AUTHOR=Pohl Johannes , Ryser Alain , Veerbeek Janne Marieke , Verheyden Geert , Vogt Julia Elisabeth , Luft Andreas Rüdiger , Awai Easthope Chris 

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

JOURNAL=Frontiers in Physiology

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/physiology/articles/10.3389/fphys.2022.952757

DOI=10.3389/fphys.2022.952757

ISSN=1664-042X

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. Calculation of real-world use metrics, such as arm use duration and laterality preferences, rely 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 with a conventional thresholds and an optimal threshold methods.
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 and sequenced into 1-seconds epochs. Actigraph counts were computed, and an optimal threshold for functional movement was determined by receiver operating characteristic curve (ROC) 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 hours) of fourteen 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. 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 to 82%) to conventional thresholds (58 to 66%) across unilateral and bilateral activities.
Conclusion: This work compares the validity of methods classifying stroke survivors’ real-life functional and non-functional activities measured by wrist-worn sensors. 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.