Medication and trial duration influence postural and pointing parameters during a standing repetitive pointing task in individuals with Parkinson's disease

Classification of Parkinson's disease with freezing of gait based on 360° turning analysis using 36 kinematic features

BACKGROUND

Freezing of gait (FOG) is a sensitive problem, which is caused by motor control deficits and requires greater attention during postural transitions such as turning in people with Parkinson's disease (PD). However, the turning characteristics have not yet been extensively investigated to distinguish between people with PD with and without FOG (freezers and non-freezers) based on full-body kinematic analysis during the turning task. The objectives of this study were to identify the machine learning model that best classifies people with PD and freezers and reveal the associations between clinical characteristics and turning features based on feature selection through stepwise regression.

METHODS

The study recruited 77 people with PD (31 freezers and 46 non-freezers) and 34 age-matched older adults. The 360° turning task was performed at the preferred speed for the inner step of the more affected limb. All experiments on the people with PD were performed in the "Off" state of medication. The full-body kinematic features during the turning task were extracted using the three-dimensional motion capture system. These features were selected via stepwise regression.

RESULTS

In feature selection through stepwise regression, five and six features were identified to distinguish between people with PD and controls and between freezers and non-freezers (PD and FOG classification problem), respectively. The machine learning model accuracies revealed that the random forest (RF) model had 98.1% accuracy when using all turning features and 98.0% accuracy when using the five features selected for PD classification. In addition, RF and logistic regression showed accuracies of 79.4% when using all turning features and 72.9% when using the six selected features for FOG classification.

CONCLUSION

We suggest that our study leads to understanding of the turning characteristics of people with PD and freezers during the 360° turning task for the inner step of the more affected limb and may help improve the objective classification and clinical assessment by disease progression using turning features.

Prolonged Standing Task Affects Adaptability of Postural Control in People With Parkinson's Disease

BACKGROUND

Studies on short-term upright quiet standing tasks have presented contradictory findings about postural control in people with Parkinson's disease (pwPD). Prolonged trial durations might better depict body sway and discriminate pwPD and controls.

OBJECTIVE

The aim of this study was to investigate postural control in pwPD during a prolonged standing task.

METHODS

A total of 26 pwPD and 25 neurologically healthy individuals performed 3 quiet standing trials (60 s) before completing a constrained prolonged standing task for 15 minutes. Motion capture was used to record body sway (Vicon, 100 Hz). To investigate the body sway behavior during the 15 minutes of standing, the analysis was divided into three 5-minute-long phases: early, middle, and late. The following body sway parameters were calculated for the anterior-posterior (AP) and medial-lateral (ML) directions: velocity, root-mean-square, and detrended fluctuations analysis (DFA). The body sway area was also calculated. Two-way ANOVAs (group and phases) and 1-way ANOVA (group) were used to compare these parameters for the prolonged standing and quiet standing, respectively.

RESULTS

pwPD presented smaller sway area (P < .001), less complexity (DFA; AP: P < .009; ML: P < .01), and faster velocity (AP: P < .002; ML: P < .001) of body sway compared with the control group during the prolonged standing task. Although the groups swayed similarly (no difference for sway area) during quiet standing, they presented differences in sway area during the prolonged standing task (P < .001).

CONCLUSIONS

Prolonged standing task reduced adaptability of the postural control system in pwPD. In addition, the prolonged standing task may better analyze the adaptability of the postural control system in pwPD.

Assessing Postural Stability Using Coupling Strengths between Center of Pressure and Its Ground Reaction Force Components

The center of pressure (COP), which is defined as the point at which the resultant ground reaction force (GRF) is applied on a body, provides valuable information for postural stability assessment. This is because the fundamental goal of balance control is to regulate the center of mass (COM) of the human body by adaptively changing the position of the COP. By using Newtonian mechanics to develop two equations that relate the two-dimensional COP coordinates to the GRF components, one can easily determine the location of the COP using a force plate. An important property of these two equations is that for a given COP position, there exists an infinite number of GRF component combinations that can satisfy these two equations. However, the manner in which a postural control system deals with such redundancy is still unclear. To address this redundancy problem, we introduce four postural stability features by quantifying the coupling strengths between the COP coordinates and their GRF components. Experiments involving younger (18–24 years old) and older (65–73 years) participants were conducted. The efficacy of the proposed features was demonstrated by comparing the differences between variants of each feature for each age group (18–24 and 65–73 years). The results demonstrated that the coupling strengths between the anterior–posterior (AP) direction coordinate of the COP and its GRF components for the older group were significantly higher than those of the younger group. These experimental results suggest that (1) the balance control system of the older group is more constrained than that of the younger group in coordinating the GRF components and (2) the proposed features are more sensitive to age variations than one of the most reliable and accurate conventional COP features. The best testing classification accuracy achieved by the proposed features was 0.883, whereas the testing classification accuracy achieved by the most accurate conventional COP feature was 0.777. Finally, by investigating the interactions between the COP and its GRF components using the proposed features, we found that that the AP component of the GRF of younger people plays a more active role in balance control than that of the GRF of older people. Based on these findings, it is believed that the proposed features can be used as a set of stability measures to assess the effects on posture stability from various health-related conditions such as aging and fall risk.