Dataset Information

Classification of functional and non-functional arm use by inertial measurement units in individuals with upper limb impairment after stroke.

ABSTRACT: Background: Arm use metrics derived from wrist-mounted movement sensors are widely used to quantify the upper limb performance in real-life conditions of individuals with stroke throughout motor recovery. The calculation of real-world use metrics, such as arm use duration and laterality preferences, relies on accurately identifying functional movements. Hence, classifying upper limb activity into functional and non-functional classes is paramount. Acceleration thresholds are conventionally used to distinguish these classes. However, these methods are challenged by the high inter and intra-individual variability of movement patterns. In this study, we developed and validated a machine learning classifier for this task and compared it to methods using conventional and optimal thresholds. Methods: Individuals after stroke were video-recorded in their home environment performing semi-naturalistic daily tasks while wearing wrist-mounted inertial measurement units. Data were labeled frame-by-frame following the Taxonomy of Functional Upper Limb Motion definitions, excluding whole-body movements, and sequenced into 1-s epochs. Actigraph counts were computed, and an optimal threshold for functional movement was determined by receiver operating characteristic curve analyses on group and individual levels. A logistic regression classifier was trained on the same labels using time and frequency domain features. Performance measures were compared between all classification methods. Results: Video data (6.5 h) of 14 individuals with mild-to-severe upper limb impairment were labeled. Optimal activity count thresholds were ≥20.1 for the affected side and ≥38.6 for the unaffected side and showed high predictive power with an area under the curve (95% CI) of 0.88 (0.87,0.89) and 0.86 (0.85, 0.87), respectively. A classification accuracy of around 80% was equivalent to the optimal threshold and machine learning methods and outperformed the conventional threshold by ∼10%. Optimal thresholds and machine learning methods showed superior specificity (75-82%) to conventional thresholds (58-66%) across unilateral and bilateral activities. Conclusion: This work compares the validity of methods classifying stroke survivors' real-life arm activities measured by wrist-worn sensors excluding whole-body movements. The determined optimal thresholds and machine learning classifiers achieved an equivalent accuracy and higher specificity than conventional thresholds. Our open-sourced classifier or optimal thresholds should be used to specify the intensity and duration of arm use.

SUBMITTER: Pohl J

PROVIDER: S-EPMC9554104 | biostudies-literature | 2022

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Classification of functional and non-functional arm use by inertial measurement units in individuals with upper limb impairment after stroke.

Pohl Johannes J Ryser Alain A Veerbeek Janne Marieke JM Verheyden Geert G Vogt Julia Elisabeth JE Luft Andreas Rüdiger AR Awai Easthope Chris C

Frontiers in physiology 20220928

Background: Arm use metrics derived from wrist-mounted movement sensors are widely used to quantify the upper limb performance in real-life conditions of individuals with stroke throughout motor recovery. The calculation of real-world use metrics, such as arm use duration and laterality preferences, relies on accurately identifying functional movements. Hence, classifying upper limb activity into functional and non-functional classes is paramount. Acceleration thresholds are ...[more]

