Gait Analysis with Wearables Can Accurately Classify Fallers from Non-Fallers: A Step toward Better Management of Neurological Disorders
Falls are the leading cause of mortality, morbidity and poor quality of life in older adults with or without neurological conditions. Applying machine learning (ML) models to gait analysis outcomes offers the opportunity to identify individuals at risk of future falls. The aim of this study was to d...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-12-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/20/23/6992 |
_version_ | 1797545496619778048 |
---|---|
author | Rana Zia Ur Rehman Yuhan Zhou Silvia Del Din Lisa Alcock Clint Hansen Yu Guan Tibor Hortobágyi Walter Maetzler Lynn Rochester Claudine J. C. Lamoth |
author_facet | Rana Zia Ur Rehman Yuhan Zhou Silvia Del Din Lisa Alcock Clint Hansen Yu Guan Tibor Hortobágyi Walter Maetzler Lynn Rochester Claudine J. C. Lamoth |
author_sort | Rana Zia Ur Rehman |
collection | DOAJ |
description | Falls are the leading cause of mortality, morbidity and poor quality of life in older adults with or without neurological conditions. Applying machine learning (ML) models to gait analysis outcomes offers the opportunity to identify individuals at risk of future falls. The aim of this study was to determine the effect of different data pre-processing methods on the performance of ML models to classify neurological patients who have fallen from those who have not for future fall risk assessment. Gait was assessed using wearables in clinic while walking 20 m at a self-selected comfortable pace in 349 (159 fallers, 190 non-fallers) neurological patients. Six different ML models were trained on data pre-processed with three techniques such as standardisation, principal component analysis (PCA) and path signature method. Fallers walked more slowly, with shorter strides and longer stride duration compared to non-fallers. Overall, model accuracy ranged between 48% and 98% with 43–99% sensitivity and 48–98% specificity. A random forest (RF) classifier trained on data pre-processed with the path signature method gave optimal classification accuracy of 98% with 99% sensitivity and 98% specificity. Data pre-processing directly influences the accuracy of ML models for the accurate classification of fallers. Using gait analysis with trained ML models can act as a tool for the proactive assessment of fall risk and support clinical decision-making. |
first_indexed | 2024-03-10T14:16:16Z |
format | Article |
id | doaj.art-253a28f01c8745ff917a66e8131b0ab2 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-10T14:16:16Z |
publishDate | 2020-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-253a28f01c8745ff917a66e8131b0ab22023-11-20T23:44:48ZengMDPI AGSensors1424-82202020-12-012023699210.3390/s20236992Gait Analysis with Wearables Can Accurately Classify Fallers from Non-Fallers: A Step toward Better Management of Neurological DisordersRana Zia Ur Rehman0Yuhan Zhou1Silvia Del Din2Lisa Alcock3Clint Hansen4Yu Guan5Tibor Hortobágyi6Walter Maetzler7Lynn Rochester8Claudine J. C. Lamoth9Translational and Clinical Research Institute, Faculty of Medical Sciences, Newcastle University, Newcastle Upon Tyne NE4 5PL, UKDepartment of Human Movement Sciences, University Medical Center Groningen, University of Groningen, 9713 AV Groningen, The NetherlandsTranslational and Clinical Research Institute, Faculty of Medical Sciences, Newcastle University, Newcastle Upon Tyne NE4 5PL, UKTranslational and Clinical Research Institute, Faculty of Medical Sciences, Newcastle University, Newcastle Upon Tyne NE4 5PL, UKDepartment of Neurology, University Hospital Schleswig-Holstein, Campus Kiel, 24105 Kiel, GermanySchool of Computing, Newcastle University, Newcastle Upon Tyne NE4 5TG, UKDepartment of Human Movement Sciences, University Medical Center Groningen, University of Groningen, 9713 AV Groningen, The NetherlandsDepartment of Neurology, University Hospital Schleswig-Holstein, Campus Kiel, 24105 Kiel, GermanyTranslational and Clinical Research Institute, Faculty of Medical Sciences, Newcastle University, Newcastle Upon Tyne NE4 5PL, UKDepartment of Human Movement Sciences, University Medical Center Groningen, University of Groningen, 9713 AV Groningen, The NetherlandsFalls are the leading cause of mortality, morbidity