Detection of unsupervised standardized gait tests from real-world inertial sensor data in Parkinson’s disease

Ullrich M, Mücke A, Küderle A, Roth N, Gladow T, Gaßner H, Marxreiter F, Klucken J, Eskofier B, Kluge F (2021)

Publication Type: Journal article, Original article

Publication year: 2021

Journal

IEEE Transactions on Neural Systems and Rehabilitation Engineering Institute of Electrical and Electronics Engineers (IEEE)

Original Authors: Martin Ullrich, Annika Mucke, Arne Kuderle, Nils Roth, Till Gladow, Heiko Gassner, Franz Marxreiter, Jochen Klucken, Bjoern M. Eskofier, Felix Kluge

Pages Range: 2103-2111

Journal Issue: 29

URI: https://ieeexplore.ieee.org/abstract/document/9567680

DOI: 10.1109/TNSRE.2021.3119390

Abstract

Gait tests as part of home monitoring study protocols for patients with movement disorders may provide valuable standardized anchor-points for real-world gait analysis using inertial measurement units (IMUs). However, analyzing unsupervised gait tests relies on reliable test annotations by the patients requiring a potentially error-prone interaction with the recording system. To overcome this limitation, this work presents a novel algorithmic pipeline for the automated detection of unsupervised standardized gait tests from continuous real-world IMU data. In a study with twelve Parkinson’s disease patients, we recorded real-world gait data over two weeks using foot-worn IMUs. During continuous daily recordings, the participants performed series of three consecutive 4x10-Meters-Walking-Tests (4x10MWTs) at different walking speeds, besides their usual daily-living activities. The algorithm first detected these gait test series using a gait sequence detection algorithm, a peak enhancement pipeline, and subsequence Dynamic Time Warping and then decomposed them into single 4x10MWTs based on the walking speed. In the evaluation with 419 available gait test series, the detection reached an F1-score of 88.9% and the decomposition an F1-score of 94.0%. A concurrent validity evaluation revealed very good agreement between spatio-temporal gait parameters derived from manually labelled and automatically detected 4x10MWTs. Our algorithm allows to remove the burden of system interaction from the patients and reduces the time for manual data annotation for researchers. The study contributes to an improved automated processing of real-world IMU gait data and enables a simple integration of standardized tests into continuous long-term recordings. This will help to bridge the gap between supervised and unsupervised gait assessment.

Authors with CRIS profile

Martin Ullrich Machine Learning and Data Analytics Lab Arne Küderle Machine Learning and Data Analytics Lab Nils Roth Machine Learning and Data Analytics Lab Heiko Gaßner Department of Molecular Neurology Franz Marxreiter Department of Molecular Neurology Björn Eskofier Machine Learning and Data Analytics Lab Felix Kluge Machine Learning and Data Analytics Lab

Additional Organisation(s)

Lehrstuhl für Hochfrequenztechnik Sonderforschungsbereich 1483/1 Empathokinästhetische Sensorik – Sensortechniken und Datenanalyseverfahren zur empathokinästhetischen Modellbildung und Zustandsbestimmung

Related research project(s)

Empatho-Kinaesthetic Sensor Technology (SFB 1483 EmpkinS) July 1, 2021 - June 30, 2025 Sensorbasierte Bewegungs- und Schlafanalyse beim Parkinson-Syndrom (SFB 1483 EmpkinS D04) Empatho-Kinaesthetic Sensor Technology (SFB 1483 EmpkinS) July 1, 2021 - June 30, 2025

Involved external institutions

Medical Valley - Europäische Metropolregion Nürnberg DE Germany (DE) University of Luxembourg LU Luxembourg (LU)

How to cite

APA:

Ullrich, M., Mücke, A., Küderle, A., Roth, N., Gladow, T., Gaßner, H.,... Kluge, F. (2021). Detection of unsupervised standardized gait tests from real-world inertial sensor data in Parkinson’s disease. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 29, 2103-2111. https://dx.doi.org/10.1109/TNSRE.2021.3119390

MLA:

Ullrich, Martin, et al. "Detection of unsupervised standardized gait tests from real-world inertial sensor data in Parkinson’s disease." IEEE Transactions on Neural Systems and Rehabilitation Engineering 29 (2021): 2103-2111.

BibTeX: Download