The purposes of the study were (1) to compare postural sway between participants with Parkinson’s disease (PD) and healthy controls and (2) to develop and validate an automated classification of PD postural control patterns using a machine learning approach. A total of 9 participants in the early stage of PD and 12 healthy controls were recruited. Participants were instructed to stand on a force plate and maintain stillness for 2 minutes with eyes open and eyes closed. The center of pressure data were collected at 50 Hz. Linear displacements, standard deviations, total distances, sway areas, and multiscale entropy of center of pressure were calculated and compared using mixed-model analysis of variance. Five supervised machine learning algorithms (ie, logistic regression, K-nearest neighbors, Naïve Bayes, decision trees, and random forest) were used to classify PD postural control patterns. Participants with PD exhibited greater center of pressure sway and variability compared with controls. The K-nearest neighbor method exhibited the best prediction performance with an accuracy rate of up to 0.86. In conclusion, participants with PD exhibited impaired postural stability and their postural sway features could be identified by machine learning algorithms.
Yumeng Li, Shuqi Zhang, and Christina Odeh
Allison H. Gruber, Shuqi Zhang, Jiahao Pan, and Li Li
The running footwear literature reports a conceptual disconnect between shoe cushioning and external impact loading: footwear or surfaces with greater cushioning tend to result in greater impact force characteristics during running. Increased impact loading with maximalist footwear may reflect an altered lower-extremity gait strategy to adjust for running in compliant footwear. The authors hypothesized that ankle and knee joint stiffness would change to maintain the effective vertical stiffness, as cushioning changed with minimalist, traditional, and maximalist footwear. Eleven participants ran on an instrumental treadmill (3.5 m·s−1) for a 5-minute familiarization in each footwear, plus an additional 110 seconds before data collection. Vertical, leg, ankle, and knee joint stiffness and vertical impact force characteristics were calculated. Mixed model with repeated measures tested differences between footwear conditions. Compared with traditional and maximalist, the minimalist shoes were associated with greater average instantaneous and average vertical loading rates (P < .050), greater vertical stiffness (P ≤ .010), and less change in leg length between initial contact and peak resultant ground reaction force (P < .050). No other differences in stiffness or impact variables were observed. The shoe cushioning paradox did not hold in this study due to a similar musculoskeletal strategy for running in traditional and maximalist footwear and running with a more rigid limb in minimalist footwear.