AI-Driven Digital Rehabilitation Versus Supervised Physiotherapy Following Total Knee Arthroplasty: Evidence from Randomized Controlled Trials
AI-Driven Rehabilitation Versus Supervised Physiotherapy After TKA
Keywords:
Arthroplasty, Artificial Intelligence, Knee, Physical Therapy, TelerehabilitationAbstract
Background: Supervised physiotherapy after total knee arthroplasty (TKA) is limited by access, cost and adherence. Artificial intelligence (AI)-driven digital rehabilitation systems, which analyze movement and give real-time feedback at home, may extend structured rehabilitation beyond the clinic. This review compared AI-driven digital rehabilitation with supervised physiotherapy after TKA.
Methods: PubMed/MEDLINE, Embase, Scopus, Web of Science, CENTRAL, CINAHL, PEDro, IEEE Xplore, ClinicalTrials.gov and the WHO ICTRP were searched from inception to August 2026. Randomized controlled trials (RCTs) in adults after primary TKA comparing AI-driven rehabilitation (automated movement analysis with feedback, algorithm-driven progression or a virtual coach) with supervised physiotherapy or unsupervised home exercise were eligible. Two reviewers independently screened records, extracted data and assessed risk of bias with RoB 2. Narrative synthesis followed SWiM; certainty was rated with GRADE.
Results: Seven RCTs (2020–2025; 726 participants) were included: four compared AI-driven rehabilitation with supervised physiotherapy and three with unsupervised home exercise. Against supervised physiotherapy, knee function and range of motion did not differ in any trial, and pain was similar in three trials, while one small pilot reported higher pain with the sensor system. Both non-inferiority trials met their margins, and the largest trial (n = 306) reported lower 12-week healthcare costs (median $1,050 vs $2,805) and fewer rehospitalizations. Against unsupervised exercise, one trial found no difference and two favored the intervention. No trial was at low risk of bias; three had some concerns, three were at high risk and one could not be assessed. Certainty was low versus supervised physiotherapy and very low versus unsupervised exercise.
Conclusion: AI-driven digital rehabilitation may produce similar short-term recovery to supervised physiotherapy after TKA at lower cost, but its benefit over unsupervised home exercise is very uncertain. Larger, rigorously designed trials with longer follow-up and full economic evaluation are needed.
DOI: https://doi.org/10.59564/amrj/04.04/014
References
Shichman I, Roof M, Askew N, Nherera L, Rozell JC, Seyler TM, et al. Projections and epidemiology of primary hip and knee arthroplasty in Medicare patients to 2040-2060. JB JS Open Access. 2023;8(1):e22.00112. https://doi.org/10.2106/JBJS.OA.22.00112
Cheng HY, Beswick AD, Bertram W, Siddiqui MA, Gooberman-Hill R, Whitehouse MR, et al. What proportion of people have long-term pain after total hip or knee replacement? An update of a systematic review and meta-analysis. BMJ Open. 2025;15(5):e088975. https://doi.org/10.1136/bmjopen-2024-088975
Singh M, Harary J, Schilling PL, Moschetti WE. Patient satisfaction is nearly 90% after total knee arthroplasty; we are better than we were. J Arthroplasty. 2025;40(6):1521–5.e1. https://doi.org/10.1016/j.arth.2024.11.038
Jette DU, Hunter SJ, Burkett L, Langham B, Logerstedt DS, Piuzzi NS, et al. Physical therapist management of total knee arthroplasty. Phys Ther. 2020;100(9):1603–31. https://doi.org/10.1093/ptj/pzaa099
Bakaa N, Chen LH, Carlesso L, Richardson J, Shanthanna H, Macedo L. Reporting of post-operative rehabilitation interventions for total knee arthroplasty: a scoping review. BMC Musculoskelet Disord. 2021;22(1):602. https://doi.org/10.1186/s12891-021-04460-w
Liu L, Wang S, Ye C, Chen D, Dong H. The effects of digital health on exercise adherence and intervention outcomes in older adults with knee diseases: a systematic review. Ann Phys Rehabil Med. 2025;68(5):101952. https://doi.org/10.1016/j.rehab.2025.101952
Hao J, Sun S, Dou T, Deng J, Li W, Ma C, et al. Intelligent rehabilitation: advances in artificial intelligence for musculoskeletal rehabilitation: a narrative review. Orthop Res Rev. 2026;18:1–15. https://doi.org/10.2147/ORR.S607912
Prvu Bettger J, Green CL, Holmes DN, Chokshi A, Mather RC 3rd, Hoch BT, et al. Effects of virtual exercise rehabilitation in-home therapy compared with traditional care after total knee arthroplasty: VERITAS, a randomized controlled trial. J Bone Joint Surg Am. 2020;102(2):101–9. https://doi.org/10.2106/JBJS.19.00695
Correia FD, Nogueira A, Magalhães I, Guimarães J, Moreira M, Barradas I, et al. Medium-term outcomes of digital versus conventional home-based rehabilitation after total knee arthroplasty: prospective, parallel-group feasibility study. JMIR Rehabil Assist Technol. 2019;6(1):e13111. https://doi.org/10.2196/13111
Shim GY, Kim EH, Lee SJ, Chang CB, Lee YS, Lee JI, et al. Postoperative rehabilitation using a digital healthcare system in patients with total knee arthroplasty: a randomized controlled trial. Arch Orthop Trauma Surg. 2023;143(10):6361–70. https://doi.org/10.1007/s00402-023-04894-y
Zhao R, Cheng L, Zheng Q, Lv Y, Wang YM, Ni M, et al. A smartphone application-based remote rehabilitation system for post-total knee arthroplasty rehabilitation: a randomized controlled trial. J Arthroplasty. 2024;39(3):575–81.e8. https://doi.org/10.1016/j.arth.2023.08.019
Tsang MP, Man GCW, Xin H, Chong YC, Ong MT, Yung PS. The effectiveness of telerehabilitation in patients after total knee replacement: a systematic review and meta-analysis of randomized controlled trials. J Telemed Telecare. 2024;30(5):795–808. https://doi.org/10.1177/1357633X221097469
Özden F, Sarı Z. The effect of mobile application-based rehabilitation in patients with total knee arthroplasty: a systematic review and meta-analysis. Arch Gerontol Geriatr. 2023;113:105058. https://doi.org/10.1016/j.archger.2023.105058
Zhai S, Wu R, Du G, Chen X, Liu Y, Zhao J, et al. Smart device-assisted telerehabilitation versus conventional rehabilitation after total knee arthroplasty: a systematic review and meta-analysis. J Orthop Surg Res. 2025;20(1):954. https://doi.org/10.1186/s13018-025-06393-9
Ma L, Liu JQ, Yu K, Tan MY. Meta-analysis of comparative effects of mobile app-based digital rehabilitation versus traditional rehabilitation after total knee arthroplasty. Front Physiol. 2026;16:1737373. https://doi.org/10.3389/fphys.2025.1737373
Peng L, Wang K, Wu L, Zeng Y, Shen B. Effectiveness of interactive remote rehabilitation after total knee arthroplasty: systematic review and meta-analysis of randomized controlled trials. J Med Internet Res. 2026;28:e89321. https://doi.org/10.2196/89321
Page MJ, McKenzie JE, Bossuyt PM, Boutron I, Hoffmann TC, Mulrow CD, et al. The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. BMJ. 2021;372:n71. https://doi.org/10.1136/bmj.n71
Higgins JPT, Thomas J, Chandler J, Cumpston M, Li T, Page MJ, et al., editors. Cochrane Handbook for Systematic Reviews of Interventions. Version 6.5. London: Cochrane; 2024. Available from: https://www.training.cochrane.org/handbook
Campbell M, McKenzie JE, Sowden A, Katikireddi SV, Brennan SE, Ellis S, et al. Synthesis without meta-analysis (SWiM) in systematic reviews: reporting guideline. BMJ. 2020;368:l6890. https://doi.org/10.1136/bmj.l6890
Ouzzani M, Hammady H, Fedorowicz Z, Elmagarmid A. Rayyan—a web and mobile app for systematic reviews. Syst Rev. 2016;5:210. https://doi.org/10.1186/s13643-016-0384-4
Hoffmann TC, Glasziou PP, Boutron I, Milne R, Perera R, Moher D, et al. Better reporting of interventions: template for intervention description and replication (TIDieR) checklist and guide. BMJ. 2014;348:g1687. https://doi.org/10.1136/bmj.g1687
Sterne JAC, Savović J, Page MJ, Elbers RG, Blencowe NS, Boutron I, et al. RoB 2: a revised tool for assessing risk of bias in randomised trials. BMJ. 2019;366:l4898. https://doi.org/10.1136/bmj.l4898
McGuinness LA, Higgins JPT. Risk-of-bias VISualization (robvis): an R package and Shiny web app for visualizing risk-of-bias assessments. Res Synth Methods. 2021;12(1):55–61. https://doi.org/10.1002/jrsm.1411
Guyatt G, Oxman AD, Akl EA, Kunz R, Vist G, Brozek J, et al. GRADE guidelines: 1. Introduction—GRADE evidence profiles and summary of findings tables. J Clin Epidemiol. 2011;64(4):383–94. https://doi.org/10.1016/j.jclinepi.2010.04.026
Murad MH, Mustafa RA, Schünemann HJ, Sultan S, Santesso N. Rating the certainty in evidence in the absence of a single estimate of effect. Evid Based Med. 2017;22(3):85–7. https://doi.org/10.1136/ebmed-2017-110668
Bell KM, Onyeukwu C, Smith CN, Oh A, Devito Dabbs A, Piva SR, et al. A portable system for remote rehabilitation following a total knee replacement: a pilot randomized controlled clinical study. Sensors (Basel). 2020;20(21):6118. https://doi.org/10.3390/s20216118
Nuevo M, Rodríguez-Rodríguez D, Jauregui R, Fabrellas N, Zabalegui A, Conti M, et al. Telerehabilitation following fast-track total knee arthroplasty is effective and safe: a randomized controlled trial with the ReHub® platform. Disabil Rehabil. 2024;46(12):2629–39. https://doi.org/10.1080/09638288.2023.2228689
Pua YH, Yeo SJ, Clark RA, Tan BY, Haines T, Bettger JP, et al. Cost and outcomes of hospital-based usual care versus tele-monitor self-directed rehabilitation (HUATR) in patients with total knee arthroplasty: a randomized, controlled, non-inferiority trial. Osteoarthritis Cartilage. 2024;32(5):601–11. https://doi.org/10.1016/j.joca.2023.11.017
Jung S, Kim JH, Rhee SJ. Home-based rehabilitation using wearable motion tracker with smart phone application feedback is as effective as conventional self-directed rehabilitation after total knee arthroplasty: randomized controlled trial. BMC Sports Sci Med Rehabil. 2025;17:370. https://doi.org/10.1186/s13102-025-01374-1
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Hira Asif, Wardha Jamal, Isra Sadaqat, Gohar Fatimah, Urwat El Wosqua
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
