Automated Classification of Postural Control for Individuals With Parkinson’s Disease Using a Machine Learning Approach: A Preliminary Study

in Journal of Applied Biomechanics
View More View Less
  • 1 Texas State University
  • 2 Boise State University
  • 3 Northern Illinois University
Restricted access

Purchase article

USD  $24.95

Student 1 year online subscription

USD  $88.00

1 year online subscription

USD  $118.00

Student 2 year online subscription

USD  $168.00

2 year online subscription

USD  $224.00

The purposes of the study were (1) to compare postural sway between participants with Parkinson’s disease (PD) and healthy controls and (2) to develop and validate an automated classification of PD postural control patterns using a machine learning approach. A total of 9 participants in the early stage of PD and 12 healthy controls were recruited. Participants were instructed to stand on a force plate and maintain stillness for 2 minutes with eyes open and eyes closed. The center of pressure data were collected at 50 Hz. Linear displacements, standard deviations, total distances, sway areas, and multiscale entropy of center of pressure were calculated and compared using mixed-model analysis of variance. Five supervised machine learning algorithms (ie, logistic regression, K-nearest neighbors, Naïve Bayes, decision trees, and random forest) were used to classify PD postural control patterns. Participants with PD exhibited greater center of pressure sway and variability compared with controls. The K-nearest neighbor method exhibited the best prediction performance with an accuracy rate of up to 0.86. In conclusion, participants with PD exhibited impaired postural stability and their postural sway features could be identified by machine learning algorithms.

Li is with the Department of Health and Human Performance, Texas State University, San Marcos, TX, USA. Zhang is with the Center for Orthopaedic and Biomechanics Research, Department of Kinesiology, Boise State University, Boise, ID, USA. Odeh is with the Department of Physical Therapy, Northern Illinois University, DeKalb, IL, USA.

Zhang (shuqizhang@boisestate.edu) is corresponding author.
  • 1.

    de Lau LML, Breteler MMB. Epidemiology of Parkinson’s disease. Lancet Neurol. 2006;5(6):525535. PubMed ID: 16713924 doi:10.1016/S1474-4422(06)70471-9

    • Search Google Scholar
    • Export Citation
  • 2.

    Błaszczyk JW, Orawiec R, Duda-Kłodowska D, Opala G. Assessment of postural instability in patients with Parkinson’s disease. Exp Brain Res. 2007;183(1):107114. PubMed ID: 17609881 doi:10.1007/s00221-007-1024-y

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 3.

    Morris ME, Huxham F, McGinley J, Dodd K, Iansek R. The biomechanics and motor control of gait in Parkinson disease. Clin Biomech. 2001;16(6):459470. doi:10.1016/S0268-0033(01)00035-3

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 4.

    Cavanagh PR. A technique for averaging center of pressure paths from a force platform. J Biomech. 1978;11(10–12):487491. doi:10.1016/0021-9290(78)90060-X

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 5.

    Matinolli M, Korpelainen JT, Korpelainen R, Sotaniemi KA, Virranniemi M, Myllylä VV. Postural sway and falls in Parkinson’s disease: a regression approach. Mov Disord. 2007;22(13):19271935. PubMed ID: 17595043 doi:10.1002/mds.21633

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 6.

    Mancini M, Carlson-Kuhta P, Zampieri C, Nutt JG, Chiari L, Horak FB. Postural sway as a marker of progression in Parkinson’s disease: a pilot longitudinal study. Gait Posture. 2012;36(3):471476. PubMed ID: 22750016 doi:10.1016/j.gaitpost.2012.04.010

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 7.

    Schmit JM, Riley MA, Dalvi A, et al. Deterministic center of pressure patterns characterize postural instability in Parkinson’s disease. Exp Brain Res. 2006;168(3):357367. PubMed ID: 16047175 doi:10.1007/s00221-005-0094-y

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 8.

    Morrison S, Kerr G, Newell KM, Silburn PA. Differential time- and frequency-dependent structure of postural sway and finger tremor in Parkinson’s disease. Neurosci Lett. 2008;443(3):123128. PubMed ID: 18682273 doi:10.1016/j.neulet.2008.07.071

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 9.

    Rocchi L, Chiari L, Cappello A, Horak FB. Identification of distinct characteristics of postural sway in Parkinson’s disease: a feature selection procedure based on principal component analysis. Neurosci Lett. 2006;394(2):140145. PubMed ID: 16269212 doi:10.1016/j.neulet.2005.10.020

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 10.

    Kononenko I. Machine learning for medical diagnosis: history, state of the art and perspective. Artif Intell Med. 2001;23(1):89109. PubMed ID: 11470218 doi:10.1016/S0933-3657(01)00077-X

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 11.

