Assessing Upper Limb Motor Function in the Immediate Post-Stroke Perioud Using Accelerometry. (arXiv:2311.04226v1 [cs.LG])

Accelerometry has been extensively studied as an objective means of measuring
upper limb function in patients post-stroke. The objective of this paper is to
determine whether the accelerometry-derived measurements frequently used in
more long-term rehabilitation studies can also be used to monitor and rapidly
detect sudden changes in upper limb motor function in more recently
hospitalized stroke patients. Six binary classification models were created by
training on variable data window times of paretic upper limb accelerometer
feature data. The models were assessed on their effectiveness for
differentiating new input data into two classes: severe or moderately severe
motor function. The classification models yielded Area Under the Curve (AUC)
scores that ranged from 0.72 to 0.82 for 15-minute data windows to 0.77 to 0.94
for 120-minute data windows. These results served as a preliminary assessment
and a basis on which to further investigate the efficacy of using accelerometry
and machine learning to alert healthcare professionals to rapid changes in
motor function in the days immediately following a stroke.