Search

Introduction Objective monitoring of movement in Parkinson’s Disease (PD) is important to assess response to treatment. Currently, PD treatment decisions are made based on expert assessment and conduct of clinical rating scales and patient diaries. Each of these is insensitive, episodic and subjective with inherent rater bias. Wearable inertial sensor technology using accelerometers and gyroscopes, which can quantify gait metrics, have been studied for their ability to monitor PD signs. We sought to evaluate the performance of wearable inertial sensor technology in quantifying movement related to PD signs using the Mobility Lab system ( http://www.apdm.com ). Methods We compared endpoints of the Mobility Lab 2-min walk test in 41 healthy volunteers (HV) and in 25 PD patients. HV had two test sessions at greater than a one hour interval. Each PD patient also performed the task twice: once in ON state ( ∼ 1 h after administering the patient’s scheduled levodopa dose) and again in the OFF state (immediately prior to administering the patient’s next scheduled levodopa dose). PD patients were randomized with half performing on state evaluations prior to off state evaluations, and the other half reversing this order. Each subject walked 10 meter linear laps with a 180 degree turn at the apex for two minutes while wearing sensors on each limb, and the sternum and lumbar regions. Results We found the highest reliability of the following endpoints in HV: cadence (Pearson’s r = 0.9860), stride length (r = 0.963), and arm range of motion (r = 0.962). In PD patients, Mobility Lab endpoints including turn duration ( p = 0.003), gait speed (p = 0.009), stride length (p = 0.006) and arm range of motion (p = 0.02) significantly differed before and after levodopa intake, and correlated with the Unified Parkinson Disease Rating Scale Motor Score (e.g. turn duration r = 0.4). Conclusion The Mobility Lab System 2-min walk test generated endpoints with good reliability and detected changes in PD patients before and after levodopa. Wearable inertial sensors have the potential to enhance our ability to detect signals of efficacy in therapeutic development.

Introduction Reliably detecting ON/OFF states is important for monitoring PD treatment and progression. Currently, subjective patient diaries capture this information. We investigate if detection of motor signs of ON/OFF states can be achieved by using kinematic measurements from wearable sensor technology combined with a machine learning (ML) pipeline. Methods Twenty-five PD subjects (19 males, 69 ± 7 years) taking levodopa performed 10-m Instrumented Stand and Walk (ISAW) tests in their ON and OFF states while wearing Ambulatory Parkinson Disease Monitoring (APDM) sensors on their sternum, wrists, lumbar and lower extremities. A neurologist scored each ISAW according to the MDS-UPDRS-III. We analyzed 98 kinematic features for significance to neurologist total motor score and ON/OFF using both statistical (repeated-measures ANOVA, step-wise mixed-model regression, likelihood-ratio test, ridge regression) and ML methods. Results Twenty-two features significantly differed between patient reported ON/OFF states, with the most significant being trunk transverse range-of-motion (RofM), arm RofM, mid-swing elevation, stride length, turn velocity, steps in turn and toe out angles. Estimates from regression model showed average difference of 14 points between OFF/ON states in total UPDRS score and 9 points when adjusted for 5 significant features for individual baseline (mean trunk transverse RofM, right arm RofM, and toe out angle having highest effect; coeff. −8.67, −5.25, −3.36 respectively). Several approaches were employed for predicting ON/OFF states based on these features: direct binary classification (acc = 0.56), regression to total UPDRS score (acc = 0.76), regression to PIGD sub-score (acc = 0.64), and classification of ON–OFF/OFF–ON transitions using feature differences (Naive Bayes: acc = 0.74, AUC = 0.78; Random Forest: acc = 0.76, AUC = 0.90). Conclusion Wearable inertial sensors hold promise for detecting ON/OFF states in PD patients using an augmented ML approach. This could be particularly useful for monitoring response to therapy in an outpatient setting.