    Kamruzzaman J, Begg RK. Support vector machines and other pattern recognition approaches to the diagnosis of cerebral palsy gait. IEEE Trans Biomed Eng. 2006;53(12, pt 1):24792490. PubMed ID: 17153205 doi:10.1109/TBME.2006.883697

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 12.

    Kaczmarczyk K, Wit A, Krawczyk M, Zaborski J. Gait classification in post-stroke patients using artificial neural networks. Gait Posture. 2009;30(2):207210. PubMed ID: 19464892 doi:10.1016/j.gaitpost.2009.04.010

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 13.

    Sun R, Hsieh KL, Sosnoff JJ. Fall risk prediction in multiple sclerosis using postural sway measures: a machine learning approach. Sci Rep. 2019;9(1):16154. PubMed ID: 31695127 doi:10.1038/s41598-019-52697-2

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 14.

    Pradhan C, Wuehr M, Akrami F, et al. Automated classification of neurological disorders of gait using spatio-temporal gait parameters. J Electromyogr Kinesiol. 2015;25(2):413422. PubMed ID: 25725811 doi:10.1016/j.jelekin.2015.01.004

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 15.

    Costa L, Gago MF, Yelshyna D, et al. Application of machine learning in postural control kinematics for the diagnosis of Alzheimer’s disease. Comput Intell Neurosci. 2016;2016(4):3891253. doi:10.1155/2016/3891253

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 16.

    Garcia-Masso X, Ye-Lin Y, Garcia-Casado J, Querol F, Gonzalez L-M. Assessment of haemophilic arthropathy through balance analysis: a promising tool. Comput Methods Biomech Biomed Engin. 2019;22(4):418425. PubMed ID: 30714398 doi:10.1080/10255842.2018.1561877

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 17.

    Zeng W, Liu F, Wang Q, Wang Y, Ma L, Zhang Y. Neuroscience letters Parkinson’s disease classification using gait analysis via deterministic learning. Neurosci Lett. 2016;633:268278. PubMed ID: 27693437 doi:10.1016/j.neulet.2016.09.043

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 18.

    Abdulhay E, Arunkumar N, Narasimhan K, Vellaiappan E, Venkatraman V. Gait and tremor investigation using machine learning techniques for the diagnosis of Parkinson disease. Future Gener Comput Syst. 2018;83:366373. doi:10.1016/j.future.2018.02.009

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 19.

    Zheng H, Yang M, Wang H, McClean S. Machine learning and statistical approaches to support the discrimination of neuro-degenerative diseases based on gait analysis. In: McClean S, Millard P, El-Darzi E, Nugent C, eds. Intelligent Patient Management. Berlin, Heidelberg: Springer Berlin Heidelberg; 2009:5770. doi:10.1007/978-3-642-00179-6_4

    • Search Google Scholar
    • Export Citation
  • 20.

    Eskofier BM, Lee SI, Daneault J, et al. Recent machine learning advancements in sensor-based mobility analysis: Deep learning for Parkinson’s disease assessment. 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). 2016:655658. doi:10.1109/EMBC.2016.7590787

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 21.

    Gaenslen A, Berg D. Early diagnosis of Parkinson’s disease. Int Rev Neurobiol. 2010;90:8192. PubMed ID: 20692495 doi:10.1016/s0074-7742(10)90006-8

  • 22.

    Hernandez L, Manning J, Zhang S. Voluntary control of breathing affects center of pressure complexity during static standing in healthy older adults. Gait Posture. 2019;68(2):488493. PubMed ID: 30616178 doi:10.1016/j.gaitpost.2018.12.032

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 23.

    Ferrazzoli D, Fasano A, Maestri R, et al. Balance dysfunction in Parkinson’s disease: the role of posturography in developing a rehabilitation program. Parkinsons Dis. 2015;2015(13):520128. PubMed ID: 26504611 doi:10.1155/2015/520128

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 24.

    Li Y, Mache MA, Todd TA. Complexity of center of pressure in postural control for children with autism spectrum disorders was partially compromised. J Appl Biomech. 2019;35(3):190195. PubMed ID: 30676165 doi:10.1123/jab.2018-0042

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 25.

    Gow JB, Peng C-K, Wayne MP, Ahn CA. Multiscale entropy analysis of center-of-pressure dynamics in human postural control: Methodological considerations. Entropy. 2015;17(12):79267947. doi:10.3390/e17127849

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 26.

    Li Y, Kakar RS, Fu Y-C, et al. Postural control of individuals with spinal fusion for adolescent idiopathic scoliosis. Clin Biomech. 2019;61:4651. doi:10.1016/j.clinbiomech.2018.11.001

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 27.