PMID: 36246133

Similar Datasets

Project description:BackgroundQuantifying lower-limb load and asymmetry during team sport match-play may be important for injury prevention and understanding performance. However, current analysis methods of lower-limb symmetry during match-play employ wearable microtechnology that may not be best suited to the task. A popular microtechnology is global positioning systems (GPS), which are torso worn. The torso location, and the summary workload measures calculated by GPS are not suited to the calculation of lower-limb load. Instead, research grade accelerometers placed directly on the lower-limb may provide better load information than GPS. This study proposes a new technique to quantify external mechanical load, and lower-limb asymmetry during on-field team sport play using inertial measurement units.MethodsFour professional rugby league players (Age: 23.4 ± 3.1 years; Height: 1.89 ± 0.05 m; Mass: 107.0 ± 12.9 kg) wore two accelerometers, one attached to each foot by the boot laces, during match simulations. Custom Matlab (R2017b, The Mathworks Inc, Natick, MA) code was used to calculate total time, area under the curve (AUC), and percentage of time (%Time) spent in seven acceleration categories (negative to very high, <0 g to >16 g), as well as minimum and maximum acceleration during match simulations. Lower-limb AUC and %Time asymmetry was calculated using the Symmetry Angle Equation, which does not require normalization to a reference leg.ResultsThe range of accelerations experienced across all participants on the left and right sides were 15.68-17.53 g, and 16.18-17.69 g, respectively. Clinically significant asymmetry in AUC and %Time was observed for all but one participant, and only in negative (<0 g) and very high accelerations (>16 g). Clinically significant AUC differences in very high accelerations ranged from 19.10%-26.71%. Clinically significant %Time differences in negative accelerations ranged from 12.65%-25.14%, and in very high accelerations from 18.59%-25.30%. All participants experienced the most AUC at very low accelerations (2-4 g), and the least AUC at very high accelerations (165.00-194.00 AU vs. 0.32-3.59 AU). The %Time results indicated that all participants spent the majority of match-play (73.82-92.06%) in extremely low (0-2 g) to low (4-6 g) acceleration intensities, and the least %Time in very high accelerations (0.01%-0.05%).DiscussionA wearable located on the footwear to measure lower-limb load and asymmetry is feasible to use during rugby league match-play. The location of the sensor on the boot is suited to minimize injury risk occurring from impact to the sensor. This technique is able to quantify external mechanical load and detect inter limb asymmetries during match-play at the source of impact and loading, and is therefore likely to be better than current torso based methods. The results of this study may assist in preparing athletes for match-play, and in preventing injury.

Project description:BackgroundCerebral palsy (CP) is a physical disability that affects movement and posture. Approximately 17 million people worldwide and 34,000 people in Australia are living with CP. In clinical and kinematic research, goniometers and inclinometers are the most commonly used clinical tools to measure joint angles and positions in children with CP.ObjectiveThis paper presents collaborative research between the School of Electrical Engineering, Computing and Mathematical Sciences at Curtin University and a team of clinicians in a multicenter randomized controlled trial involving children with CP. This study aims to develop a digital solution for mass data collection using inertial measurement units (IMUs) and the application of machine learning (ML) to classify the movement features associated with CP to determine the effectiveness of therapy. The results were calculated without the need to measure Euler, quaternion, and joint measurement calculation, reducing the time required to classify the data.MethodsCustom IMUs were developed to record the usual wrist movements of participants in 2 age groups. The first age group consisted of participants approaching 3 years of age, and the second age group consisted of participants approaching 15 years of age. Both groups consisted of participants with and without CP. The IMU data were used to calculate the joint angle of the wrist movement and determine the range of motion. A total of 9 different ML algorithms were used to classify the movement features associated with CP. This classification can also confirm if the current treatment (in this case, the use of wrist extension) is effective.ResultsUpon completion of the project, the wrist joint angle was successfully calculated and validated against Vicon motion capture. In addition, the CP movement was classified as a feature using ML on raw IMU data. The Random Forrest algorithm achieved the highest accuracy of 87.75% for the age range approaching 15 years, and C4.5 decision tree achieved the highest accuracy of 89.39% for the age range approaching 3 years.ConclusionsAnecdotal feedback from Minimising Impairment Trial researchers was positive about the potential for IMUs to contribute accurate data about active range of motion, especially in children, for whom goniometric methods are challenging. There may also be potential to use IMUs for continued monitoring of hand movements throughout the day.Trial registrationAustralian New Zealand Clinical Trials Registry (ANZCTR) ACTRN12614001276640, https://www.anzctr.org.au/Trial/Registration/TrialReview.aspx?id=367398; ANZCTR ACTRN12614001275651, https://www.anzctr.org.au/Trial/Registration/TrialReview.aspx?id=367422.

Dataset Information

Classification of functional and non-functional arm use by inertial measurement units in individuals with upper limb impairment after stroke.

Publications

Classification of functional and non-functional arm use by inertial measurement units in individuals with upper limb impairment after stroke.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets