Using Machine Learning Algorithms for Identifying Gait Parameters Suitable to Evaluate Subtle Changes in Gait in People with Multiple Sclerosis
In multiple sclerosis (MS), gait impairment is one of the most prominent symptoms. For a sensitive assessment of pathological gait patterns, a comprehensive analysis and processing of several gait analysis systems is necessary. The objective of this work was to determine the best diagnostic gait sys...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-08-01
|
| Series: | Brain Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3425/11/8/1049 |
| _version_ | 1827685727625805824 |
|---|---|
| author | Katrin Trentzsch Paula Schumann Grzegorz Śliwiński Paul Bartscht Rocco Haase Dirk Schriefer Andreas Zink Andreas Heinke Thurid Jochim Hagen Malberg Tjalf Ziemssen |
| author_facet | Katrin Trentzsch Paula Schumann Grzegorz Śliwiński Paul Bartscht Rocco Haase Dirk Schriefer Andreas Zink Andreas Heinke Thurid Jochim Hagen Malberg Tjalf Ziemssen |
| author_sort | Katrin Trentzsch |
| collection | DOAJ |
| description | In multiple sclerosis (MS), gait impairment is one of the most prominent symptoms. For a sensitive assessment of pathological gait patterns, a comprehensive analysis and processing of several gait analysis systems is necessary. The objective of this work was to determine the best diagnostic gait system (DIERS pedogait, GAITRite system, and Mobility Lab) using six machine learning algorithms for the differentiation between people with multiple sclerosis (pwMS) and healthy controls, between pwMS with and without fatigue and between pwMS with mild and moderate impairment. The data of the three gait systems were assessed on 54 pwMS and 38 healthy controls. Gaussian Naive Bayes, Decision Tree, k-Nearest Neighbor, and Support Vector Machines (SVM) with linear, radial basis function (rbf) and polynomial kernel were applied for the detection of subtle walking changes. The best performance for a healthy-sick classification was achieved on the DIERS data with a SVM rbf kernel (κ = 0.49 ± 0.11). For differentiating between pwMS with mild and moderate disability, the GAITRite data with the SVM linear kernel (κ = 0.61 ± 0.06) showed the best performance. This study demonstrates that machine learning methods are suitable for identifying pathologic gait patterns in early MS. |
| first_indexed | 2024-03-10T08:58:35Z |
| format | Article |
| id | doaj.art-8eb56387f0e941a5bfbdde35368f8db9 |
| institution | Directory Open Access Journal |
| issn | 2076-3425 |
| language | English |
| last_indexed | 2024-03-10T08:58:35Z |
| publishDate | 2021-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Brain Sciences |
| spelling | doaj.art-8eb56387f0e941a5bfbdde35368f8db92023-11-22T06:59:22ZengMDPI AGBrain Sciences2076-34252021-08-01118104910.3390/brainsci11081049Using Machine Learning Algorithms for Identifying Gait Parameters Suitable to Evaluate Subtle Changes in Gait in People with Multiple SclerosisKatrin Trentzsch0Paula Schumann1Grzegorz Śliwiński2Paul Bartscht3Rocco Haase4Dirk Schriefer5Andreas Zink6Andreas Heinke7Thurid Jochim8Hagen Malberg9Tjalf Ziemssen10Center of Clinical Neuroscience, Neurological Clinic, University Hospital Carl Gustav Carus, TU Dresden, Fetscherstr. 74, 01307 Dresden, GermanyInstitute of Biomedical Engineering, TU Dresden, Fetscherstr. 29, 01307 Dresden, GermanyInstitute of Biomedical Engineering, TU Dresden, Fetscherstr. 29, 01307 Dresden, GermanyCenter of Clinical Neuroscience, Neurological Clinic, University Hospital Carl Gustav Carus, TU Dresden, Fetscherstr. 74, 01307 Dresden, GermanyCenter of Clinical Neuroscience, Neurological Clinic, University Hospital Carl Gustav Carus, TU Dresden, Fetscherstr. 74, 01307 Dresden, GermanyCenter of Clinical Neuroscience, Neurological Clinic, University Hospital Carl Gustav Carus, TU Dresden, Fetscherstr. 74, 01307 Dresden, GermanyCenter of Clinical Neuroscience, Neurological Clinic, University Hospital Carl Gustav Carus, TU Dresden, Fetscherstr. 74, 01307 Dresden, GermanyInstitute of Biomedical Engineering, TU Dresden, Fetscherstr. 29, 01307 Dresden, GermanyInstitute of Biomedical Engineering, TU Dresden, Fetscherstr. 29, 01307 Dresden, GermanyInstitute of Biomedical Engineering, TU Dresden, Fetscherstr. 29, 01307 Dresden, GermanyCenter of Clinical Neuroscience, Neurological Clinic, University Hospital Carl Gustav Carus, TU Dresden, Fetscherstr. 