Accelerometer devices are becoming efficient tools in clinical studies for automatically measuring the activities of daily living. Such data provides a time series describing activity level at every second and displays a subject’s activity pattern throughout a day. However, the analysis of such data is very challenging due to the large number of observations produced each second and the variability among subjects. The purpose of this study is to develop efficient statistical analysis techniques for predicting the recovery level of the upper limb function after stroke based on the free-living accelerometer data. We propose to use a Gaussian Mixture Model (GMM)-based method for clustering and extracting new features to capture the information contained in the raw data. A nonlinear mixed effects model with Gaussian Process prior for the random effects is developed as the predictive model for evaluating the recovery level of the upper limb function. Results of applying to the accelerometer data for patients after stroke are presented.
JørgensenHSNakayamaHRaaschouHO, et al.
Stroke: neurologic and functional recovery the Copenhagen Stroke Study. Phys Med Rehabil Clin1999;
10: 887–906.
3.
Nichols-LarsenDSClarkPCZeringueA, et al.
Factors influencing stroke survivors’ quality of life during subacute recovery.Am Heart Assoc2005;
36: 1480–1484.
4.
LangCEBlandMDBaileyRR, et al.
Assessment of upper extremity impairment, function, and activity after stroke: foundations for clinical decision making.J Hand Ther2013;
26: 104–115.
5.
LyleRC.A performance test for assessment of upper limb function in physical rehabilitation treatment and research. Int J Rehabil Res1981;
4: 483–492.
6.
MathiowetzVVollandGKashmanN, et al.
Adult norms for the Box and Block Test of manual dexterity.Am J Occup Ther1985;
39: 386–391.
7.
WolfSLLecrawDEBartonLA, et al.
Forced use of hemiplegic upper extremities to reverse the effect of learned nonuse among chronic stroke and head-injured patients. Exp Neurol1989;
104: 125–132.
8.
BarrecaSRStratfordPWLambertCL, et al.
Test-retest reliability, validity, and sensitivity of the Chedoke arm and hand activity inventory: a new measure of upper-limb function for survivors of stroke.Arch Phys Med Rehabil2005;
86: 1616–1622.
9.
DuncanPWWallaceDLaiSM, et al.
The stroke impact scale version 2.0: evaluation of reliability, validity, and sensitivity to change.Stroke1999;
30: 2131–2140.
10.
TaubEMillerNENovackTA, et al.
Technique to improve chronic motor deficit after stroke.Arch Phys Med Rehabil1993;
74: 347–354.
11.
SerradillaJShiJQChengYF, et al. Automatic assessment of upper limb function during play of the action video game, circus challenge: validity and sensitivity to change. In: 2014 3nd International conference on serious games and applications for health (SeGAH), 2014, pp.1-7.
12.
SmithBALangCE.Sensor measures of symmetry quantify upper limb movement in the natural environment across the lifespan. Arch Phys Med Rehabil, https://doi.org/10.1016/j.apmr.2019.01.004 (2019, accessed 14 June 2019).
13.
AllenFRAmbikairajahELovellNH, et al.
Classification of a known sequence of motions and postures from accelerometry data using adapted Gaussian mixture models.Physiol Meas2006;
27: 935.
14.
PreeceSJGoulermasJYKenneyLPJ, et al. A comparison of different feature generation methods in activity classification. In: Proc ICAMPAM (Rotterdam). May 2008, pp. 87.
15.
WangNAmbikairajahELovellNH, et al. Accelerometry based classification of walking patterns using time-frequency analysis. In: 29th Annual international conference of the IEEE engineering in medicine and biology society, 2007, pp.4899-4902.
16.
WalseKHDharaskarRVThakareVM. PCA based optimal ANN classifiers for human activity recognition using mobile sensors data. In: Proceedings of first international conference on information and communication technology for intelligent systems, 2016, volume no.1, pp.429–436.
17.
BensonLCClermontCAOsisST, et al.
