Developing and validating an accelerometer-based algorithm with machine learning to classify physical activity after acquired brain injury

References

• Castellanos NP, Paúl N, Ordóñez VE, Demuynck O, Bajo R, Campo P, Bilbao A, Ortiz T, del-Pozo F, Maestú F, et al. Reorganization of functional connectivity as a correlate of cognitive recovery in acquired brain injury. Brain. 2010;133(Pt 8):2365–81. doi:10.1093/brain/awq174.
   PubMed Web of Science ®Google Scholar
• Langhorne P, Bernhardt J, Kwakkel G. 2011. Stroke rehabilitation. Lancet. 377(9778):1693–702. doi:10.1016/s0140-6736(11)60325-5.
   PubMed Web of Science ®Google Scholar
• Walker WC, Pickett TC. Motor impairment after severe traumatic brain injury: A longitudinal multicenter study. J Rehabil Res Dev. 2007;44(7):975. doi:10.1682/JRRD.2006.12.0158.
   PubMedGoogle Scholar
• Langhammer B, Lindmark B. Predictors for walking capacity after stroke: sitting, standing static or dynamic balance? Brain Inj. 2014;28(5–6):561. doi:10.3109/02699052.2014.919534.
   Web of Science ®Google Scholar
• World Health Organization. International classification of functioning, disability and health: ICF. Geneva: World Health Organization; 2001.
   Google Scholar
• Geyh S, Cieza A, Schouten J, Dickson H, Frommelt P, Omar Z, Kostanjsek N, Ring H, Stucki G. ICF core sets for stroke. J Rehabil Med. 2004;36(44 Suppl):135–41. doi:10.1080/16501960410016776. Epub 2004/09/17. PubMed PMID: 15370761.
   PubMed Web of Science ®Google Scholar
• Caspersen CJ, Powell KE, Christenson GM.Physical activity, exercise, and physical fitness: definitions and distinctions for health-related research. Public Health Rep (Washington, DC: 1974). 1985;100(2):126–31.
   PubMed Web of Science ®Google Scholar
• Duncan PW, Goldstein LB, Matchar D, Divine GW, Feussner J. 1992. Measurement of motor recovery after stroke. Outcome assessment and sample size requirements. Stroke. 23(8):1084–89. doi:10.1161/01.STR.23.8.1084.
   PubMed Web of Science ®Google Scholar
• Kwakkel G, Lannin NA, Borschmann K, English C, Ali M, Churilov L, Saposnik G, Winstein C, van Wegen EEH, Wolf SL, et al. Standardized measurement of sensorimotor recovery in stroke trials: consensus-based core recommendations from the stroke recovery and rehabilitation roundtable. Int J Stroke. 2017;12(5):451–61. doi:10.1177/1747493017711813.
   PubMed Web of Science ®Google Scholar
• Langhorne P, Coupar F, Pollock A. 2009. Motor recovery after stroke: a systematic review. Lancet Neurol. 8(8):741. doi:10.1016/S1474-4422(09)70150-4.
   PubMed Web of Science ®Google Scholar
• Fini NA, Holland AE, Keating J, Simek J, Bernhardt J. 2014. How is physical activity monitored in people following stroke? Disabil Rehabil. 37(19):1717–31. doi:10.3109/09638288.2014.978508.
   PubMed Web of Science ®Google Scholar
• Dyrstad MS, Hansen HB, Holme MI, Anderssen AS. 2014. Comparison of self-reported versus accelerometer-measured physical activity. Med Sci Sports Exerc. 46(1):99–106. doi:10.1249/MSS.0b013e3182a0595f.
   PubMed Web of Science ®Google Scholar
• Fini NA, Holland AE, Keating J, Simek J, Bernhardt J. How is physical activity monitored in people following stroke? Disabil Rehabil. 2015;37(19):1717–31. doi:10.3109/09638288.2014.978508. Epub 2014/ 11/07. PubMed PMID: 25374044.
   PubMed Web of Science ®Google Scholar
• King A, McCluskey A, Schurr K. 2011. The time use and activity levels of inpatients in a co-located acute and rehabilitation stroke unit: an observational study. Top Stroke Rehabil. 18(Suppl 1):654–65. doi:10.1310/tsr18s01-654.
   PubMed Web of Science ®Google Scholar
• Hassett L, Wong S, Sheaves E, Daher M, Grady A, Egan C, Seeto C, Hosking T, Moseley A. 2018. Time use and physical activity in a specialised brain injury rehabilitation unit: an observational study. Brain Inj. 32(7):850–57. doi:10.1080/02699052.2018.1463454.
   PubMed Web of Science ®Google Scholar
• Elmesmari R, Reilly JJ, Martin A, Paton JY. Accelerometer measured levels of moderate-to-vigorous intensity physical activity and sedentary time in children and adolescents with chronic disease: A systematic review and meta-analysis. PloS One. 2017;12(6):e0179429. doi:10.1371/journal.pone.0179429. Epub 2017/ 06/24. PubMed PMID: 28640907; PubMed Central PMCID: PMCPMC5480890.
