A novel sensorized shoe system to classify gait severity in children with cerebral palsy

Present and future of gait assessment in clinical practice: Towards the application of novel trends and technologies

Background

Despite being available for more than three decades, quantitative gait analysis remains largely associated with research institutions and not well leveraged in clinical settings. This is mostly due to the high cost/cumbersome equipment and complex protocols and data management/analysis associated with traditional gait labs, as well as the diverse training/experience and preference of clinical teams. Observational gait and qualitative scales continue to be predominantly used in clinics despite evidence of less efficacy of quantifying gait.

Research objective

This study provides a scoping review of the status of clinical gait assessment, including shedding light on common gait pathologies, clinical parameters, indices, and scales. We also highlight novel state-of-the-art gait characterization and analysis approaches and the integration of commercially available wearable tools and technology and AI-driven computational platforms.

Methods

A comprehensive literature search was conducted within PubMed, Web of Science, Medline, and ScienceDirect for all articles published until December 2021 using a set of keywords, including normal and pathological gait, gait parameters, gait assessment, gait analysis, wearable systems, inertial measurement units, accelerometer, gyroscope, magnetometer, insole sensors, electromyography sensors. Original articles that met the selection criteria were included.

Results and significance

Clinical gait analysis remains highly observational and is hence subjective and largely influenced by the observer's background and experience. Quantitative Instrumented gait analysis (IGA) has the capability of providing clinicians with accurate and reliable gait data for diagnosis and monitoring but is limited in clinical applicability mainly due to logistics. Rapidly emerging smart wearable technology, multi-modality, and sensor fusion approaches, as well as AI-driven computational platforms are increasingly commanding greater attention in gait assessment. These tools promise a paradigm shift in the quantification of gait in the clinic and beyond. On the other hand, standardization of clinical protocols and ensuring their feasibility to map the complex features of human gait and represent them meaningfully remain critical challenges.

Machine learning corroborates subjective ratings of walking and balance difficulty in multiple sclerosis

Machine learning can discern meaningful information from large datasets. Applying machine learning techniques to raw sensor data from instrumented walkways could automatically detect subtle changes in walking and balance. Multiple sclerosis (MS) is a neurological disorder in which patients report varying degrees of walking and balance disruption. This study aimed to determine whether machine learning applied to walkway sensor data could classify severity of self-reported symptoms in MS patients. Ambulatory people with MS (n = 107) were asked to rate the severity of their walking and balance difficulties, from 1-No problems to 5-Extreme problems, using the MS-Impact Scale-29. Those who scored less than 3 (moderately) were assigned to the “mild” group (n = 35), and those scoring higher were in the “moderate” group (n = 72). Three machine learning algorithms were applied to classify the “mild” group from the “moderate” group. The classification achieved 78% accuracy, a precision of 85%, a recall of 90%, and an F1 score of 87% for distinguishing those people reporting mild from moderate walking and balance difficulty. This study demonstrates that machine learning models can reliably be applied to instrumented walkway data and distinguish severity of self-reported impairment in people with MS.

A heel-strike real-time auditory feedback device to promote motor learning in children who have cerebral palsy: a pilot study to test device accuracy and feasibility to use a music and dance-based learning paradigm

Background

Cerebral palsy (CP) is a developmental disorder of movement and posture that occurs due to damage to the developing nervous system. As part of therapy, wearable sensors that trigger interactive feedback may provide multi-sensory guidance and motivation. A prototype of a heel-strike real-time feedback system has been developed which records the number of heel strikes during gait and indicates successful heel contact through real-time auditory feedback. The first aim of this feasibility study was to test the prototype accuracy.Since the end user for this device is a child, the device should be esthetically appealing and sufficiently motivating for children to perform repetitive challenging therapeutic movements. The second aim of this study was to collect feedback from the subjects with regard to the device usability and understand if the bell sound used as feedback used was motivating enough for children to continue using the prototype. This would help us in developing the next generation of the device.

Methods

The prototype was tested with typically developing children and children who have CP. The accuracy in detecting heel strikes was calculated. As part of the study, the subjects were also asked questions to test the device compliance and acceptability of the musical beats with the pediatric population.

Results

The device accuracy in identifying heel strikes is 97.44% (95% CI 96.31, 98.88%). The subjects did not show any hesitation to put on the device and the sound feedback motivated them to move. Based on this pilot study, a minimum age limit of 5 years is appropriate and the intervention study should be conducted for no more than 30 min per week.

Conclusions

The pilot study showed that a main study can be conducted to test auditory feedback as an intervention to promote motor learning in children who have cerebral palsy. No adverse event or safety issues were reported in the feasibility study.

Evaluation of two approaches for aligning data obtained from a motion capture system and an in-shoe pressure measurement system

An in-shoe pressure measurement (IPM) system can be used to measure center of pressure (COP) locations, and has fewer restrictions compared to the more conventional approach using a force platform. The insole of an IPM system, however, has its own coordinate system. To use an IPM system along with a motion capture system, there is thus a need to align the coordinate systems of the two measurement systems. To address this need, the current study examined two different approaches—rigid body transformation and nonlinear mapping (i.e., multilayer feed-forward neural network (MFNN))—to express COP measurements from an IPM system in the coordinate system of a motion capture system. Ten participants (five male and five female) completed several simulated manual material handling (MMH) activities, and during these activities the performance of the two approaches was assessed. Results indicated that: (1) performance varied between MMH activity types; and (2) a MFNN performed better than or comparable to the rigid body transformation, depending on the specific input variable sets used. Further, based on the results obtained, it was argued that a nonlinear mapping vs. rigid body transformation approach may be more effective to account for shoe deformation during MMH or potentially other types of physical activity.

A wireless flexible sensorized insole for gait analysis

This paper introduces the design and development of a novel pressure-sensitive foot insole for real-time monitoring of plantar pressure distribution during walking. The device consists of a flexible insole with 64 pressure-sensitive elements and an integrated electronic board for high-frequency data acquisition, pre-filtering, and wireless transmission to a remote data computing/storing unit. The pressure-sensitive technology is based on an optoelectronic technology developed at Scuola Superiore Sant'Anna. The insole is a low-cost and low-power battery-powered device. The design and development of the device is presented along with its experimental characterization and validation with healthy subjects performing a task of walking at different speeds, and benchmarked against an instrumented force platform.