Chasing Feet in the Wild: A Proposed Egocentric Motion-Aware Gait Assessment Tool

Nouredanesh, Mina; Li, Aaron W.; Godfrey, Alan; Hoey, Jesse; Tung, James

doi:10.1007/978-3-030-11024-6_12

Cited by 8 publications

(5 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous CBR detection studies [19]- [22] considered alternate methods of model training and performance assessment, such as k-fold and leave-one-subject-out cross-validation. Similar to our previous research works [21], [23], we hypothesize in the current study that incorporating a training dataset curated from data sources that are independently collected from the test dataset would result in the machine learning models with more realistic results in terms of generalization to unseen data (although lower accuracies are expected to be obtained compared to the cross-validation methods where training and test datasets share very similar distributions, e.g., k-fold [21]). Specifically, this study examines the use of in-lab perturbation data for model training as a viable approach to detect real-world CBRs (in the test dataset).…”

Section: A Key Considerations For Cbr Detection Models' Training and ...mentioning

confidence: 57%

Automated Detection of Older Adults’ Naturally-Occurring Compensatory Balance Reactions: Translation From Laboratory to Free-Living Conditions

Nouredanesh

Ojeda

Alexander

et al. 2022

IEEE J. Transl. Eng. Health Med.

Self Cite

View full text Add to dashboard Cite

Objective: Older adults' falls are a critical public health problem. The majority of free-living fall risk assessment methods have investigated fall predictive power of step-related digital biomarkers extracted from wearable inertial measurement unit (IMU) data. Alternatively, the examination of characteristics and frequency of naturally-occurring compensatory balance reactions (CBRs) may provide valuable information on older adults' propensity for falls. To address this, models to automatically detect naturally-occurring CBRs are needed. However, compared to steps, CBRs are rare events. Therefore, prolonged collection of criterion standard data (along with IMU data) is required to validate model's performance in free-living conditions. Methods: By investigating 11 fallers' and older non-fallers' freeliving criterion standard data, 8 naturally-occurring CBRs, i.e., 7 trips (self-reported using a wrist-mounted voice-recorder) and 1 hit/bump (verified using egocentric vision data) were localized in the corresponding trunk-mounted IMU data. Random forest models were trained on independent/unseen datasets curated from multiple sources, including in-lab data captured using a perturbation treadmill. Subsequently, the models' translation/generalization to older adults' out-of-lab data were assessed. Results: A subset of models differentiated between naturally-occurring CBRs and free-living activities with high sensitivity (100%) and specificity (≥ 99%). Conclusions: The findings suggest that accurate detection of naturally-occurring CBRs is feasible. Clinical/Translational Impact-As a multi-institutional validation study to detect older adults' naturally-occurring CBRs, suitability for larger-scale free-living studies to investigate falls etiology, and/or assess the effectiveness of perturbation training programs is discussed.INDEX TERMS Compensatory balance reactions, free-living digital biomarker, falls, machine learning, fall risk assessment.

show abstract

Section: A Key Considerations For Cbr Detection Models' Training and ...mentioning

confidence: 57%

Automated Detection of Older Adults’ Naturally-Occurring Compensatory Balance Reactions: Translation From Laboratory to Free-Living Conditions

Nouredanesh

Ojeda

Alexander

et al. 2022

IEEE J. Transl. Eng. Health Med.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Equally, it is not possible to quantify the usual free-living mobility habits of the participants or to determine if this chronic mTBI cohort displayed any compensatory behaviour strategies (e.g., refraining from talking or performing other tasks whilst walking) that could further impact results. The introduction of egocentric video recordings of free-living mobility may enable greater insight and a robust reference to better understand the context of environments [53]. If used in conjunction with objective free-living IMU assessment, video data could yield even greater contextual understanding of free-living gait performance and any compensatory behaviour mTBI patients display within an environment.…”

Section: Free-living Gait Quality Measures Are Not Impaired In Chroni...mentioning

confidence: 99%

“…Although use of a single IMU alone on the lower back facilitated more rapid data collection and reduced burden, it fails to quantify other useful gait characteristics which may provide more insight to dynamic postural control and environmental information i.e., step width and step width variability arising from uneven terrain [55].Thus, future research should investigate additional gait characteristics (based on conceptual gait models) with e.g., multiple IMU's (on the feet) or a video-based wearable for a more informed free-living assessment. While the authors are not currently aware of any IMU-based technology to quantify step width during free-living, a computer vision approach has been suggested from a wearable camera [53]. Additionally, the outcome measures presented are primarily research-orientated, requiring a great deal of time-consuming post-processing and checking, which is based on prior experience of inertial data [56,57].…”

Section: Strengths and Limitationsmentioning

confidence: 99%

Free-living gait does not differentiate chronic mTBI patients compared to healthy controls