   PubMed Web of Science ®Google Scholar
• Tomkins-Lane CC, Haig AJ. A review of activity monitors as a new technology for objectifying function in lumbar spinal stenosis. J Back Musculoskelet Rehabil. 2012;25(3):177–85. doi:10.3233/bmr-2012-0325. Epub 2012/ 09/01. PubMed PMID: 22935856.
   PubMed Web of Science ®Google Scholar
• van Laarhoven SN, Lipperts M, Bolink SA, Senden R, Heyligers IC, Grimm B. Validation of a novel activity monitor in impaired, slow-walking, crutch-supported patients. Ann Phys Rehabil Med. 2016;59(5–6):308–13. doi:10.1016/j.rehab.2016.05.006. Epub 2016/ 09/24. PubMed PMID: 27659237.
   PubMed Web of Science ®Google Scholar
• Ji-Young L, Suyeon K, Won-Seok K, Soo Jung H, Jihong P, Nam-Jong P. 2018. Feasibility, reliability, and validity of using accelerometers to measure physical activities of patients with stroke during inpatient rehabilitation. PLoS ONE. 13(12):e0209607. doi:10.1371/journal.pone.0209607.
   PubMed Web of Science ®Google Scholar
• Butler EN, Evenson KR. Prevalence of physical activity and sedentary behavior among stroke survivors in the United States. Top Stroke Rehabil. 2014;21(3):246–55. doi:10.1310/tsr2103-246. Epub 2014/ 07/06. PubMed PMID: 24985392; PubMed Central PMCID: PMCPMC4146341.
   PubMed Web of Science ®Google Scholar
• Chen H-L, Lin K-C, Hsieh Y-W, Wu C-Y, Liing R-J, Chen C-L. 2018. A study of predictive validity, responsiveness, and minimal clinically important difference of arm accelerometer in real-world activity of patients with chronic stroke. Clin Rehabil. 32(1):75–83. doi:10.1177/0269215517712042.
   PubMed Web of Science ®Google Scholar
• Gebruers N, Vanroy C, Truijen S, Engelborghs S, De Deyn PP. 2010. Monitoring of physical activity after stroke: a systematic review of accelerometry-based measures. Arch Phys Med Rehabil. 91(2):288–97. doi:10.1016/j.apmr.2009.10.025.
   PubMed Web of Science ®Google Scholar
• Luo W, Phung D, Tran T, Gupta S, Rana S, Karmakar C, Shilton A, Yearwood J, Dimitrova N, Ho TB, et al. Guidelines for developing and reporting machine learning predictive models in biomedical research: a multidisciplinary view. J Med Internet Res. 2016;18:e323.
   PubMed Web of Science ®Google Scholar
• Bossuyt PM, Cohen JF, Gatsonis CA, Korevaar DA. 2016. STARD 2015: updated reporting guidelines for all diagnostic accuracy studies. Ann Transl Med. 4(4):urn:2305–5839. doi:10.3978/j..2305-5839.2016.02.06.
   Web of Science ®Google Scholar
• Anderson JL, Green AJ, Yoward LS, Hall HK. 2018. Validity and reliability of accelerometry in identification of lying, sitting, standing or purposeful activity in adult hospital inpatients recovering from acute or critical illness: a systematic review. Clin Rehabil. 32(2):233–42. doi:10.1177/0269215517724850.
   PubMed Web of Science ®Google Scholar
• Dobkin BH, Xu HX, Batalin HM, Thomas HS, Kaiser HW. 2011. Reliability and validity of bilateral ankle accelerometer algorithms for activity recognition and walking speed after stroke. Stroke. 42(8):2246–50. doi:10.1161/STROKEAHA.110.611095.
   PubMed Web of Science ®Google Scholar
• Lau H-Y, Tong K-Y, Zhu H. 2009. Support vector machine for classification of walking conditions of persons after stroke with dropped foot. Hum Mov Sci. 28(4):504–14. doi:10.1016/j.humov.2008.12.003.
   PubMed Web of Science ®Google Scholar
• Harris PA, Taylor R, Thielke R, Payne J, Gonzalez N, Conde JG. 2009. Research electronic data capture (REDCap)—A metadata-driven methodology and workflow process for providing translational research informatics support. J Biomed Inform. 42(2):377–81. doi:10.1016/j.jbi.2008.08.010.
   PubMed Web of Science ®Google Scholar
• Harris PA, Taylor R, Minor BL, Elliott V, Fernandez M, O’Neal L, McLeod L, Delacqua G, Delacqua F, Kirby J, et al. The REDCap consortium: building an international community of software platform partners. J Biomed Inform. 2019;95:103208.
   PubMed Web of Science ®Google Scholar
• Gade R, Moeslund T. 2014. Thermal cameras and applications: a survey. Mach Vis Appl. 25(1):245–62. doi:10.1007/s00138-013-0570-5.
