journal article
Jan 01, 2021
Automating the Clinical Assessment of Independent Wheelchair Sitting Pivot Transfer Techniques
Topics in Spinal Cord Injury Rehabilitation
Vol. 27
No. 3
pp. 1-11
·
American Spinal Injury Association
Abstract
Background:
Using proper transfer technique can help to reduce forces and prevent secondary injuries. However, current assessment tools rely on the ability to subjectively identify harmful movement patterns.
Objectives:
The purpose of the study was to determine the accuracy of using a low-cost markerless motion capture camera and machine learning methods to evaluate the quality of independent wheelchair sitting pivot transfers. We hypothesized that the algorithms would be able to discern proper (low risk) and improper (high risk) wheelchair transfer techniques in accordance with component items on the Transfer Assessment Instrument (TAI).
Methods:
Transfer motions of 91 full-time wheelchair users were recorded and used to develop machine learning classifiers that could be used to discern proper from improper technique. The data were labeled using the TAI item scores. Eleven out of 18 TAI items were evaluated by the classifiers. Motion variables from the Kinect were inputted as the features. Random forests and k-nearest neighbors algorithms were chosen as the classifiers. Eighty percent of the data were used for model training and hyperparameter turning. The validation process was performed using 20% of the data as the test set.
Results:
The area under the receiver operating characteristic curve of the test set for each item was over 0.79. After adjusting the decision threshold, the precisions of the models were over 0.87, and the model accuracies were over 71%.
Conclusion:
The results show promise for the objective assessment of the transfer technique using a low cost camera and machine learning classifiers.
Using proper transfer technique can help to reduce forces and prevent secondary injuries. However, current assessment tools rely on the ability to subjectively identify harmful movement patterns.
Objectives:
The purpose of the study was to determine the accuracy of using a low-cost markerless motion capture camera and machine learning methods to evaluate the quality of independent wheelchair sitting pivot transfers. We hypothesized that the algorithms would be able to discern proper (low risk) and improper (high risk) wheelchair transfer techniques in accordance with component items on the Transfer Assessment Instrument (TAI).
Methods:
Transfer motions of 91 full-time wheelchair users were recorded and used to develop machine learning classifiers that could be used to discern proper from improper technique. The data were labeled using the TAI item scores. Eleven out of 18 TAI items were evaluated by the classifiers. Motion variables from the Kinect were inputted as the features. Random forests and k-nearest neighbors algorithms were chosen as the classifiers. Eighty percent of the data were used for model training and hyperparameter turning. The validation process was performed using 20% of the data as the test set.
Results:
The area under the receiver operating characteristic curve of the test set for each item was over 0.79. After adjusting the decision threshold, the precisions of the models were over 0.87, and the model accuracies were over 71%.
Conclusion:
The results show promise for the objective assessment of the transfer technique using a low cost camera and machine learning classifiers.
Topics
No keywords indexed for this article. Browse by subject →
References
60
[1]
Worobey
LA,
Zigler
CK,
Huzinec
R,
Rigot,
SK,
Sung
J,
Rice
LA.
Reliability and validity of the revised transfer assessment instrument.
Top Spinal Cord Inj Rehabil.
2018;
24(
3):
217–
226.
[2]
Tsai
CY,
Boninger
ML,
Bass
SR,
Koontz
AM.
Upper-limb biomechanical analysis of wheelchair transfer techniques in two toilet configurations.
Clin Biomech (Bristol, Avon).
2018;
55:
79–
85.
[3]
Koontz
AM,
Lin
YS,
Kankipati
P,
Boninger
ML,
Cooper
RA.
Development of custom measurement system for biomechanical evaluation of independent wheelchair transfers.
J Rehabil Res Dev.
2011;
48(
8):
1015–
1028.
[4]
Gagnon
D,
Nadeau
S,
Desjardins
P,
Noreau
L.
Biomechanical assessment of sitting pivot transfer tasks using a newly developed instrumented transfer system among long-term wheelchair users.
J Biomech.
2008;
41(
5):
1104–
1110.
[5]
Gagnon
D,
Nadeau
S,
Noreau
L,
Eng
JJ,
Gravel
D.
Trunk and upper extremity kinematics during sitting pivot transfers performed by individuals with spinal cord injury.
Clin Biomech (Bristol, Avon).
2008;
23(
3):
279–
290.
[6]
Clark
RA,
Pua
YH,
Fortin
K,
Ritchie
C,
Webster
KE,
Denehy
L,
Bryant
AL.
