kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Quantifying Gait Characteristics and Neurological Effects in people with Spinal Cord Injury using Data-Driven Techniques
KTH, School of Engineering Sciences (SCI), Engineering Mechanics, Vehicle Engineering and Solid Mechanics. (KTH MoveAbility)ORCID iD: 0000-0003-4571-1984
2024 (English)Licentiate thesis, comprehensive summary (Other academic)Alternative title
Kvantifiering av gångens egenskaper och neurologisk funktionens effekt hos personer med ryggmärgsskada med hjälp av datadrivna metoder (Swedish)
Abstract [en]

Spinal cord injury, whether traumatic or nontraumatic, can partially or completely damage sensorimotor pathways between the brain and the body, leading to heterogeneous gait abnormalities. Mobility impairments also depend on other factors such as age, weight, time since injury, pain, and walking aids used. The ASIA Impairment Scale is recommended to classify injury severity, but is not designed to characterize individual ambulatory capacity. Other standardized tests based on subjective or timing/distance assessments also have only limited ability to determine an individual's capacity. Data-driven techniques have demonstrated effectiveness in analysing complexity in many domains and may provide additional perspectives on the complexity of gait performance in persons with spinal cord injury. The studies in this thesis aimed to address the complexity of gait and functional abilities after spinal cord injury using data-driven approaches.

The aim of the first manuscript was to characterize the heterogeneous gait patterns in persons with incomplete spinal cord injury. Dissimilarities among gait patterns in the study population were quantified with multivariate dynamic time warping. Gait patterns were classified into six distinct clusters using hierarchical agglomerative clustering. Through random forest classifiers with explainable AI, peak ankle plantarflexion during swing was identified as the feature that most often distinguished most clusters from the controls. By combining clinical evaluation with the proposed methods, it was possible to provide comprehensive analyses of the six gait clusters.    

The aim of the second manuscript was to quantify sensorimotor effects on walking performance in persons with spinal cord injury. The relationships between 11 input features and 2 walking outcome measures - distance walked in 6 minutes and net energy cost of transport - were captured using 2 Gaussian process regression models. Explainable AI revealed the importance of muscle strength on both outcome measures. Use of walking aids also influenced distance walked, and  cardiovascular capacity influenced energy cost. Analyses for each person also gave useful insights into individual performance.    

The findings from these studies demonstrate the large potential of advanced machine learning and explainable AI to address the complexity of gait function in persons with spinal cord injury.

Abstract [sv]

Skador på ryggmärgen, oavsett om de är traumatiska eller icke-traumatiska, kan helt eller delvis skada sensoriska och motoriska banor mellan hjärnan och kroppen, vilket påverkar gången i varierande grad. Rörelsenedsättningen beror också på andra faktorer såsom ålder, vikt, tid sedan skadan uppstod, smärta och gånghjälpmedel. ASIA-skalan används för att klassificera ryggmärgsskadans svårighetsgrad, men är inte utformad för att karaktärisera individens gångförmåga. Andra standardiserade tester baserade på subjektiva eller tids och avståndsbedömningar har också begränsad möjlighet att beskriva individuell kapacitet. Datadrivna metoder är kraftfulla och kan ge ytterligare perspektiv på gångens komplexitet och prestation. Studierna i denna avhandling syftar till att analysera komplexa relationer mellan gång, motoriska samt sensoriska funktion efter ryggmärgsskada med hjälp av datadrivna metoder.

Syftet med den första studien är att karaktärisera de heterogena gångmönster hos personer med inkomplett ryggmärgsskada. Multivariat dynamisk tidsförvrägning (eng: Multivariate dynamic time warping) användes för att kvantifiera gångskillnader i studiepopulationen. Hierarkisk agglomerativ klusteranalys (eng: hierarchical agglomerative clustering) delade upp gång i sex distinkta kluster, varav fyra hade lägre hastighet än kontroller. Med hjälp av förklarbara AI (eng: explainable AI) identifierades det att fotledsvinkeln i svingfasen hade störst påverkan om vilken kluster som gångmönstret hamnat i. Genom att kombinera klinisk undersökning med datadrivna metoder kunde vi beskriva en omfattande bild av de sex gångklustren.

Syftet med den andra manuskriptet är att kvantifiera sensoriska och motoriska faktorerans påverkan på gångförmåga efter ryggmärgsskada. Med hjälp av två Gaussian process-regressionsmodeller identiferades sambanden mellan 11 beskrivande faktorer och 2 gång prestationsmått, nämligen gångavstånd på 6 minuter samt metabola energiåtgång. Med hjälp av förklarbar AI påvisades det stora påverkan av muskelstyrka på både gångsträckan och energiåtgång. Gånghjälpmedlet samt kardiovaskulär kapaciteten hade också betydande påverkan på gångprestation. Enskilda analyser gav insiktsfull information om varje individ.

Resultaten från dessa studier visar på potentiella tillämpningar av avancerad maskininlärning och AI metoder för att analysera komplexa relationer mellan funktion och motorisk prestation efter ryggmärgsskada.

Place, publisher, year, edition, pages
Stockholm: KTH Royal Institute of Technology, 2024. , p. 45
Series
TRITA-SCI-FOU ; 2024:11
Keywords [en]
gait analysis, pathological gait, biomechanics, health informatics, metabolic cost, unsupervised learning, nonparametric regression, shapley addictive explanations
Keywords [sv]
gånganalys, funktionsnedsättning, gångpatologi, energiförbrukning, maskininlärning, hälsoinformatik, biomekanik, AI
National Category
Health Sciences Clinical Medicine
Research subject
Engineering Mechanics
Identifiers
URN: urn:nbn:se:kth:diva-343577ISBN: 978-91-8040-850-9 (print)OAI: oai:DiVA.org:kth-343577DiVA, id: diva2:1839419
Presentation
2024-03-12, https://kth-se.zoom.us/j/7691643418, E3, Osquars Backe 14, Stockholm, 10:00 (English)
Opponent
Supervisors
Funder
Promobilia foundation, 18200Swedish Research Council, 2018-00750
Note

QC 20240221

Available from: 2024-02-21 Created: 2024-02-20 Last updated: 2024-03-06Bibliographically approved
List of papers
1. Gait Stratification in People with Incomplete Spinal Cord Injury using Data-Driven Techniques
Open this publication in new window or tab >>Gait Stratification in People with Incomplete Spinal Cord Injury using Data-Driven Techniques
(English)Manuscript (preprint) (Other academic)
Abstract [en]

Background: Incomplete spinal cord injury often causes heterogeneous locomotion function, depending on remaining sensorimotor functions below the injury. Standardized tests have limited ability to quantify diverse gait impairments. Combining clustering methods with dynamic time warping distances can objectively capture heterogeneous gait patterns without bias. Moreover, tree-based models with explainable AI can reveal important features often missed by traditional gait analyses. This study presents a framework to characterize gait heterogeneity in persons with incomplete spinal cord injury based on unsupervised learning and explainable AI. We aimed to stratify gait heterogeneity into clusters without priori identification of parameters, and to gain clinical insights into the derived clusters.

Methods: A cohort of 28 individuals with incomplete spinal cord injury and 21 non-disabled control subjects were recruited. Individuals with incomplete spinal cord injury underwent physical assessment of lower extremity strength, sensory function, and spasticity. Both groups underwent 3D gait analysis.  Multidimensional dynamic time warping and hierarchical agglomerative clustering were used to identify distinct gait subgroups after injury. A random forest classifier and TreeSHAP were used to identify gait predictors that distinguished each cluster from the controls. 

Results: Six distinct gait clusters were identified from 280 gait cycles. Walking speed and step length were smaller than controls in four clusters. Gait patterns in two clusters were relatively similar to those in control.  Low maximal ankle plantarflexion during swing was found to be a common gait impairments in five of the six clusters. Overall muscle strength significantly differed between clusters.

Conclusions: In this study, we describe a data-driven framework coupled with explainable AI to identify clusters of common gait patterns without priori parameter identification among the otherwise heterogeneous gait patterns in persons with spinal cord injury. This work represents an initial step in developing individualized rehabilitation programs for persons with incomplete spinal cord injury.

Keywords
multivariate time series, hierarchical clustering analysis, pathological gait, binary classification, shapley addictive explanations
National Category
Health Sciences Clinical Medicine
Research subject
Engineering Mechanics
Identifiers
urn:nbn:se:kth:diva-343580 (URN)
Funder
Promobilia foundation, 18200Swedish Research Council, 2018-00750
Note

QC 20240228

Available from: 2024-02-20 Created: 2024-02-20 Last updated: 2025-03-31Bibliographically approved
2. Estimation of Sensorimotor Effects on Walking Performance in people with Spinal Cord Injury
Open this publication in new window or tab >>Estimation of Sensorimotor Effects on Walking Performance in people with Spinal Cord Injury
(English)Manuscript (preprint) (Other academic)
Abstract [en]

Spinal cord injury (SCI) impairs sensorimotor pathways, reducing walking ability. Effects of sensorimotor impairments are complex due to interactions with other factors such as age, aids, injury level, and severity. Traditional regression analysis has commonly been used to capture the effects, but it assumes linearity and misses local feature impacts. Meanwhile, explainable AI methods like SHapley Addictive exPlanations (SHAP) can reveal feature importances globally and locally based on cooperative game theory. Additionally, Gaussian Process Regression (GPR) can handle limited data sets, a common challenge in medical studies with small sample sizes. In this study, we proposed and evaluated a framework applying GPR and SHAP to quantify how sensorimotor impairments impact post-SCI walking performance. Thirty four recruited individuals with SCI underwent a clinical assessment and a six-minute walk test with oxygen consumption measurement. We identified strong linear relationships between muscle strength and six-minute walk test performance wherein greater strength was associated with longer distance walked and lower energy costs. The findings also highlighted considerable impacts of walking aids and cardiovascular capacity on post-SCI mobility. Individual SHAP analyses quantified how neurological factors influenced walking performance for each participant. This study demonstrated that nonparametric regression and explainable AI could provide insights into the complex neurological factors affecting walking ability in persons with SCI.

Keywords
health informatics, neurological effects, individualized effects, metabolic cost, shapley value
National Category
Health Sciences Clinical Medicine
Research subject
Engineering Mechanics
Identifiers
urn:nbn:se:kth:diva-343581 (URN)
Funder
Swedish Research Council, 2018-00750Promobilia foundation, 18200
Note

QC 20240228

Available from: 2024-02-20 Created: 2024-02-20 Last updated: 2025-03-31Bibliographically approved

Open Access in DiVA

kappa(7723 kB)598 downloads
File information
File name FULLTEXT01.pdfFile size 7723 kBChecksum SHA-512
8f547de184fd58506bd65abec3c3276aa7a54bc99d0260dfbed82549506e710b309e106a64da3dd212f9c7aa45a7af5c70a453298172ea3619a0df97e8cc3b7c
Type fulltextMimetype application/pdf

Authority records

Truong, Minh

Search in DiVA

By author/editor
Truong, Minh
By organisation
Vehicle Engineering and Solid Mechanics
Health SciencesClinical Medicine

Search outside of DiVA

GoogleGoogle Scholar
Total: 599 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 1270 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf