Primary Objective: The primary objective is to develop supervised algorithms for the classification of motor intentions for different activities of daily living. These algorithms are developed for both bipolar surface electromyography as well as…
ID
Source
Brief title
Condition
- Other condition
- Bone and joint therapeutic procedures
Synonym
Health condition
N.v.t.
Research involving
Sponsors and support
Intervention
Outcome measures
Primary outcome
The primary study parameter is the misclassification rate of a classifier.
The misclssification rate of the classifier that is based on biplor EMG and
HD-EMG will be compared. In addition, misclassification rates of classifiers
developed with different techniques will also be compared.
Secondary outcome
Secundary study parameters are:
- The misclassification rate for unsupervised algorithms Unsupervised
algorithms will also be compared to supervised algorithms. To determine - - The
effect of repeated measurements on the robustness of the classifier and
regressor
- The effect of additional sensor information on misclassification rate by
using the raw IMU sensor data from the Xsens suit. This information is recorded
during measurements anyway, as Xsens uses this information in their
biomechanical model to reconstruct movements.
- The effect of prosthesis type on the robustness of the classifier
Background summary
The control of prosthetic knees is not intuitive. Where individuals without an
amputation can flex and extend their knee voluntarily, individuals with an
amputation cannot do that but have to movement of the residual leg (stump) to
control the movement of the prosthetic knee. To realize intuitive control,
researcher are working to incorporate muscle activity, as measured with
electromyography, in prosthetic knee control. By investigating muscle activity
one can predict the activity somebody is (about to be) performing. Based on the
activity that is being performed, the prosthetis can be set to optimal settings
that are needed to successfully complete the activity. There are several ways
to obtain muscle activity, including bipolar (using two electrodes) and
high-density EMG (HD-EMG; using a grid of electrodes). Classifiers based on
HD-EMG might be superior to classifiers based on HD-EMG because with HD-EMG
more data is obtained and it is less sensitive to electrode placement. The use
of HD-EMG, however, has not been studied before in the context of prosthetic
knee control.
Study objective
Primary Objective:
The primary objective is to develop supervised algorithms for the
classification of motor intentions for different activities of daily living.
These algorithms are developed for both bipolar surface electromyography as
well as High-Density electromyography (HD-EMG).
Secondary Objective(s):
The secondary objectives are:
- Comparison of different methods that can be used to classify motor intentions
in terms of accuracy of correct classification of the activity of daily living.
- Investigate the added value of additional (non-electromyography) sensors such
as inertial magnetic units on the accuracy of the methods for the
classification of motor intentions.
- Determining the consistency of the electromyography signal over the course of
several measurements conducted on different days.
- Development of unsupervised algorithms for classification of motor intentions
- Development of regression algorithms to estimate joint angles
- Development of classifiers which are robust for prosthesis type
Study design
Observational study with a single measurement (n=60) and repeated (up to four)
measurements (n=15) and measurements on a subgroup of individuals with an
amputation (n=5) getting an intervention (active prosthesis).
Intervention
Subgroup of individuals with an amputation (n=5) will be walking on an active
prothesis during train and measurement sessions. This group also takes the
prothesis home between the trainingsessions for additional practice.
Study burden and risks
The burden and risk associated with participation is considered low. The
activities that are studied are activities that are routinely performed during
daily life. In addition, the measurements do not interfere with the execution
of daily life therefore not putting an additional strain on subjects to execute
the activities. Participants do not benefit from participation.
Roessinghsbleekweg 33b
Enschede 7522 AH
NL
Roessinghsbleekweg 33b
Enschede 7522 AH
NL
Listed location countries
Age
Inclusion criteria
Individuals without an amputation
- Aged 18 or above.
- Able to perform low to moderate vigorous physical activity for a duration of
3 hours including breaks. , Individuals with an amputation
- Aged 18 or above.
- Unilateral transfemoral amputation or knee disarticulation.
- Functional level from K2 to K4.
o Level 2: The patient has the ability or potential for ambulation with
the ability to traverse low
level environmental barriers such as curbs, stairs, or
uneven surfaces. Typical of the
community ambulator.
o Level 3: The patient has the ability or potential for ambulation with
variable cadence. Typical of
the community ambulatory who has the ability to traverse
most environmental
barriers and may have vocational, therapeutic, or
exercise activity that demands
prosthetic utilization beyond simple locomotion.
o Level 4: The patient has the ability or potential for prosthetic
ambulation that exceeds basic
ambulation skills, exhibiting high impact, stress, or
energy levels. Typical of the
prosthetic demands of the child, active adult, or
athlete.
- Able to perform low to moderate vigorous physical activity for a duration of
3 hours including breaks.
- At least one year after amputation.
Exclusion criteria
Individuals without an amputation
- Not willing to consent to participate in the study.
- Musculoskeletal problems influencing walking ability., Individuals with an
amputation:
- Not willing to consent to participate in the study.
- Other musculoskeletal problems influencing walking ability.
- Stump problems/bad socket fitting
Design
Recruitment
Followed up by the following (possibly more current) registration
No registrations found.
Other (possibly less up-to-date) registrations in this register
No registrations found.
In other registers
| Register | ID |
|---|---|
| CCMO | NL67247.044.18 |