Validity of the Microsoft Kinect for assessment of postural control.
Gait Posture.
2012;
36(
3):
372–
377.
[7]
Galen
SS,
Pardo
V,
Wyatt
D,
Diamond
A,
Brodith
V,
Pavlov
A.
Validity of an interactive functional reach test.
Games Health J.
2015;
4(
4):
278–
284.
[8]
Shih
MC,
Wang
RY,
Cheng
SJ,
Yang
YR.
Effects of a balance-based exergaming intervention using the Kinect sensor on posture stability in individuals with Parkinson’s disease: A single-blinded randomized controlled trial.
J Neuroeng Rehabil.
2016;
13(
1):
78.
[9]
Dehbandi
B,
Barachant
A,
Smeragliuolo
AH,
Long
JD,
Bumanlag
SJ,
He
V,
Lampe
A,
Putrino,
D.
Using data from the Microsoft Kinect 2 to determine postural stability in healthy subjects: A feasibility trial.
PLoS One.
2017;
12(
2):
e0170890.
[10]
Eltoukhy
MA,
Kuenze
C,
Oh
J,
Signorile
JF.
Validation of static and dynamic balance assessment using Microsoft Kinect for young and elderly populations.
IEEE J Biomed Health Inform.
2018;
22(
1):
147–
153.
[11]
Galna
B,
Barry
G,
Jackson
D,
Mhiripiri
D,
Olivier
P,
Rochester
L.
Accuracy of the Microsoft Kinect sensor for measuring movement in people with Parkinson’s disease.
Gait Posture.
2014;
39(
4):
1062–
1068.
[12]
Gabel
M,
Gilad-Bachrach
R,
Renshaw
E,
Schuster
A.
Full body gait analysis with Kinect.
Conf Proc IEEE Eng Med Biol Soc.
2012;
2012:
1964–
1967.
[13]
Stone
EE,
Skubic
M.
Capturing habitual, in-home gait parameter trends using an inexpensive depth camera.
Conf Proc IEEE Eng Med Biol Soc.
2012;
2012:
5106–
5109.
[14]
Saposnik
G,
Levin
M,
Outcome Research Canada Working Group.
Virtual reality in stroke rehabilitation: A meta-analysis and implications for clinicians.
Stroke.
2011;
42(
5):
1380–
1386.
[15]
Bo
APL,
Hayashibe
M,
Poignet
P.
Joint angle estimation in rehabilitation with inertial sensors and its integration with Kinect.
Conf Proc IEEE Eng Med Biol Soc.
2011;
2011:
3479–
3483.
[16]
Da Gama
A,
Fallavollita
P,
Teichrieb
V,
Navab
N.
Motor rehabilitation using Kinect: A systematic review.
Games Health J.
2015;
4(
2):
123–
135.
[17]
Pastor
I,
Hayes
HA,
Bamberg
SJM.
A feasibility study of an upper limb rehabilitation system using Kinect and computer games.
Conf Proc IEEE Eng Med Biol Soc.
2012;
2012:
1286–
1289.
[18]
Dolatabadi
E,
Taati
B,
Mihailidis
A.
Automated classification of pathological gait after stroke using ubiquitous sensing technology.
Conf Proc IEEE Eng Med Biol Soc.
2016;
2016:
6150–
6153.
[19]
Leightley
D,
Yap
MH.
Digital analysis of sit-to-stand in masters athletes, healthy old people, and young adults using a depth sensor.
Healthcare (Basel).
2018;
6(
1).
[20]
Xu
X,
McGorry
RW.
The validity of the first and second generation Microsoft Kinect for identifying joint center locations during static postures.
Appl Ergon.
2015;
49:
47–
54.
[21]
Lin Wei
TB,
Ka
H,
Koontz
AM.
Evaluating wheelchair transfer technique by Microsoft Kinect.
Presented at International Seating Symposium;
2017;
Nashville, TN.
[22]
Tsai
CY,
Hogaboom
NS,
Boninger
ML,
Koontz
AM.
The relationship between independent transfer skills and upper limb kinetics in wheelchair users.
Biomed Res Int.
2014;
2014:
984526.
[23]
Halilaj,
E.,
Rajagopal
A,
Fiterau
M,
Hicks
JL,
Hastie
TJ,
Delp
SL.
Machine learning in human movement biomechanics: Best practices, common pitfalls, and new opportunities.
J Biomech.
2018;
81:
1–
11.
[24]
Barbareschi
G,
Holloway
C,
Bianchi-Berthouze
N,
Sonenblum
S,
Sprigle
S.
Use of a low-cost, chest-mounted accelerometer to evaluate transfer skills of wheelchair users during everyday activities: Observational study.
JMIR Rehabil Assist Technol.
2018;
5(
2):
e11748.
[25]
van den Berg-Emons
RJ,
L’Ortye
AA,
Buffart
LM,
Nieuwenhuijsen
C,
Nooijen
CF,
Bergen
MP,
Stam
HJ,
Bussmann
JB.
Validation of the Physical Activity Scale for individuals with physical disabilities.
Arch Phys Med Rehabil.
2011;
92(
6):
923–
928.
[26]
Microsoft. Azure Kinect body tracking joints. https://docs.microsoft.com/en-us/azure/kinect-dk/body-joints
[27]
Baldominos
A,
Saez
Y,
del Pozo
CG.
An approach to physical rehabilitation using state-of-the-art virtual reality and motion tracking technologies.
Procedia Comput Sci.
2015;
64:
10–
16.
[28]
Ferche
O,
Moldoveanu
A,
aMoldoveanu
F.
Evaluating lightweight optical hand tracking for virtual reality rehabilitation.
Romanian J Human-Comput Interact.
2016;
9(
2).
[29]
Cidota
MA,
Lukosch
SG,
Dezentje
P,
Bank
PJM,
Lukosch
HK,
Clifford
RMS.
Serious gaming in augmented reality using HMDs for assessment of upper extremity motor dysfunctions.
i-com J Interact Media.
2016;
15(
2):
155–
169.
[30]
Chhor
J,
Gong
Y,
Rau
PL.
Breakout: Design and evaluation of a serious game for health employing Intel RealSense.
Presented at: International Conference on Cross-Cultural Design;
2017:
531–
545.
[31]
Worobey
LA,
Zigler
CK,
Huzinec
R,
Rigot,
SK,
Sung
J,
Rice
LA.
Reliability and validity of the revised transfer assessment instrument.
Top Spinal Cord Inj Rehabil.
2018;
24(
3):
217–
226.
[32]
Tsai
CY,
Boninger
ML,
Bass
SR,
Koontz
AM.
Upper-limb biomechanical analysis of wheelchair transfer techniques in two toilet configurations.
Clin Biomech (Bristol, Avon).
2018;
55:
79–
85.
[33]
Koontz
AM,
Lin
YS,
Kankipati
P,
Boninger
ML,
Cooper
RA.
Development of custom measurement system for biomechanical evaluation of independent wheelchair transfers.
J Rehabil Res Dev.
2011;
48(
8):
1015–
1028.
[34]
Gagnon
D,
Nadeau
S,
Desjardins
P,
Noreau
L.
Biomechanical assessment of sitting pivot transfer tasks using a newly developed instrumented transfer system among long-term wheelchair users.
J Biomech.
2008;
41(
5):
1104–
1110.
[35]
Gagnon
D,
Nadeau
S,
Noreau
L,
Eng
JJ,
Gravel
D.
Trunk and upper extremity kinematics during sitting pivot transfers performed by individuals with spinal cord injury.
Clin Biomech (Bristol, Avon).
2008;
23(
3):
279–
290.
[36]
Clark
RA,
Pua
YH,
Fortin
K,
Ritchie
C,
Webster
KE,
Denehy
L,
Bryant
AL.
Validity of the Microsoft Kinect for assessment of postural control.
Gait Posture.
2012;
36(
3):
372–
377.
[37]
Galen
SS,
Pardo
V,
Wyatt
D,
Diamond
A,
Brodith
V,
Pavlov
A.
Validity of an interactive functional reach test.
Games Health J.
2015;
4(
4):
278–
284.
[38]
Shih
MC,
Wang
RY,
Cheng
SJ,
Yang
YR.
Effects of a balance-based exergaming intervention using the Kinect sensor on posture stability in individuals with Parkinson’s disease: A single-blinded randomized controlled trial.
J Neuroeng Rehabil.
2016;
13(
1):
78.
[39]
Dehbandi
B,
Barachant
A,
Smeragliuolo
AH,
Long
JD,
Bumanlag
SJ,
He
V,
Lampe
A,
Putrino,
D.
Using data from the Microsoft Kinect 2 to determine postural stability in healthy subjects: A feasibility trial.
PLoS One.
2017;
12(
2):
e0170890.
[40]
Eltoukhy
MA,
Kuenze
C,
Oh
J,
Signorile
JF.
Validation of static and dynamic balance assessment using Microsoft Kinect for young and elderly populations.
IEEE J Biomed Health Inform.
2018;
22(
1):
147–
153.
[41]
Galna
B,
Barry
G,
Jackson
D,
Mhiripiri
D,
Olivier
P,
Rochester
L.
Accuracy of the Microsoft Kinect sensor for measuring movement in people with Parkinson’s disease.
Gait Posture.
2014;
39(
4):
1062–
1068.
[42]
Gabel
M,
Gilad-Bachrach
R,
Renshaw
E,
Schuster
A.
Full body gait analysis with Kinect.
Conf Proc IEEE Eng Med Biol Soc.
2012;
2012:
1964–
1967.
[43]
Stone
EE,
Skubic
M.
Capturing habitual, in-home gait parameter trends using an inexpensive depth camera.
Conf Proc IEEE Eng Med Biol Soc.
2012;
2012:
5106–
5109.
[44]
Saposnik
G,
Levin
M,
Outcome Research Canada Working Group.
Virtual reality in stroke rehabilitation: A meta-analysis and implications for clinicians.
Stroke.
2011;
42(
5):
1380–
1386.
[45]
Bo
APL,
Hayashibe
M,
Poignet
P.
Joint angle estimation in rehabilitation with inertial sensors and its integration with Kinect.
Conf Proc IEEE Eng Med Biol Soc.
2011;
2011:
3479–
3483.
[46]
Da Gama
A,
Fallavollita
P,
Teichrieb
V,
Navab
N.
Motor rehabilitation using Kinect: A systematic review.
Games Health J.
2015;
4(
2):
123–
135.
[47]
Pastor
I,
Hayes
HA,
Bamberg
SJM.
A feasibility study of an upper limb rehabilitation system using Kinect and computer games.
Conf Proc IEEE Eng Med Biol Soc.
2012;
2012:
1286–
1289.
[48]
Dolatabadi
E,
Taati
B,
Mihailidis
A.
Automated classification of pathological gait after stroke using ubiquitous sensing technology.
Conf Proc IEEE Eng Med Biol Soc.
2016;
2016:
6150–
6153.
[49]
Leightley
D,
Yap
MH.
Digital analysis of sit-to-stand in masters athletes, healthy old people, and young adults using a depth sensor.
Healthcare (Basel).
2018;
6(
1).
[50]
Xu
X,
McGorry
RW.
The validity of the first and second generation Microsoft Kinect for identifying joint center locations during static postures.
Appl Ergon.
2015;
49:
47–
54.
Showing 50 of 60 references
Cited By
7
A systematic review of the applications of markerless motion capture (MMC) technology for clinical measurement in rehabilitation
Journal of NeuroEngineering and Reh...
Winnie W. T. Lam, Yuk Ming Tang · 2023
Metrics
7
Citations
60
References
Details
- Published
- Jan 01, 2021
- Vol/Issue
- 27(3)
- Pages
- 1-11
Authors
Cite This Article
Lin Wei, Cheng-Shiu Chung, Alicia M. Koontz (2021). Automating the Clinical Assessment of Independent Wheelchair Sitting Pivot Transfer Techniques. Topics in Spinal Cord Injury Rehabilitation, 27(3), 1-11. https://doi.org/10.46292/sci20-00050
Related
You May Also Like
International Standards for Neurological Classification of Spinal Cord Injury
Rudiger Rupp, Fin Biering-Sørensen · 2021
425 citations
International Standards to document remaining Autonomic Function after Spinal Cord Injury (ISAFSCI), First Edition 2012
Andrei Krassioukov, Fin Biering-Sorensen · 2012
46 citations
Effects of High-Intensity Interval Training Versus Moderate-Intensity Training on Cardiometabolic Health Markers in Individuals With Spinal Cord Injury: A Pilot Study
Kyle Graham, Ceren Yarar-Fisher · 2019
43 citations
Body Composition and Metabolic Assessment After Motor Complete Spinal Cord Injury: Development of a Clinically Relevant Equation to Estimate Body Fat
David R. Gater, Gary J. Farkas · 2021
36 citations
Improving Sexual Satisfaction in Persons with Spinal Cord Injuries: Collective Wisdom
Marcalee Alexander, Frédérique Courtois · 2017
29 citations