    Kotsiantis SB. Supervised machine learning: a review of classification techniques. Informatica. 2007;31(1):249268.

  • 28.

    Murthy SK. Automatic construction of decision trees from data: a multi-disciplinary survey. Data Min Knowl Discov. 1998;2(4):345389. doi:10.1023/A:1009744630224

    • Search Google Scholar
    • Export Citation
  • 29.

    Breiman L. Random forests. Mach Learn. 2001;45(1):532. doi:10.1023/A:1010933404324

  • 30.

    Bloem BR. Postural instability in Parkinson’s disease. Clin Neurol Neurosurg. 1992;94(2):4145. doi:10.1016/0303-8467(92)90018-X

  • 31.

    Vaugoyeau M, Viel S, Assaiante C, Amblard B, Azulay JP. Impaired vertical postural control and proprioceptive integration deficits in Parkinson’s disease. Neuroscience. 2007;146(2):852863. PubMed ID: 17367947 doi:10.1016/j.neuroscience.2007.01.052

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 32.

    Kerr GK, Worringham CJ, Cole MH, Lacherez PF, Wood JM, Silburn PA. Predictors of future falls in Parkinson disease. Neurology. 2010;75(2):116124. doi:10.1212/WNL.0b013e3181e7b688

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 33.

    Mak MKY, Pang MYC. Fear of falling is independently associated with recurrent falls in patients with Parkinson’s disease: a 1-year prospective study. J Neurol. 2009;256(10):16891695. PubMed ID: 19479166 doi:10.1007/s00415-009-5184-5

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 34.

    Genever RW, Downes TW, Medcalf P. Fracture rates in Parkinson’s disease compared with age- and gender-matched controls: a retrospective cohort study. Age Ageing. 2005;34(1):2124. PubMed ID: 15591480 doi:10.1093/ageing/afh203

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 35.

    Bloem BR, Grimbergen YA, Cramer M, Willemsen M, Zwinderman AH. Prospective assessment of falls in Parkinson’s disease. J Neurol. 2001;248(11):950958. PubMed ID: 11757958 doi:10.1007/s004150170047

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 36.

    Allen NE, Schwarzel AK, Canning CG. Recurrent falls in Parkinson’s disease: a systematic review. Parkinsons Dis. 2013;2013(3):906274. PubMed ID: 23533953 doi:10.1155/2013/906274

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 37.

    Saito T, Rehmsmeier M. The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLoS One. 2015;10(3):e0118432. PubMed ID: 25738806 doi:10.1371/journal.pone.0118432

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 38.

    Suchowersky O, Reich S, Perlmutter J, Zesiewicz T, Gronseth G, Weiner WJ. Practice parameter: diagnosis and prognosis of new onset Parkinson disease (an evidence-based review): report of the quality standards subcommittee of the American Academy of Neurology. Neurology. 2006;66(7):968975. PubMed ID: 16606907 doi:10.1212/01.wnl.0000215437.80053.d0

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 39.

    Harel B, Cannizzaro M, Snyder PJ. Variability in fundamental frequency during speech in prodromal and incipient Parkinson’s disease: a longitudinal case study. Brain Cogn. 2004;56(1):2429. PubMed ID: 15380872 doi:10.1016/j.bandc.2004.05.002

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 40.

    Rosenblum S, Samuel M, Zlotnik S, Erikh I, Schlesinger I. Handwriting as an objective tool for Parkinson’s disease diagnosis. J Neurol. 2013;260(9):23572361. PubMed ID: 23771509 doi:10.1007/s00415-013-6996-x

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 41.

    Stoessl AJ, Lehericy S, Strafella AP. Imaging insights into basal ganglia function, Parkinson’s disease, and dystonia. Lancet. 2014;384(9942):532544. doi:10.1016/S0140-6736(14)60041-6

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 42.

    Stoessl AJ, Martin WW, McKeown MJ, Sossi V. Advances in imaging in Parkinson’s disease. Lancet Neurol. 2011;10(11):9871001. PubMed ID: 22014434 doi:10.1016/S1474-4422(11)70214-9

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 43.

    Alam MN, Garg A, Munia TTK, Fazel-Rezai R, Tavakolian K. Vertical ground reaction force marker for Parkinson’s disease. PLoS One. 2017;12(5):e0175951. PubMed ID: 28493868 doi:10.1371/journal.pone.0175951

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 44.

    Mancini M, Salarian A, Carlson-Kuhta P, et al. ISway: a sensitive, valid and reliable measure of postural control. J Neuroeng Rehabil. 2012;9(1):59. doi:10.1186/1743-0003-9-59

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
All Time Past Year Past 30 Days
Abstract Views 486 486 409
Full Text Views 10 10 0
PDF Downloads 6 6 0