and poor quality of life in older adults with or without neurological conditions. Applying machine learning (ML) models to gait analysis outcomes offers the opportunity to identify individuals at risk of future falls. The aim of this study was to determine the effect of different data pre-processing methods on the performance of ML models to classify neurological patients who have fallen from those who have not for future fall risk assessment. Gait was assessed using wearables in clinic while walking 20 m at a self-selected comfortable pace in 349 (159 fallers, 190 non-fallers) neurological patients. Six different ML models were trained on data pre-processed with three techniques such as standardisation, principal component analysis (PCA) and path signature method. Fallers walked more slowly, with shorter strides and longer stride duration compared to non-fallers. Overall, model accuracy ranged between 48% and 98% with 43–99% sensitivity and 48–98% specificity. A random forest (RF) classifier trained on data pre-processed with the path signature method gave optimal classification accuracy of 98% with 99% sensitivity and 98% specificity. Data pre-processing directly influences the accuracy of ML models for the accurate classification of fallers. Using gait analysis with trained ML models can act as a tool for the proactive assessment of fall risk and support clinical decision-making.https://www.mdpi.com/1424-8220/20/23/6992neurological disordersmachine learningclassificationfallpath signaturegait |
spellingShingle | Rana Zia Ur Rehman Yuhan Zhou Silvia Del Din Lisa Alcock Clint Hansen Yu Guan Tibor Hortobágyi Walter Maetzler Lynn Rochester Claudine J. C. Lamoth Gait Analysis with Wearables Can Accurately Classify Fallers from Non-Fallers: A Step toward Better Management of Neurological Disorders Sensors neurological disorders machine learning classification fall path signature gait |
title | Gait Analysis with Wearables Can Accurately Classify Fallers from Non-Fallers: A Step toward Better Management of Neurological Disorders |
title_full | Gait Analysis with Wearables Can Accurately Classify Fallers from Non-Fallers: A Step toward Better Management of Neurological Disorders |
title_fullStr | Gait Analysis with Wearables Can Accurately Classify Fallers from Non-Fallers: A Step toward Better Management of Neurological Disorders |
title_full_unstemmed | Gait Analysis with Wearables Can Accurately Classify Fallers from Non-Fallers: A Step toward Better Management of Neurological Disorders |
title_short | Gait Analysis with Wearables Can Accurately Classify Fallers from Non-Fallers: A Step toward Better Management of Neurological Disorders |
title_sort | gait analysis with wearables can accurately classify fallers from non fallers a step toward better management of neurological disorders |
topic | neurological disorders machine learning classification fall path signature gait |
url | https://www.mdpi.com/1424-8220/20/23/6992 |
work_keys_str_mv | AT ranaziaurrehman gaitanalysiswithwearablescanaccuratelyclassifyfallersfromnonfallersasteptowardbettermanagementofneurologicaldisorders AT yuhanzhou gaitanalysiswithwearablescanaccuratelyclassifyfallersfromnonfallersasteptowardbettermanagementofneurologicaldisorders AT silviadeldin gaitanalysiswithwearablescanaccuratelyclassifyfallersfromnonfallersasteptowardbettermanagementofneurologicaldisorders AT lisaalcock gaitanalysiswithwearablescanaccuratelyclassifyfallersfromnonfallersasteptowardbettermanagementofneurologicaldisorders AT clinthansen gaitanalysiswithwearablescanaccuratelyclassifyfallersfromnonfallersasteptowardbettermanagementofneurologicaldisorders AT yuguan gaitanalysiswithwearablescanaccuratelyclassifyfallersfromnonfallersasteptowardbettermanagementofneurologicaldisorders AT tiborhortobagyi gaitanalysiswithwearablescanaccuratelyclassifyfallersfromnonfallersasteptowardbettermanagementofneurologicaldisorders AT waltermaetzler gaitanalysiswithwearablescanaccuratelyclassifyfallersfromnonfallersasteptowardbettermanagementofneurologicaldisorders AT lynnrochester gaitanalysiswithwearablescanaccuratelyclassifyfallersfromnonfallersasteptowardbettermanagementofneurologicaldisorders AT claudinejclamoth gaitanalysiswithwearablescanaccuratelyclassifyfallersfromnonfallersasteptowardbettermanagementofneurologicaldisorders |