Classifying running speed conditions using a single wearable sensor: Optimal segmentation and feature extraction methods.J Biomech2018;
71: 94–99.
18.
GertheissJGoldsmithJCrainiceanuC, et al.
Longitudinal scalar-on-functions regression with application to tractography data.Biostatistics2013;
14: 447–461.
19.
GoldsmithJCrainiceanuCMCaffoB, et al.
Longitudinal penalized functional regression for cognitive outcomes on neuronal tract measurements.J R Stat Soc Ser C Appl Stat2012;
61: 453–469.
20.
FuchsKScheiplFGrevenS.Penalized scalar-on-functions regression with interaction term. Comput Stat Data Anal2015;
81: 38–51.
21.
CiarleglioAOgdenRT.Wavelet-based scalar-on-function finite mixture regression models.Comput Stat Data Anal2016;
93: 86–96.
LiHZhangYCarrollRJ, et al.
A joint modeling and estimation method for multivariate longitudinal data with mixed types of responses to analyze physical activity data generated by accelerometers.Stat Med2017;
36: 4028–4040.
24.
MadansinghSIMurphreeDHKaufmanKR, et al.
Assessment of gait kinetics in post-menopausal women using tri-axial ankle accelerometers during barefoot walking.Gait Posture2019;
69: 85–90.
25.
XuYSNelsonSKerrJ, et al.
Statistical approaches to account for missing values in accelerometer data: applications to modeling physical activity.Stat Meth Med Res2018;
27: 1168–1186.
26.
ShiJQChoiT.Gaussian process regression analysis for functional data.
New York:
Chapman and Hall/CRC, 2011.
27.
ShiJQWangBWillEJ, et al.
Mixed-effects Gaussian process functional regression models with application to dose–response curve prediction.Stat Med2012;
31: 3165–3177.
28.
WangBShiJQ.Generalized Gaussian process regression model for non-Gaussian functional data. J Am Stat Assoc2014;
109: 1123–1133.
29.
BoutenCVKoekkoekKTVerduinM, et al.
A triaxial accelerometer and portable data processing unit for the assessment of daily physical activity. IEEE Trans Biomed Eng1997;
44: 136–147.
30.
LanghornePCouparFPollockA.Motor recovery after stroke: a systematic review. Lancet Neurol2009;
8: 741–754.
31.
BishopCM.Pattern recognition and machine learning.
New York:
Springer, 2006.
32.
TibshiraniR.Regression shrinkage and selection via the lasso. J R Stat Soc Ser B Methodol1996;
58: 267–288.
33.
FanJLiR.Variable selection via nonconcave penalized likelihood and its oracle properties. J Am Stat Assoc2001;
96: 1348–1360.
34.
ShiJQChengYF. GPFDA: apply Gaussian process in functional data analysis. R package version 2.2, https://CRAN.R-project.org/package=GPFDA (2014, accessed 14 June 2019).
35.
ShiJQWangB.Curve prediction and clustering with mixtures of Gaussian process functional regression models. Stat Comput2008;
18: 267–283.
36.
ChoiYTaylorJTibshiraniR.Selecting the number of principal components: estimation of the true rank of a noisy matrix. Ann Statist2017;
45: 2590–2617.
37.
LerouxBG.Consistent estimation of a mixing distribution. Ann Stat1992;
20: 1350–1360.
38.
StephensM.Bayesian analysis of mixture models with an unknown number of components – an alternative to reversible jump methods. Ann Stat2000;
28: 40–74.
39.
GrurDRasmussenCE.Dirichlet process Gaussian mixture models: choice of the base distribution.J Comput Sci Tech2010;
25: 615–626.
CaoCZShiJQLeeY.Robust functional regression model for marginal mean and subject-specific inferences. Stat Meth Med Res2019;
27: 3236–3254.
42.
WangZFShiJQLeeY.Extended t-process regression models. J Stat Plan Inference2017;
189: 38–60.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
