Objective Monitoring of Motor Symptoms and their Progression in Parkinson’s Disease Using a Digital Gait Sensor#

Authors#

Tamara Raschka, Jackrite To, Tom Hähnel, Stefano Sapienza, Alzhraa Ibrahim, Enrico Glaab, Ralph Steidl, Jürgen Winkler, Jean-Christophe Corvol, Jochen Klucken, Björn Falkenburger, Holger Fröhlich

Abstract#

Background Digital technologies for monitoring motor symptoms of Parkinson’s Disease (PD) have undergone a significant evolution during the past years. Although it has been shown for several devices that derived features can reliably discriminate between healthy controls and patients with PD, it is still unknown, in how far digital gait devices allow for an objective monitoring of motor symptoms and their progression. Furthermore, the potential benefit as endpoint in a clinical trial context has not been investigated so far. Results In this study we focused on the Portabiles digital gait device, which has been used by almost 900 patients within the LuxPark cohort study (n = 612, Luxembourg) as well as within routine clinical care visits at the University Medical Center Erlangen (n = 264, Erlangen, Germany). Linear (mixed) models were used to assess the association between task-specific digital gait features and disease progression and severity scores derived from dedicated questionaires. Furthermore, we employed machine learning to evaluate whether digital gait assessments were prognostic for patient-level motor symptom progression. Overall, features derived from the Portabiles gait device were found to effectively monitor motor symptoms and their longitudinal progression. At the same time the prognostic performance of digital gait was limited. However, we could show a strong reduction in required sample size, if digitally assessed gait features were employed as endpoints in a clinical trial context. Conclusion The Portabiles digital gait device provides an effective way to objectively monitor motor symptoms and their progression. Furthermore, the digital gait device has significant potential as an alternative and easily assessable endpoint in a clinical trial context.