74, 01307 Dresden, GermanyIn multiple sclerosis (MS), gait impairment is one of the most prominent symptoms. For a sensitive assessment of pathological gait patterns, a comprehensive analysis and processing of several gait analysis systems is necessary. The objective of this work was to determine the best diagnostic gait system (DIERS pedogait, GAITRite system, and Mobility Lab) using six machine learning algorithms for the differentiation between people with multiple sclerosis (pwMS) and healthy controls, between pwMS with and without fatigue and between pwMS with mild and moderate impairment. The data of the three gait systems were assessed on 54 pwMS and 38 healthy controls. Gaussian Naive Bayes, Decision Tree, k-Nearest Neighbor, and Support Vector Machines (SVM) with linear, radial basis function (rbf) and polynomial kernel were applied for the detection of subtle walking changes. The best performance for a healthy-sick classification was achieved on the DIERS data with a SVM rbf kernel (κ = 0.49 ± 0.11). For differentiating between pwMS with mild and moderate disability, the GAITRite data with the SVM linear kernel (κ = 0.61 ± 0.06) showed the best performance. This study demonstrates that machine learning methods are suitable for identifying pathologic gait patterns in early MS.https://www.mdpi.com/2076-3425/11/8/1049multiple sclerosisgait analysismobilitymachine learningfeature selection |
| spellingShingle | Katrin Trentzsch Paula Schumann Grzegorz Śliwiński Paul Bartscht Rocco Haase Dirk Schriefer Andreas Zink Andreas Heinke Thurid Jochim Hagen Malberg Tjalf Ziemssen Using Machine Learning Algorithms for Identifying Gait Parameters Suitable to Evaluate Subtle Changes in Gait in People with Multiple Sclerosis Brain Sciences multiple sclerosis gait analysis mobility machine learning feature selection |
| title | Using Machine Learning Algorithms for Identifying Gait Parameters Suitable to Evaluate Subtle Changes in Gait in People with Multiple Sclerosis |
| title_full | Using Machine Learning Algorithms for Identifying Gait Parameters Suitable to Evaluate Subtle Changes in Gait in People with Multiple Sclerosis |
| title_fullStr | Using Machine Learning Algorithms for Identifying Gait Parameters Suitable to Evaluate Subtle Changes in Gait in People with Multiple Sclerosis |
| title_full_unstemmed | Using Machine Learning Algorithms for Identifying Gait Parameters Suitable to Evaluate Subtle Changes in Gait in People with Multiple Sclerosis |
| title_short | Using Machine Learning Algorithms for Identifying Gait Parameters Suitable to Evaluate Subtle Changes in Gait in People with Multiple Sclerosis |
| title_sort | using machine learning algorithms for identifying gait parameters suitable to evaluate subtle changes in gait in people with multiple sclerosis |
| topic | multiple sclerosis gait analysis mobility machine learning feature selection |
| url | https://www.mdpi.com/2076-3425/11/8/1049 |
| work_keys_str_mv | AT katrintrentzsch usingmachinelearningalgorithmsforidentifyinggaitparameterssuitabletoevaluatesubtlechangesingaitinpeoplewithmultiplesclerosis AT paulaschumann usingmachinelearningalgorithmsforidentifyinggaitparameterssuitabletoevaluatesubtlechangesingaitinpeoplewithmultiplesclerosis AT grzegorzsliwinski usingmachinelearningalgorithmsforidentifyinggaitparameterssuitabletoevaluatesubtlechangesingaitinpeoplewithmultiplesclerosis AT paulbartscht usingmachinelearningalgorithmsforidentifyinggaitparameterssuitabletoevaluatesubtlechangesingaitinpeoplewithmultiplesclerosis AT roccohaase usingmachinelearningalgorithmsforidentifyinggaitparameterssuitabletoevaluatesubtlechangesingaitinpeoplewithmultiplesclerosis AT dirkschriefer usingmachinelearningalgorithmsforidentifyinggaitparameterssuitabletoevaluatesubtlechangesingaitinpeoplewithmultiplesclerosis AT andreaszink usingmachinelearningalgorithmsforidentifyinggaitparameterssuitabletoevaluatesubtlechangesingaitinpeoplewithmultiplesclerosis AT andreasheinke usingmachinelearningalgorithmsforidentifyinggaitparameterssuitabletoevaluatesubtlechangesingaitinpeoplewithmultiplesclerosis AT thuridjochim usingmachinelearningalgorithmsforidentifyinggaitparameterssuitabletoevaluatesubtlechangesingaitinpeoplewithmultiplesclerosis AT hagenmalberg usingmachinelearningalgorithmsforidentifyinggaitparameterssuitabletoevaluatesubtlechangesingaitinpeoplewithmultiplesclerosis AT tjalfziemssen usingmachinelearningalgorithmsforidentifyinggaitparameterssuitabletoevaluatesubtlechangesingaitinpeoplewithmultiplesclerosis |