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

Egocentric vision-based detection of surfaces: towards context-aware free-living digital biomarkers for gait and fall risk assessment

Background

Falls in older adults are a critical public health problem. As a means to assess fall risks, free-living digital biomarkers (FLDBs), including spatiotemporal gait measures, drawn from wearable inertial measurement unit (IMU) data have been investigated to identify those at high risk. Although gait-related FLDBs can be impacted by intrinsic (e.g., gait impairment) and/or environmental (e.g., walking surfaces) factors, their respective impacts have not been differentiated by the majority of free-living fall risk assessment methods. This may lead to the ambiguous interpretation of the subsequent FLDBs, and therefore, less precise intervention strategies to prevent falls.

Methods

With the aim of improving the interpretability of gait-related FLDBs and investigating the impact of environment on older adults’ gait, a vision-based framework was proposed to automatically detect the most common level walking surfaces. Using a belt-mounted camera and IMUs worn by fallers and non-fallers (mean age 73.6 yrs), a unique dataset (i.e., Multimodal Ambulatory Gait and Fall Risk Assessment in the Wild (MAGFRA-W)) was acquired. The frames and image patches attributed to nine participants’ gait were annotated: (a) outdoor terrains: pavement (asphalt, cement, outdoor bricks/tiles), gravel, grass/foliage, soil, snow/slush; and (b) indoor terrains: high-friction materials (e.g., carpet, laminated floor), wood, and tiles. A series of ConvNets were developed: EgoPlaceNet categorizes frames into indoor and outdoor; and EgoTerrainNet (with outdoor and indoor versions) detects the enclosed terrain type in patches. To improve the framework’s generalizability, an independent training dataset with 9,424 samples was curated from different databases including GTOS and MINC-2500, and used for pretrained models’ (e.g., MobileNetV2) fine-tuning.

Results

EgoPlaceNet detected outdoor and indoor scenes in MAGFRA-W with 97.36$$\%$$ % and 95.59$$\%$$ % (leave-one-subject-out) accuracies, respectively. EgoTerrainNet-Indoor and -Outdoor achieved high detection accuracies for pavement (87.63$$\%$$ % ), foliage (91.24$$\%$$ % ), gravel (95.12$$\%$$ % ), and high-friction materials (95.02$$\%$$ % ), which indicate the models’ high generalizabiliy.

Conclusions

Encouraging results suggest that the integration of wearable cameras and deep learning approaches can provide objective contextual information in an automated manner, towards context-aware FLDBs for gait and fall risk assessment in the wild.

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

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.

Automated Detection of Multidirectional Compensatory Balance Reactions: A Step Towards Tracking Naturally Occurring Near Falls

Falls are the leading cause of fatal and non-fatal injuries among seniors with serious and costly consequences. Laboratory evidence supports the view that impaired ability to execute compensatory balance reactions (CBRs) or near-falls is linked to an increased risk of falling. Therefore, as an alternative to the commonly used fall risk assessment methods examining spatial-temporal parameters of gait, this study focuses on the development of machine learning-based models to detect multidirectional CBRs using wearable inertial measurement units (IMUs). Random forest models were developed based upon the data captured by five wearable IMUs to 1) detect CBRs during normal gait, and 2) identify the type of CBR (eight different classes). A perturbation treadmill (PT) was employed to systematically elicit CBRs (i.e. PT-CBRs) during walking in different directions (e.g slip-like, trip-like, and medio-lateral) and amplitudes (e.g., low-, high-amplitude). We hypothesized that these PT-CBRs could simulate naturally-occurring CBRs (N-CBRs). Proof-of-concept testing in 9 young, healthy adults demonstrated accuracies of 96.60% and 80.64% for the PT-CBR detection and type identification models, respectively. Performance of the detection model was tested against a published dataset (IMUFD) simulating N-CBRs, including the most common types observed in older adults in long-term care facilities, which achieved sensitivity of 100%, but poor specificity. Adding normal gait data from IMUFD for training improved specificity, indicating treadmill walking alone is insufficient exemplar data. Perturbation treadmill combined with overground walking data is a suitable paradigm to collect training datasets of involuntary CBR events. These findings suggest that accurate detection of naturally-occurring CBRs is feasible, and supports further investigation of implementing a wearable sensor system to track naturally-occurring CBRs as a novel means of fall risk assessment.