Artificial intelligence application versus physical therapist for squat evaluation: a randomized controlled trial

Alessandro Luna, Lorenzo Casertano, Jean Timmerberg, Margaret O'Neil, Jason Machowsky, Cheng-Shiun Leu, Jianghui Lin, Zhiqian Fang, William Douglas, Sunil Agrawal, Alessandro Luna, Lorenzo Casertano, Jean Timmerberg, Margaret O'Neil, Jason Machowsky, Cheng-Shiun Leu, Jianghui Lin, Zhiqian Fang, William Douglas, Sunil Agrawal

Abstract

Artificial intelligence technology is becoming more prevalent in health care as a tool to improve practice patterns and patient outcomes. This study assessed ability of a commercialized artificial intelligence (AI) mobile application to identify and improve bodyweight squat form in adult participants when compared to a physical therapist (PT). Participants randomized to AI group (n = 15) performed 3 squat sets: 10 unassisted control squats, 10 squats with performance feedback from AI, and 10 additional unassisted test squats. Participants randomized to PT group (n = 15) also performed 3 identical sets, but instead received performance feedback from PT. AI group intervention did not differ from PT group (log ratio of two odds ratios = - 0.462, 95% confidence interval (CI) (- 1.394, 0.471), p = 0.332). AI ability to identify a correct squat generated sensitivity 0.840 (95% CI (0.753, 0.901)), specificity 0.276 (95% CI (0.191, 0.382)), PPV 0.549 (95% CI (0.423, 0.669)), NPV 0.623 (95% CI (0.436, 0.780)), and accuracy 0.565 95% CI (0.477, 0.649)). There was no statistically significant association between group allocation and improved squat performance. Current AI had satisfactory ability to identify correct squat form and limited ability to identify incorrect squat form, which reduced diagnostic capabilities.Trial Registration NCT04624594, 12/11/2020, retrospectively registered.

Conflict of interest statement

The authors declare no competing interests.

© 2021. The Author(s).

Figures

Figure 1
Figure 1
Participant flowchart. 42 people were eligible, but 6 people did not sign up for a time slot and 3 people were injured prior to participation.
Figure 2
Figure 2
Correct and incorrect squats as scored by AI and evaluators (E1 = Evaluator 1, E2 = Evaluator 2, E3 = Evaluator 3). “Control” refers to the first set of 10 unassisted squat repetitions. “Test” refers to the third and last set of 10 unassisted squat repetitions performed by participants after receiving feedback in the second set.
Figure 3
Figure 3
Feedback for incorrect squats as provided by AI and evaluators (E1, E2, E3).

