On-Demand Gait-Synchronous Electrical Cueing in Parkinson's Disease Using Machine Learning and Edge Computing: A Pilot Study
<italic>Goal:</italic> Parkinson's disease (PD) can lead to gait impairment and Freezing of Gait (FoG). Recent advances in cueing technologies have enhanced mobility in PD patients. While sensor technology and machine learning offer real-time detection for on-demand cueing, ex...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Open Journal of Engineering in Medicine and Biology |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10504963/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832582336796950528 |
|---|---|
| author | Ardit Dvorani Constantin Wiesener Christina Salchow-Hommen Magdalena Jochner Lotta Spieker Matej Skrobot Hanno Voigt Andrea Kuhn Nikolaus Wenger Thomas Schauer |
| author_facet | Ardit Dvorani Constantin Wiesener Christina Salchow-Hommen Magdalena Jochner Lotta Spieker Matej Skrobot Hanno Voigt Andrea Kuhn Nikolaus Wenger Thomas Schauer |
| author_sort | Ardit Dvorani |
| collection | DOAJ |
| description | <italic>Goal:</italic> Parkinson's disease (PD) can lead to gait impairment and Freezing of Gait (FoG). Recent advances in cueing technologies have enhanced mobility in PD patients. While sensor technology and machine learning offer real-time detection for on-demand cueing, existing systems are limited by the usage of smartphones between the sensor(s) and cueing device(s) for data processing. By avoiding this we aim at improving usability, robustness, and detection delay. <italic>Methods:</italic> We present a new technical solution, that runs detection and cueing algorithms directly on the sensing and cueing devices, bypassing the smartphone. This solution relies on edge computing on the devices' hardware. The wearable system consists of a single inertial sensor to control a stimulator and enables machine-learning-based FoG detection by classifying foot motion phases as either normal or FoG-affected. We demonstrate the system's functionality and safety during on-demand gait-synchronous electrical cueing in two patients, performing freezing of gait assessments. As references, motion phases and FoG episodes have been video-annotated. <italic>Results:</italic> The analysis confirms adequate gait phase and FoG detection performance. The mobility assistant detected foot motions with a rate above 94 % and classified them with an accuracy of 84 % into normal or FoG-affected. The FoG detection delay is mainly defined by the foot-motion duration, which is below the delay in existing sliding-window approaches. <italic>Conclusions:</italic> Direct computing on the sensor and cueing devices ensures robust detection of FoG-affected motions for on demand cueing synchronized with the gait. The proposed solution can be easily adopted to other sensor and cueing modalities. |
| format | Article |
| id | doaj-art-cce108a80a69495ba4fe80eb520dcff7 |
| institution | Kabale University |
| issn | 2644-1276 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Engineering in Medicine and Biology |
| spelling | doaj-art-cce108a80a69495ba4fe80eb520dcff72025-01-30T00:03:52ZengIEEEIEEE Open Journal of Engineering in Medicine and Biology2644-12762024-01-01530631510.1109/OJEMB.2024.339056210504963On-Demand Gait-Synchronous Electrical Cueing in Parkinson's Disease Using Machine Learning and Edge Computing: A Pilot StudyArdit Dvorani0https://orcid.org/0009-0002-2765-8729Constantin Wiesener1https://orcid.org/0000-0003-0795-2306Christina Salchow-Hommen2https://orcid.org/0000-0001-5527-9895Magdalena Jochner3https://orcid.org/0000-0003-1505-4135Lotta Spieker4https://orcid.org/0009-0000-7750-1469Matej Skrobot5https://orcid.org/0000-0001-6686-1880Hanno Voigt6https://orcid.org/0009-0007-7159-2321Andrea Kuhn7https://orcid.org/0000-0002-4134-9060Nikolaus Wenger8https://orcid.org/0000-0002-0965-7530Thomas Schauer9https://orcid.org/0000-0002-0865-4418Control Systems Group, Technische Universität Berlin, Berlin, GermanySensorStim Neurotechnology GmbH, Berlin, GermanyDepartment for Neurology, Charité – Universitätsmedizin Berlin, Berlin, GermanyDepartment for Neurology, Charité – Universitätsmedizin Berlin, Berlin, GermanyControl Systems Group, Technische Universität Berlin, Berlin, GermanyDepartment for Neurology, Charité – Universitätsmedizin Berlin, Berlin, GermanySensorStim Neurotechnology GmbH, Berlin, GermanyDepartment for Neurology, Charité – Universitätsmedizin Berlin, Berlin, GermanyDepartment for Neurology, Charité – Universitätsmedizin Berlin, Berlin, GermanyControl Systems Group, Technische Universität Berlin, Berlin, Germany<italic>Goal:</italic> Parkinson's