Objective measurement of dyskinesia in Parkinson's disease using a force plate

Abstract

Clinical investigation of levodopa-induced dyskinesia (LID) in Parkinson's disease (PD) is limited because of lack of objective measurements and no consensus on use of a standard measuring tool. Currently, clinical trials use subject-completed diaries of dyskinesia throughout the day or investigator-administered clinical rating scales. An objective and valid method of measuring LID would reduce bias, variability, and decrease the time and number needed in trials of potential anti-dyskinetic agents. We have investigated using a force plate under standing subjects, which records movement of the center of pressure (CoP) to quantify LID over a levodopa (L-dopa) cycle. Twenty-two PD subjects (15 with LID, 7 without LID) admitted to an inpatient research facility had their PD meds withheld overnight, followed by a 2 hours intravenous L-dopa infusion the next day. The root mean squared of the velocity in the anterior-posterior direction (RMSV) derived from an analysis of the CoP, and, the modified Abnormal Involuntary Movement Scale (mAIMS) were performed repeatedly for 6 hours, initially as subjects were OFF before the infusion, through infusion until OFF again. There was a high correlation between the area under the curve (AUC) of the mAIMS and the RMSV within and between subjects. As a measure of LID, RMSV had excellent validity and reliability between subjects, and using a force plate was feasible. Sensitivity to changes in LID was initially demonstrated but should be repeated. Thus, CoP recordings on a force plate can objectively quantify LID in PD and may be very useful in clinical trials or other investigations of dyskinesia.

Figure 1. Group Means (+/- SEM) of the CDRS and RMSV during an ON-OFF cycle

Figure 2. RMSV parallels CDRS in simple or complex LID patterns

Figure 3. Non-PD Control values do not vary (CDRS=0)

Figure 4. PD subjects without LID have low RMSV values (CDRS=0)

Figure 5

The CDRS is a composite score of ratings in 7 body parts, therefore we examined each individual subscore for its performance. The trunk, neck, and most affected arm and leg correlated well, whereas the face produced the worst correlations. This is especially true in the subject with only facial dyskinesia.