References

    1. Bini SA. Artificial intelligence, machine learning, deep learning, and cognitive computing: What do these terms mean and how will they impact health care? J. Arthroplasty. 2018;33(8):2358–2361. doi: 10.1016/j.arth.2018.02.067.
    1. Jiang F, Jiang Y, Zhi H, Dong Y, Li H, Ma S, et al. Artificial intelligence in healthcare: Past, present and future. Stroke Vasc. Neurol. 2017;2(4):230–243. doi: 10.1136/svn-2017-000101.
    1. Hamet P, Tremblay J. Artificial intelligence in medicine. Metabolism. 2017;69:S36–S40. doi: 10.1016/j.metabol.2017.01.011.
    1. Fasola J, Mataric M. A socially assistive robot exercise coach for the elderly. J. Hum. Robot Interact. 2013 doi: 10.5898/JHRI.2.2.Fasola.
    1. Hamilton MT, Hamilton DG, Zderic TW. The necessity of active muscle metabolism for healthy aging: Muscular activity throughout the entire day. Progr. Mol. Biol. Transl. Sci. 2018;155:53–68. doi: 10.1016/bs.pmbts.2017.12.014.
    1. Gopinath B, Kifley A, Flood VM, Mitchell P. Physical activity as a determinant of successful aging over ten years. Sci. Rep. 2018 doi: 10.1038/s41598-018-28526-3.
    1. Jakovljevic DG. Physical activity and cardiovascular aging: Physiological and molecular insights. Exp. Gerontol. 2018;109:67–74. doi: 10.1016/j.exger.2017.05.016.
    1. Dahlberg LE, Dell’Isola A, Lohmander LS, Nero H. Improving osteoarthritis care by digital means—Effects of a digital self-management program after 24- or 48-weeks of treatment. PLoS ONE. 2020;15(3):e0229783. doi: 10.1371/journal.pone.0229783.
    1. Toelle TR, Utpadel-Fischler DA, Haas K-K, Priebe JA. App-based multidisciplinary back pain treatment versus combined physiotherapy plus online education: A randomized controlled trial. NPJ Digit. Med. 2019;2(1):34. doi: 10.1038/s41746-019-0109-x.
    1. Kritz M, Cronin J, Hume P. The bodyweight squat: A movement screen for the squat pattern. Strength Cond. J. 2009;31(1):76–85. doi: 10.1519/SSC.0b013e318195eb2f.
    1. O’Reilly MA, Whelan DF, Wassrd TE, Delahunt E, Caulfield BM. Technology in strength and conditioning. J. Strength Cond. Res. 2017;31:2303–2312. doi: 10.1519/JSC.0000000000001957.
    1. Myer GD, Ford KR, Hewett TE. Rationale and clinical techniques for anterior cruciate ligament injury prevention among female athletes. J. Athl. Train. 2004;39(4):352–364.
    1. Escamilla RF. Knee biomechanics of the dynamic squat exercise. Med. Sci. Sports Exerc. 2001;33(1):127–141. doi: 10.1097/00005768-200101000-00020.
    1. Heijne A, Fleming BC, Renstrom PA, Peura GD, Beynnon BD, Werner S. Strain on the anterior cruciate ligament during closed kinetic chain exercises. Med. Sci. Sports Exerc. 2004;36(6):935–941. doi: 10.1249/01.MSS.0000128185.55587.A3.
    1. Schoenfeld BJ. Squatting kinematics and kinetics and their application to exercise performance. J. Strength Cond. Res. 2010;24(12):3497–3506. doi: 10.1519/JSC.0b013e3181bac2d7.
    1. Myer GD, Kushner AM, Brent JL, Schoenfeld BJ, Hugentobler J, Lloyd RS, et al. The back squat. Strength Cond. J. 2014;36(6):4–27. doi: 10.1519/SSC.0000000000000103.
    1. Swinton PA, Stewart AD, Lloyd R, Keogh JWL, Agouris I. A biomechanical comparison of the traditional squat, powerlifting squat, and box squat. J. Strength Cond. Res. 2012;26(7):1805–1816. doi: 10.1519/JSC.0b013e3182577067.
    1. Brocki KC, Bohlin G. Executive functions in children aged 6 to 13: A dimensional and developmental study. Dev. Neuropsychol. 2004;26(2):571–593. doi: 10.1207/s15326942dn2602_3.
    1. Shults J, Sun W, Tu X, Kim H, Amsterdam J, Hilbe JM, et al. A comparison of several approaches for choosing between working correlation structures in generalized estimating equation analysis of longitudinal binary data. Stat. Med. 2009;28(18):2338–2355. doi: 10.1002/sim.3622.
    1. Hallgren KA. Computing inter-rater reliability for observational data: An overview and tutorial. Tutor Quant. Methods Psychol. 2012;8(1):23–34. doi: 10.20982/tqmp.08.1.p023.
    1. RStudio. RStudio (2020). . Accessed 16 Jan 2020.
    1. Power M, Fell G, Wright M. Principles for high-quality, high-value testing. Evid. Based Med. 2013;18(1):5–10. doi: 10.1136/eb-2012-100645.
    1. Renggli D, Graf C, Tachatos N, Singh N, Meboldt M, Taylor WR, et al. Wearable inertial measurement units for assessing gait in real-world environments. Front. Physiol. 2020 doi: 10.3389/fphys.2020.00090/full.
    1. Giggins OM, Sweeney KT, Caulfield B. Rehabilitation exercise assessment using inertial sensors: A cross-sectional analytical study. J. Neuroeng. Rehabil. 2014;11(1):158. doi: 10.1186/1743-0003-11-158.
    1. O’Reilly, M., et al. Evaluating squat performance with a single inertial measurement unit. In 2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks (BSN). IEEE, 1–6 (2015). .
    1. Whelan DF, O’Reilly MA, Ward TE, Delahunt E, Caulfield B. Technology in rehabilitation: Evaluating the single leg squat exercise with wearable inertial measurement units. Methods Inf. Med. 2017;56(2):88–94. doi: 10.3414/ME16-02-0002.
    1. Whelan, D., O’Reilly, M., Ward, T., Delahunt, E. & Caulfield, B. Evaluating performance of the single leg squat exercise with a single inertial measurement unit. In Proc. 3rd 2015 Workshop on ICTs for improving Patients Rehabilitation Research Techniques—REHAB’15, 144–147 (ACM Press, 2015). . Accessed 28 Aug 2020.
    1. Whelan, D., O’Reilly, M., Ward, T., Delahunt, E. & Caulfield, B. Evaluating performance of the lunge exercise with multiple and individual inertial measurement units. In Proc. 10th EAI International Conference on Pervasive Computing Technologies for Healthcare. ACM. 10.4108/eai.16-5-2016.2263319 (2016).
    1. McHugh ML. Interrater reliability: The kappa statistic. Biochem. Med. 2012;22(3):276–282. doi: 10.11613/BM.2012.031.
    1. Zagnit EA, Rajan S, Basch CH. Prevalence and pricing of chain gyms in New York City. Int. J. Health Promot. Educ. 2016;54(1):50–57. doi: 10.1080/14635240.2015.1069717.

Source: PubMed

Sponsors en medewerkers

Medische omstandigheden

Geneesmiddelinterventies

3
Abonneren