Powell

Godfrey

Parrington

et al. 2022

J NeuroEngineering Rehabil

Self Cite

View full text Add to dashboard Cite

Background Physical function remains a crucial component of mild traumatic brain injury (mTBI) assessment and recovery. Traditional approaches to assess mTBI lack sensitivity to detect subtle deficits post-injury, which can impact a patient’s quality of life, daily function and can lead to chronic issues. Inertial measurement units (IMU) provide an opportunity for objective assessment of physical function and can be used in any environment. A single waist worn IMU has the potential to provide broad/macro quantity characteristics to estimate gait mobility, as well as more high-resolution micro spatial or temporal gait characteristics (herein, we refer to these as measures of quality). Our recent work showed that quantity measures of mobility were less sensitive than measures of turning quality when comparing the free-living physical function of chronic mTBI patients and healthy controls. However, no studies have examined whether measures of gait quality in free-living conditions can differentiate chronic mTBI patients and healthy controls. This study aimed to determine whether measures of free-living gait quality can differentiate chronic mTBI patients from controls. Methods Thirty-two patients with chronic self-reported balance symptoms after mTBI (age: 40.88 ± 11.78 years, median days post-injury: 440.68 days) and 23 healthy controls (age: 48.56 ± 22.56 years) were assessed for ~ 7 days using a single IMU at the waist on a belt. Free-living gait quality metrics were evaluated for chronic mTBI patients and controls using multi-variate analysis. Receiver operating characteristics (ROC) and Area Under the Curve (AUC) analysis were used to determine outcome sensitivity to chronic mTBI. Results Free-living gait quality metrics were not different between chronic mTBI patients and controls (all p > 0.05) whilst controlling for age and sex. ROC and AUC analysis showed stride length (0.63) was the most sensitive measure for differentiating chronic mTBI patients from controls. Conclusions Our results show that gait quality metrics determined through a free-living assessment were not significantly different between chronic mTBI patients and controls. These results suggest that measures of free-living gait quality were not impaired in our chronic mTBI patients, and/or, that the metrics chosen were not sensitive enough to detect subtle impairments in our sample.

show abstract

“…refraining from talking or performing other tasks whilst walking). The introduction of egocentric video recordings of free-living mobility may allow for better understanding and a robust reference [55]. If used in conjunction with objective free-living IMU assessment, video assessment could yield even greater understanding of free-living gait performance and any compensatory behaviour mTBI patients display within an environment.…”

Section: Free Living Gait Characteristics Are Not Impaired In Chronicmentioning

confidence: 99%

Free-living Turning Rather Than Gait Differentiates People with Chronic Mild Traumatic Brain Injury from Controls

Powell¹,

Godfrey²,

Parrington³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Background: Physical function remains a crucial component of mild traumatic brain injury (mTBI) assessment and recovery. Traditional approaches to assess mTBI lack sensitivity to subtle deficits post-injury, which can impact quality of life, daily function and can lead to chronic issues. Inertial measurement units (IMU) provide an objective alternative for measuring physical function of gait and turning and can be used in any environment. Our recent work has found that turning quality is more sensitive than the quantity of physical activity when comparing chronic mTBI and healthy controls. However, no studies have compared the quality of free-living gait and turning characteristics concurrently in chronic mTBI and healthy controls. This study aimed to determine whether free-living gait or turning is more sensitive in differentiating chronic mTBI from controls.Methods: Thirty-two people with chronic self-reported balance symptoms after mTBI (age: 40.88 ± 11.78 years, median days post injury: 440.68 days) and 23 healthy controls (age: 48.56 ± 22.56 years) were assessed for ~7 days using a single IMU at the waist on a belt. Free-living gait and turning characteristics were evaluated for chronic mTBI and controls using multi-variate analysis. Receiver operating characteristics (ROC) and Area Under the Curve (AUC) analysis were used to determine outcome sensitivity to chronic mTBI.Results: Free-living gait characteristics were not different in chronic mTBI and controls (all p>0.05). In contrast, all but two (number of turns and average velocity CV) free-living turning characteristics were significantly different between chronic mTBI and controls, whilst controlling for age and sex (Bonferroni adjusted p<0.002). The chronic mTBI group had larger turn angles and longer turn durations compared to controls. ROC and AUC analysis showed turn duration (AUC = 0.92) was the most sensitive measure for differentiating chronic mTBI from controls. Conclusions: Results show that turning rather than gait characteristics were significantly different between chronic mTBI and controls, with turn duration being the most sensitive measure. These results suggest turning is a suitable surrogate biomarker to assess and monitor chronic mTBI.

show abstract

Chasing Feet in the Wild: A Proposed Egocentric Motion-Aware Gait Assessment Tool

Cited by 8 publications

References 49 publications

Automated Detection of Older Adults’ Naturally-Occurring Compensatory Balance Reactions: Translation From Laboratory to Free-Living Conditions

Automated Detection of Older Adults’ Naturally-Occurring Compensatory Balance Reactions: Translation From Laboratory to Free-Living Conditions

Free-living gait does not differentiate chronic mTBI patients compared to healthy controls

Free-living Turning Rather Than Gait Differentiates People with Chronic Mild Traumatic Brain Injury from Controls

Contact Info

Product

Resources

About