scholarly journals Inertial sensors versus standard systems in gait analysis: a systematic review and meta-analysis

2019 ◽  
Vol 55 (2) ◽  
Author(s):  
Federica Petraglia ◽  
Luca Scarcella ◽  
Giuseppe Pedrazzi ◽  
Luigi Brancato ◽  
Robert Puers ◽  
...  
Keyword(s):  
Systematic Review ◽  
Gait Analysis ◽  
Inertial Sensors ◽  
Meta Analysis

A systematic review of gait analysis methods based on inertial sensors and adaptive algorithms

2017 ◽  
Vol 57 ◽  
pp. 204-210 ◽  
Author(s):  
Rafael Caldas ◽  
Marion Mundt ◽  
Wolfgang Potthast ◽  
Fernando Buarque de Lima Neto ◽  
Bernd Markert
Keyword(s):  
Systematic Review ◽  
Gait Analysis ◽  
Inertial Sensors ◽  
Adaptive Algorithms ◽  
Analysis Methods

scholarly journals Supervised Machine Learning for Aiding Diagnosis of Knee Osteoarthritis: A Systematic Review and Meta-Analysis

2020 ◽  
Author(s):  
Luca Parisi ◽  
Narrendar RaviChandran ◽  
Matteo Lanzillotta
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Knee Osteoarthritis ◽  
Gait Analysis ◽  
Meta Analysis ◽  
Supervised Machine Learning ◽  
Gait Patterns ◽  
Kinematic Data ◽  
Knee Oa ◽  
Symptomatic Knee

<p><b>Background</b></p> <p>Knee osteoarthritis (OA) remains a leading aetiology of disability worldwide. Clinical assessment of such knee-related conditions has improved with recent advances in gait analysis. Despite being a gold standard method, gait data acquired by motion capture (mocap) technology are highly non-linear and dimensional, which make traditional gait analysis challenging. Thus, extrinsic algorithms need to be used to make sense of gait data. Supervised Machine Learning (ML)-based classifiers outperform conventional statistical methods in revealing intrinsic patterns that can discern gait abnormalities when using mocap data, making them a suitable tool for aiding diagnosis of knee OA.</p> <p><b>Research question</b></p> <p>Studies have demonstrated the accuracy of supervised ML-based classifiers in gait analysis. However, these techniques have not gained wide acceptance amongst biomechanists for two reasons: the reliability of such methods has not been assessed and there is no consensus on which classifier or group of classifiers to select. Specifically, it is not clear whether classifiers that leverage optimal separating hyperplanes (OSH) or artificial neural networks (ANN) are more accurate and reliable.</p> <p><b>Methods</b></p> <p>A systematic review and meta-analysis were conducted to assess the capability of such algorithms to predict pathological kinematic and kinetic gait patterns as indicators of knee OA. With 153 eligible studies, 6 studies met the inclusion criteria for a subsequent meta-analysis, accounting for <a>273 healthy subjects and 313 patients </a>with symptomatic knee OA. The classification performance of supervised ML classifiers (OSH- or ANN-based) used in these studies was quantitatively assessed and compared across four following performance metrics: classification accuracy on the test set (ACC), sensitivity (SN), specificity (SP), and area under the receiver operating characteristic curve (AUC). </p> <p><b>Results</b></p> <p>There was no statistically significant discrepancy in the ACC between OSH- and ANN-based classifiers when dealing with kinetic and kinematic data concurrently, as well as when considering only kinematic data. However, there was a statistically significant difference in their SN and SP, with the ANN-based classifiers having higher SN and SP than OSH-based algorithms. As only one of the eligible studies reported AUC, this metric could not be assessed statistically across studies.</p> <p><b>Significance</b></p> <p>This study supports the use of ANN-based algorithms for classifying knee OA-related gait patterns as having a higher sensitivity and specificity than OSH-based classifiers. Considering their higher reliability, leveraging supervised ANN-based methods can aid biomechanists to diagnose knee OA objectively.</p>

scholarly journals Critical spatiotemporal gait parameters for individuals with dementia: A systematic review and meta-analysis

2020 ◽  
pp. 1-14
Author(s):  
Rita Chiaramonte ◽  
Matteo Cioni
Keyword(s):  
Systematic Review ◽  
Gait Analysis ◽  
Dual Task ◽  
Stride Length ◽  
Meta Analysis ◽  
Time Variability ◽  
Stride Time ◽  
Single Task ◽  
Gait Parameters ◽  
Risk Of Falls

Instrumented gait analysis allows for the identification of walking parameters to predict cognitive decline and the worsening of dementia. The aim of this study was to perform a meta-analysis to better clarify which gait parameters are affected or modified with the progression of the dementia in a larger sample, as well as which gait assessment conditions (single-task or dual-task conditions) would be more sensitive to reflect the influence of dementia. Literature searches were conducted with the keywords “quantitative gait” OR “gait analysis” AND “dementia” AND “single-task” AND “dual-task,” and for “quantitative gait” OR “gait analysis” AND “dementia” AND “fall risk” on PubMed, EMBASE, the Cochrane Library, Scopus, and Web of Science. The results were used to perform a systematic review focussing on instrumental quantitative assessment of the walking of patients with dementia, during both single and dual tasks. The search was performed independently by two authors (C. R. and C. M.) from January 2018 to April 2020 using the PICOS criteria. Nine publications met the inclusion criteria and were included in the systematic review. Our meta-analysis showed that during a single task, most of the spatiotemporal parameters of gait discriminated best between patients with dementia and healthy controls, including speed, cadence, stride length, stride time, stride time variability, and stance time. In dual tasks, only speed, stride length, and stride time variability discriminated between the two groups. In addition, compared with spatial parameters (e.g. stride length), some temporal gait parameters were more correlated to the risk of falls during the comfortable walking in a single task, such as cadence, stride time, stride time variability, and stance time. During a dual task, only the variability of stride time was associated with the risk of falls.

scholarly journals Supervised Machine Learning for Aiding Diagnosis of Knee Osteoarthritis: A Systematic Review and Meta-Analysis

2020 ◽  
Author(s):  
Luca Parisi ◽  
Narrendar RaviChandran ◽  
Matteo Lanzillotta
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Knee Osteoarthritis ◽  
Gait Analysis ◽  
Meta Analysis ◽  
Supervised Machine Learning ◽  
Gait Patterns ◽  
Kinematic Data ◽  
Knee Oa ◽  
Symptomatic Knee

<p><b>Background</b></p> <p>Knee osteoarthritis (OA) remains a leading aetiology of disability worldwide. Clinical assessment of such knee-related conditions has improved with recent advances in gait analysis. Despite being a gold standard method, gait data acquired by motion capture (mocap) technology are highly non-linear and dimensional, which make traditional gait analysis challenging. Thus, extrinsic algorithms need to be used to make sense of gait data. Supervised Machine Learning (ML)-based classifiers outperform conventional statistical methods in revealing intrinsic patterns that can discern gait abnormalities when using mocap data, making them a suitable tool for aiding diagnosis of knee OA.</p> <p><b>Research question</b></p> <p>Studies have demonstrated the accuracy of supervised ML-based classifiers in gait analysis. However, these techniques have not gained wide acceptance amongst biomechanists for two reasons: the reliability of such methods has not been assessed and there is no consensus on which classifier or group of classifiers to select. Specifically, it is not clear whether classifiers that leverage optimal separating hyperplanes (OSH) or artificial neural networks (ANN) are more accurate and reliable.</p> <p><b>Methods</b></p> <p>A systematic review and meta-analysis were conducted to assess the capability of such algorithms to predict pathological kinematic and kinetic gait patterns as indicators of knee OA. With 153 eligible studies, 6 studies met the inclusion criteria for a subsequent meta-analysis, accounting for <a>273 healthy subjects and 313 patients </a>with symptomatic knee OA. The classification performance of supervised ML classifiers (OSH- or ANN-based) used in these studies was quantitatively assessed and compared across four following performance metrics: classification accuracy on the test set (ACC), sensitivity (SN), specificity (SP), and area under the receiver operating characteristic curve (AUC). </p> <p><b>Results</b></p> <p>There was no statistically significant discrepancy in the ACC between OSH- and ANN-based classifiers when dealing with kinetic and kinematic data concurrently, as well as when considering only kinematic data. However, there was a statistically significant difference in their SN and SP, with the ANN-based classifiers having higher SN and SP than OSH-based algorithms. As only one of the eligible studies reported AUC, this metric could not be assessed statistically across studies.</p> <p><b>Significance</b></p> <p>This study supports the use of ANN-based algorithms for classifying knee OA-related gait patterns as having a higher sensitivity and specificity than OSH-based classifiers. Considering their higher reliability, leveraging supervised ANN-based methods can aid biomechanists to diagnose knee OA objectively.</p>

Sign in / Sign up

Export Citation Format

Share Document