Inertial sensor-based gait parameters reflect patient-reported fatigue in multiple sclerosis.
Accelerometer
Digital biomarker
Fatigue
Gait
IMU
MS
Machine learning
Journal
Journal of neuroengineering and rehabilitation
ISSN: 1743-0003
Titre abrégé: J Neuroeng Rehabil
Pays: England
ID NLM: 101232233
Informations de publication
Date de publication:
18 12 2020
18 12 2020
Historique:
received:
18
09
2020
accepted:
09
12
2020
entrez:
19
12
2020
pubmed:
20
12
2020
medline:
26
5
2021
Statut:
epublish
Résumé
Multiple sclerosis (MS) is a disabling disease affecting the central nervous system and consequently the whole body's functional systems resulting in different gait disorders. Fatigue is the most common symptom in MS with a prevalence of 80%. Previous research studied the relation between fatigue and gait impairment using stationary gait analysis systems and short gait tests (e.g. timed 25 ft walk). However, wearable inertial sensors providing gait data from longer and continuous gait bouts have not been used to assess the relation between fatigue and gait parameters in MS. Therefore, the aim of this study was to evaluate the association between fatigue and spatio-temporal gait parameters extracted from wearable foot-worn sensors and to predict the degree of fatigue. Forty-nine patients with MS (32 women; 17 men; aged 41.6 years, EDSS 1.0-6.5) were included where each participant was equipped with a small Inertial Measurement Unit (IMU) on each foot. Spatio-temporal gait parameters were obtained from the 6-min walking test, and the Borg scale of perceived exertion was used to represent fatigue. Gait parameters were normalized by taking the difference of averaged gait parameters between the beginning and end of the test to eliminate inter-individual differences. Afterwards, normalized parameters were transformed to principle components that were used as input to a Random Forest regression model to formulate the relationship between gait parameters and fatigue. Six principal components were used as input to our model explaining more than 90% of variance within our dataset. Random Forest regression was used to predict fatigue. The model was validated using 10-fold cross validation and the mean absolute error was 1.38 points. Principal components consisting mainly of stride time, maximum toe clearance, heel strike angle, and stride length had large contributions (67%) to the predictions made by the Random Forest. The level of fatigue can be predicted based on spatio-temporal gait parameters obtained from an IMU based system. The results can help therapists to monitor fatigue before and after treatment and in rehabilitation programs to evaluate their efficacy. Furthermore, this can be used in home monitoring scenarios where therapists can monitor fatigue using IMUs reducing time and effort of patients and therapists.
Sections du résumé
BACKGROUND
Multiple sclerosis (MS) is a disabling disease affecting the central nervous system and consequently the whole body's functional systems resulting in different gait disorders. Fatigue is the most common symptom in MS with a prevalence of 80%. Previous research studied the relation between fatigue and gait impairment using stationary gait analysis systems and short gait tests (e.g. timed 25 ft walk). However, wearable inertial sensors providing gait data from longer and continuous gait bouts have not been used to assess the relation between fatigue and gait parameters in MS. Therefore, the aim of this study was to evaluate the association between fatigue and spatio-temporal gait parameters extracted from wearable foot-worn sensors and to predict the degree of fatigue.
METHODS
Forty-nine patients with MS (32 women; 17 men; aged 41.6 years, EDSS 1.0-6.5) were included where each participant was equipped with a small Inertial Measurement Unit (IMU) on each foot. Spatio-temporal gait parameters were obtained from the 6-min walking test, and the Borg scale of perceived exertion was used to represent fatigue. Gait parameters were normalized by taking the difference of averaged gait parameters between the beginning and end of the test to eliminate inter-individual differences. Afterwards, normalized parameters were transformed to principle components that were used as input to a Random Forest regression model to formulate the relationship between gait parameters and fatigue.
RESULTS
Six principal components were used as input to our model explaining more than 90% of variance within our dataset. Random Forest regression was used to predict fatigue. The model was validated using 10-fold cross validation and the mean absolute error was 1.38 points. Principal components consisting mainly of stride time, maximum toe clearance, heel strike angle, and stride length had large contributions (67%) to the predictions made by the Random Forest.
CONCLUSIONS
The level of fatigue can be predicted based on spatio-temporal gait parameters obtained from an IMU based system. The results can help therapists to monitor fatigue before and after treatment and in rehabilitation programs to evaluate their efficacy. Furthermore, this can be used in home monitoring scenarios where therapists can monitor fatigue using IMUs reducing time and effort of patients and therapists.
Identifiants
pubmed: 33339530
doi: 10.1186/s12984-020-00798-9
pii: 10.1186/s12984-020-00798-9
pmc: PMC7749504
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
165Références
Brain Behav. 2018 Jun;8(6):e00977
pubmed: 29733529
J Neuroeng Rehabil. 2015 Apr 02;12:34
pubmed: 25885551
J Neurol. 2011 May;258(5):889-94
pubmed: 21076978
Med Sci Sports Exerc. 1982;14(5):377-81
pubmed: 7154893
Mult Scler Relat Disord. 2019 Dec 23;39:101903
pubmed: 31927199
Neurorehabil Neural Repair. 2016 May;30(4):373-83
pubmed: 26216790
J Biomech. 1996 May;29(5):619-25
pubmed: 8707788
Eur J Sport Sci. 2016 Nov;16(8):885-94
pubmed: 27240002
IEEE Trans Biomed Eng. 2013 Jan;60(1):155-8
pubmed: 23268531
Muscles Ligaments Tendons J. 2017 May 10;7(1):173-179
pubmed: 28717626
Arch Phys Med Rehabil. 1984 Mar;65(3):135-8
pubmed: 6703889
BMJ. 1997 May 31;314(7094):1580-3
pubmed: 9169401
J Sports Sci. 2011 Dec;29(15):1635-44
pubmed: 21995301
Sci Rep. 2019 Feb 20;9(1):2391
pubmed: 30787319
J Huntingtons Dis. 2016 Jun 18;5(2):199-206
pubmed: 27341134
Mult Scler. 2000 Jun;6(3):181-5
pubmed: 10871830
J Neuroeng Rehabil. 2011 Oct 26;8:59
pubmed: 22029427
Sensors (Basel). 2019 Dec 21;20(1):
pubmed: 31877760
Int J MS Care. 2016 Mar-Apr;18(2):71-7
pubmed: 27134580
Gait Posture. 2016 Jan;43:204-9
pubmed: 26481257
Front Neurol. 2019 Jan 22;10:5
pubmed: 30723450
Mult Scler. 2008 Apr;14(3):383-90
pubmed: 17942508
Arch Neurol. 1989 Oct;46(10):1121-3
pubmed: 2803071
Sensors (Basel). 2014 Feb 19;14(2):3362-94
pubmed: 24556672
J Neurol. 2019 Sep;266(Suppl 1):118-122
pubmed: 31134375
Sensors (Basel). 2015 Mar 17;15(3):6419-40
pubmed: 25789489
Gait Posture. 2001 May;13(3):193-201
pubmed: 11323225
IEEE Trans Biomed Eng. 2015 Apr;62(4):1089-97
pubmed: 25389237
J Neurol. 2020 Jun;267(6):1594-1601
pubmed: 32048014
PLoS One. 2016 Feb 10;11(2):e0148997
pubmed: 26863109
J Biomech. 2003 Apr;36(4):599-603
pubmed: 12600350
Disabil Rehabil. 2016;38(6):535-43
pubmed: 25990573
PLoS One. 2017 Oct 11;12(10):e0183989
pubmed: 29020012
J Neurol Neurosurg Psychiatry. 2002 Mar;72(3):361-5
pubmed: 11861697
Eur J Neurol. 1998 Nov;5(6):579-585
pubmed: 10210893
Mult Scler. 2009 Jul;15(7):818-27
pubmed: 19465444
Phys Ther. 2014 May;94(5):593-608
pubmed: 24363338
Int J MS Care. 2017 Mar-Apr;19(2):91-98
pubmed: 32607067
PLoS One. 2018 May 1;13(5):e0196463
pubmed: 29715279
Annu Int Conf IEEE Eng Med Biol Soc. 2010;2010:4411-4
pubmed: 21096462
Arch Phys Med Rehabil. 2016 Jun;97(6):974-82
pubmed: 26836954
Gait Posture. 2016 Feb;44:178-83
pubmed: 27004654
Neurorehabil Neural Repair. 2012 Jan;26(1):48-57
pubmed: 21856990
J Electromyogr Kinesiol. 2019 Aug;47:88-95
pubmed: 31136944
Mult Scler. 2006 Oct;12(5):613-9
pubmed: 17086908
Sensors (Basel). 2012;12(2):2255-83
pubmed: 22438763
Sensors (Basel). 2016 Aug 03;16(8):
pubmed: 27527172
Sensors (Basel). 2016 Jan 06;16(1):
pubmed: 26751449