-title":"IEEE Trans. Rehabil. Eng."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"7420","DOI":"10.1016\/j.eswa.2012.01.102","article-title":"Feature reduction and selection for EMG signal classification","volume":"39","author":"Phinyomark","year":"2012","journal-title":"Expert Syst. Appl."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1486","DOI":"10.1152\/japplphysiol.01070.2003","article-title":"The extraction of neural strategies from the surface EMG","volume":"96","author":"Farina","year":"2004","journal-title":"J. Appl. Physiol."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1007\/978-981-96-1185-0_11","article-title":"Gesture Recognition on Normalized SEMG Signals with Sliding Window","volume":"Volume 1237","author":"Gehlot","year":"2025","journal-title":"Data Science and Applications: Proceedings of ICDSA 2024, Volume 5"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"385","DOI":"10.2519\/jospt.2004.34.7.385","article-title":"Electromyographic analysis of the rotator cuff and deltoid musculature during common shoulder external rotation exercises","volume":"34","author":"Reinold","year":"2004","journal-title":"J. Orthop. Sport. Phys. Ther."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2020","DOI":"10.1038\/s41598-024-52405-9","article-title":"Optimizing the performance of convolutional neural networks for enhanced gesture recognition using sEMG","volume":"14","author":"Ashraf","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2615","DOI":"10.1007\/s00167-022-07298-4","article-title":"Machine learning model successfully identifies important clinical features for predicting outpatients with rotator cuff tears","volume":"31","author":"Li","year":"2023","journal-title":"Knee Surg. Sport. Traumatol. Arthrosc."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2843","DOI":"10.1007\/s00330-019-06639-1","article-title":"Ruling out rotator cuff tear in shoulder radiograph series using deep learning: Redefining the role of conventional radiograph","volume":"30","author":"Kim","year":"2020","journal-title":"Eur. Radiol."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"105536","DOI":"10.1016\/j.cmpb.2020.105536","article-title":"Predictive modeling of blood pressure during hemodialysis: A comparison of linear model, random forest, support vector regression, XGBoost, LASSO regression and ensemble method","volume":"195","author":"Huang","year":"2020","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"e617","DOI":"10.1016\/j.wneu.2022.04.044","article-title":"XGBoost machine learning algorithm performed better than regression models in predicting mortality of moderate-to-severe traumatic brain injury","volume":"163","author":"Wang","year":"2022","journal-title":"World Neurosurg."},{"key":"ref_26","first-page":"8","article-title":"XGBoost, a machine learning method, predicts neurological recovery in patients with cervical spinal cord injury","volume":"1","author":"Inoue","year":"2020","journal-title":"Neurotrauma Rep."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Kim, T. (2024). Factors associated with predicting knee pain using knee X-ray and personal factors: A multivariate logistic regression and XGBoost model analysis from the nationwide Korean database (KNHANES). PLoS ONE, 19.","DOI":"10.1371\/journal.pone.0314789"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"125930","DOI":"10.1016\/j.eswa.2024.125930","article-title":"Prediction of lower limb joint angles from surface electromyography using XGBoost","volume":"264","author":"Lu","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"12575","DOI":"10.1038\/s41598-025-95973-0","article-title":"Estimating gait parameters from sEMG signals using machine learning techniques under different power capacity of muscle","volume":"15","author":"Liu","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_30","first-page":"17","article-title":"Surface electromyography: Why, when and how to use it","volume":"4","author":"Garcia","year":"2011","journal-title":"Rev. Andal. Med. Deporte"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"105140","DOI":"10.1109\/ACCESS.2023.3316509","article-title":"Surface electromyography and artificial intelligence for human activity recognition\u2014A systematic review on methods, emerging trends, applications, challenges, and future implementation","volume":"11","author":"Rani","year":"2023","journal-title":"IEEE Access"},{"key":"ref_32","first-page":"2385","article-title":"Surface electromyography and artificial intelligence in rehabilitation: Current state and future directions","volume":"29","author":"Wang","year":"2021","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Zhang, J., Jin, Z., Tang, B., Huang, X., Wang, Z., Chen, Q., and He, J. (2024). Enhancing trauma care: A machine learning approach with XGBoost for predicting urgent hemorrhage interventions using NTDB data. Bioengineering, 11.","DOI":"10.3390\/bioengineering11080768"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1292","DOI":"10.1080\/10618600.2022.2067548","article-title":"Survival regression with accelerated failure time model in XGBoost","volume":"31","author":"Barnwal","year":"2022","journal-title":"J. Comput. Graph. Stat."