disease (PD) can lead to gait impairment and Freezing of Gait (FoG). Recent advances in cueing technologies have enhanced mobility in PD patients. While sensor technology and machine learning offer real-time detection for on-demand cueing, existing systems are limited by the usage of smartphones between the sensor(s) and cueing device(s) for data processing. By avoiding this we aim at improving usability, robustness, and detection delay. <italic>Methods:</italic> We present a new technical solution, that runs detection and cueing algorithms directly on the sensing and cueing devices, bypassing the smartphone. This solution relies on edge computing on the devices' hardware. The wearable system consists of a single inertial sensor to control a stimulator and enables machine-learning-based FoG detection by classifying foot motion phases as either normal or FoG-affected. We demonstrate the system's functionality and safety during on-demand gait-synchronous electrical cueing in two patients, performing freezing of gait assessments. As references, motion phases and FoG episodes have been video-annotated. <italic>Results:</italic> The analysis confirms adequate gait phase and FoG detection performance. The mobility assistant detected foot motions with a rate above 94 % and classified them with an accuracy of 84 % into normal or FoG-affected. The FoG detection delay is mainly defined by the foot-motion duration, which is below the delay in existing sliding-window approaches. <italic>Conclusions:</italic> Direct computing on the sensor and cueing devices ensures robust detection of FoG-affected motions for on demand cueing synchronized with the gait. The proposed solution can be easily adopted to other sensor and cueing modalities.https://ieeexplore.ieee.org/document/10504963/Edge computingfreezing of gaitinertial sensorsmachine learningon-demand cueing |
| spellingShingle | Ardit Dvorani Constantin Wiesener Christina Salchow-Hommen Magdalena Jochner Lotta Spieker Matej Skrobot Hanno Voigt Andrea Kuhn Nikolaus Wenger Thomas Schauer On-Demand Gait-Synchronous Electrical Cueing in Parkinson's Disease Using Machine Learning and Edge Computing: A Pilot Study IEEE Open Journal of Engineering in Medicine and Biology Edge computing freezing of gait inertial sensors machine learning on-demand cueing |
| title | On-Demand Gait-Synchronous Electrical Cueing in Parkinson's Disease Using Machine Learning and Edge Computing: A Pilot Study |
| title_full | On-Demand Gait-Synchronous Electrical Cueing in Parkinson's Disease Using Machine Learning and Edge Computing: A Pilot Study |
| title_fullStr | On-Demand Gait-Synchronous Electrical Cueing in Parkinson's Disease Using Machine Learning and Edge Computing: A Pilot Study |
| title_full_unstemmed | On-Demand Gait-Synchronous Electrical Cueing in Parkinson's Disease Using Machine Learning and Edge Computing: A Pilot Study |
| title_short | On-Demand Gait-Synchronous Electrical Cueing in Parkinson's Disease Using Machine Learning and Edge Computing: A Pilot Study |
| title_sort | on demand gait synchronous electrical cueing in parkinson x0027 s disease using machine learning and edge computing a pilot study |
| topic | Edge computing freezing of gait inertial sensors machine learning on-demand cueing |
| url | https://ieeexplore.ieee.org/document/10504963/ |
| work_keys_str_mv | AT arditdvorani ondemandgaitsynchronouselectricalcueinginparkinsonx0027sdiseaseusingmachinelearningandedgecomputingapilotstudy AT constantinwiesener ondemandgaitsynchronouselectricalcueinginparkinsonx0027sdiseaseusingmachinelearningandedgecomputingapilotstudy AT christinasalchowhommen ondemandgaitsynchronouselectricalcueinginparkinsonx0027sdiseaseusingmachinelearningandedgecomputingapilotstudy AT magdalenajochner ondemandgaitsynchronouselectricalcueinginparkinsonx0027sdiseaseusingmachinelearningandedgecomputingapilotstudy AT lottaspieker ondemandgaitsynchronouselectricalcueinginparkinsonx0027sdiseaseusingmachinelearningandedgecomputingapilotstudy AT matejskrobot ondemandgaitsynchronouselectricalcueinginparkinsonx0027sdiseaseusingmachinelearningandedgecomputingapilotstudy AT hannovoigt ondemandgaitsynchronouselectricalcueinginparkinsonx0027sdiseaseusingmachinelearningandedgecomputingapilotstudy AT andreakuhn ondemandgaitsynchronouselectricalcueinginparkinsonx0027sdiseaseusingmachinelearningandedgecomputingapilotstudy AT nikolauswenger ondemandgaitsynchronouselectricalcueinginparkinsonx0027sdiseaseusingmachinelearningandedgecomputingapilotstudy AT thomasschauer ondemandgaitsynchronouselectricalcueinginparkinsonx0027sdiseaseusingmachinelearningandedgecomputingapilotstudy |