Turning Analysis during Standardized Test Using On-Shoe Wearable Sensors in Parkinson’s Disease
Nooshin Haji Ghassemi,
Julius Hannink,
Nils Roth,
Heiko Gaßner,
Franz Marxreiter,
Jochen Klucken,
Björn M. Eskofier
Affiliations
Nooshin Haji Ghassemi
Machine Learning and Data Analytics Lab, Department of Computer Science, Friedrich-Alexander-University Erlangen-Nürnberg (FAU), Carl-Thiersch-Strasse 2b, D-91052 Erlangen, Germany
Julius Hannink
Machine Learning and Data Analytics Lab, Department of Computer Science, Friedrich-Alexander-University Erlangen-Nürnberg (FAU), Carl-Thiersch-Strasse 2b, D-91052 Erlangen, Germany
Nils Roth
Machine Learning and Data Analytics Lab, Department of Computer Science, Friedrich-Alexander-University Erlangen-Nürnberg (FAU), Carl-Thiersch-Strasse 2b, D-91052 Erlangen, Germany
Heiko Gaßner
Department of Molecular Neurology, University Hospital Erlangen, Schwabachanlage 6, D-91054 Erlangen, Germany
Franz Marxreiter
Department of Molecular Neurology, University Hospital Erlangen, Schwabachanlage 6, D-91054 Erlangen, Germany
Jochen Klucken
Department of Molecular Neurology, University Hospital Erlangen, Schwabachanlage 6, D-91054 Erlangen, Germany
Björn M. Eskofier
Machine Learning and Data Analytics Lab, Department of Computer Science, Friedrich-Alexander-University Erlangen-Nürnberg (FAU), Carl-Thiersch-Strasse 2b, D-91052 Erlangen, Germany
Mobile gait analysis systems using wearable sensors have the potential to analyze and monitor pathological gait in a finer scale than ever before. A closer look at gait in Parkinson’s disease (PD) reveals that turning has its own characteristics and requires its own analysis. The goal of this paper is to present a system with on-shoe wearable sensors in order to analyze the abnormalities of turning in a standardized gait test for PD. We investigated turning abnormalities in a large cohort of 108 PD patients and 42 age-matched controls. We quantified turning through several spatio-temporal parameters. Analysis of turn-derived parameters revealed differences of turn-related gait impairment in relation to different disease stages and motor impairment. Our findings confirm and extend the results from previous studies and show the applicability of our system in turning analysis. Our system can provide insight into the turning in PD and be used as a complement for physicians’ gait assessment and to monitor patients in their daily environment.