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"366","DOI":"10.1007\/s43465-019-00020-6","article-title":"Relation of superficial and deep layers of delaminated rotator cuff tear to supraspinatus and infraspinatus insertions","volume":"54","author":"Seo","year":"2020","journal-title":"Indian J. Orthop."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"23259671231206180","DOI":"10.1177\/23259671231206180","article-title":"Using machine learning to predict nonachievement of clinically significant outcomes after rotator cuff repair","volume":"11","author":"Alaiti","year":"2023","journal-title":"Orthop. J. Sport. Med."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Natras, R., Soja, B., and Schmidt, M. (2022). Ensemble machine learning of random forest, AdaBoost and XGBoost for vertical total electron content forecasting. Remote Sens., 14.","DOI":"10.3390\/rs14153547"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Rahman, H.A.A., Wah, Y.B., He, H., and Bulgiba, A. (2015). Comparisons of AdaBoost, KNN, SVM and logistic regression in classification of imbalanced dataset. Soft Computing in Data Science, Proceedings of the First International Conference, SCDS 2015, Putrajaya, Malaysia, 2\u20133 September 2015, Springer.","DOI":"10.1007\/978-981-287-936-3_6"},{"key":"ref_39","first-page":"548","article-title":"A study of mammogram classification using AdaBoost with decision tree, KNN, SVM and hybrid SVM-KNN as component classifiers","volume":"9","author":"Deshmukh","year":"2018","journal-title":"J. Inf. Hiding Multimed. Signal Process."},{"key":"ref_40","first-page":"6867","article-title":"An overview of boosting decision tree algorithms utilizing AdaBoost and XGBoost boosting strategies","volume":"7","author":"Azmi","year":"2020","journal-title":"Int. Res. J. Eng. Technol. (IRJET)"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1186\/s12984-020-00758-3","article-title":"Predicting clinically significant motor function improvement after contemporary task-oriented interventions using machine learning approaches","volume":"17","author":"Thakkar","year":"2020","journal-title":"J. NeuroEngineering Rehabil."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Bai, A., Song, H., Wu, Y., Dong, S., Feng, G., and Jin, H. (2025). Sliding-window CNN + channel-time attention transformer network trained with inertial measurement units and surface electromyography data for the prediction of muscle activation and motion dynamics leveraging IMU-only wearables for home-based shoulder rehabilitation. Sensors, 25.","DOI":"10.3390\/s25041275"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Mitchell, A., MajidiRad, A., and Pujalte, G. (2023, January 17\u201319). A case study on activation level of rotator cuff muscles using electromyography and associated muscle forces. Proceedings of the 2023 Design of Medical Devices Conference, Minneapolis, MN, USA.","DOI":"10.1115\/DMD2023-7918"},{"key":"ref_44","first-page":"70","article-title":"A literature review of studies evaluating rotator cuff activation during early rehabilitation exercises for post-op rotator cuff repair","volume":"19","author":"Wells","year":"2016","journal-title":"J. Exerc. Physiol. Online"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"28430","DOI":"10.1038\/s41598-024-79191-8","article-title":"Machine learning insights into scapular stabilization for alleviating shoulder pain in college students","volume":"14","author":"Mabrouk","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"012010","DOI":"10.1088\/1757-899X\/705\/1\/012010","article-title":"Assessment of muscles fatigue based on surface EMG signals using machine learning and statistical approaches: A review","volume":"705","author":"Yousif","year":"2019","journal-title":"IOP Conf. Ser. Mater. Sci. Eng."},{"key":"ref_47","unstructured":"Hajian, G. (2020). Generalized Force Estimation using Machine Learning and Deep Learning with EMG and Motion Data. [Ph.D. Thesis, Queen\u2019s University]. Order No. 28387874."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"1023","DOI":"10.1016\/j.jelekin.2010.07.004","article-title":"How should we normalize electromyograms obtained from healthy participants? What we have learned from over 25 years of research","volume":"20","author":"Burden","year":"2010","journal-title":"J. Electromyogr. Kinesiol."},{"key":"ref_49","unstructured":"SENIAM Project (1999). European Recommendations for Surface Electromyography, Roessingh Research and Development."},{"key":"ref_50","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"e57","DOI":"10.1002\/brx2.57","article-title":"Comprehensive review of Transformer-based models in neuroscience, neurology, and psychiatry","volume":"2","author":"Cong","year":"2024","journal-title":"Brain-X"}],"container-title":["Bioengineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5354\/13\/4\/483\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T12:42:00Z","timestamp":1776775320000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5354\/13\/4\/483"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,21]]},"references-count":51,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["bioengineering13040483"],"URL":"https:\/\/doi.org\/10.3390\/bioengineering13040483","relation":{},"ISSN":["2306-5354"],"issn-type":[{"value":"2306-5354","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,21]]}}}