   Web of Science ®Google Scholar
• Clarke CL, Taylor J, Crighton LJ, Goodbrand JA, McMurdo MET, Witham MD. 2017. Validation of the AX3 triaxial accelerometer in older functionally impaired people. Aging Clin Exp Res. 29(3):451–57. doi:10.1007/s40520-016-0604-8.
   PubMed Web of Science ®Google Scholar
• Witten IH, Eibe F, Mark AH. Data mining: practical machine learning tools and techniques. 3 ed. Witten IH, Frank E, Hall MA, editors. Burlington, MA: Morgan Kaufmann; 2011.
   Google Scholar
• Breiman L. 2001. Random forests. Mach Learn. 45(1):5–32. doi:10.1023/A:1010933404324.
   Web of Science ®Google Scholar
• Yan N, Chen J, Yu T, Feature A. Set for the similar activity recognition using smartphone. IEEE. 2018;1–6.
   Google Scholar
• Eysenbach G, Dobkin B, Albert M, O’Brien MK, Shawen N, Mummidisetty CK, Kaur S, Bo X, Poellabauer C, Kording K, et al. Activity recognition for persons with stroke using mobile phone technology: toward improved performance in a home setting. J Med Internet Res. 2017;19:5.
   Google Scholar
• Saver JL, Filip B, Hamilton S, Yanes A, Craig S, Cho M, Conwit R, Starkman S. Improving the reliability of stroke disability grading in clinical trials and clinical practice: the rankin focused assessment (RFA). Stroke. 2010;41(5):992–95. doi:10.1161/STROKEAHA.109.571364. Epub 2010/ 04/01. PubMed PMID: 20360551.
   PubMed Web of Science ®Google Scholar
• Stubbs PW, Pallesen H, Pedersen AR, Nielsen JF. 2014. Using EFA and FIM rating scales could provide a more complete assessment of patients with acquired brain injury. Disabil Rehabil. 36(26):2278–81. doi:10.3109/09638288.2014.904935.
   PubMed Web of Science ®Google Scholar
• Godfrey A, Conway R, Leonard M, Meagher D, Ólaighin GM. 2010. Motion analysis in delirium: A discrete approach in determining physical activity for the purpose of delirium motoric subtyping. Med Eng Phys. 32(2):101–10. doi:10.1016/j.medengphy.2009.10.012.
   PubMed Web of Science ®Google Scholar
• Rowlands VA, Olds ST, Hillsdon LM, Pulsford GR, Hurst RT, Eston RR, Gomersall RS, Johnston RK, Langford RJ. 2014. Assessing sedentary behavior with the GENEActiv: introducing the sedentary sphere. Med Sci Sports Exerc. 46(6):1235–47. doi:10.1249/MSS.0000000000000224.
   PubMed Web of Science ®Google Scholar
• Lipperts M, van Laarhoven S, Senden R, Heyligers I, Grimm B. 2017. Clinical validation of a body-fixed 3D accelerometer and algorithm for activity monitoring in orthopaedic patients. J Orthop Transl. 11(C):19–29. doi:10.1016/j.jot.2017.02.003.
   PubMed Web of Science ®Google Scholar
• Taraldsen K, Askim T, Sletvold O, Einarsen EK, Bjåstad KG, Indredavik B, Helbostad JL. 2011. Evaluation of a body-worn sensor system to measure physical activity in older people with impaired function. Phys Ther. 91(2):277–85. doi:10.2522/ptj.20100159.
   PubMed Web of Science ®Google Scholar
• Brown CJ, Roth DL, Allman RM. 2008. Validation of use of wireless monitors to measure levels of mobility during hospitalization. J Rehabil Res Dev. 45(4):551. doi:10.1682/JRRD.2007.06.0086.
   PubMedGoogle Scholar
• Pedersen MM, Bodilsen AC, Petersen J, Beyer N, Andersen O, Lawson-Smith L, Kehlet H, Bandholm T. 2013. Twenty-four-hour mobility during acute hospitalization in older medical patients. J Gerontol A Biol Sci Med Sci. 68(3):331–37. doi:10.1093/gerona/gls165.
   PubMed Web of Science ®Google Scholar
• Lyden HK, John HD, Dall HP, Granat HM. 2016. Differentiating sitting and lying using a thigh-worn accelerometer. Med Sci Sports Exerc. 48(4):742–47. doi:10.1249/MSS.0000000000000804.
   PubMed Web of Science ®Google Scholar
• van Hees VT, Golubic R, Ekelund U, Brage S. 2013. Impact of study design on development and evaluation of an activity-type classifier. J Appl Physiol (Bethesda, Md: 1985). 114(8):1042–51. doi:10.1152/japplphysiol.00984.2012.
   PubMed Web of Science ®Google Scholar
• Steins D, Dawes H, Esser P, Collett J. 2014. Wearable accelerometry-based technology capable of assessing functional activities in neurological populations in community settings: a systematic review. J Neuroeng Rehabil. 11(1):36. doi:10.1186/1743-0003-11-36.
   PubMed Web of Science ®Google Scholar