Feasibility of Sensor Technology for Balance Assessment in Home Rehabilitation Settings

AI-driven balance evaluation: a comparative study between blind and non-blind individuals using the mini-BESTest

There are 2.2 billion visually impaired individuals and 285 million blind people worldwide. The vestibular system plays a fundamental role in the balance of a person related to sight and hearing, and thus blind people require physical therapy to improve their balance. Several clinical tests have been developed to evaluate balance, such as the mini-BESTest. This test has been used to evaluate the balance of people with neurological diseases, but there have been no studies that evaluate the balance of blind individuals before. Furthermore, despite the scoring of these tests being not subjective, the performance of some activities are subject to the physiotherapist's bias. Tele-rehabilitation is a growing field that aims to provide physical therapy to people with disabilities. Among the technologies used in tele-rehabilitation are inertial measurement units that can be used to monitor the balance of individuals. The amount of data collected by these devices is large and the use of deep learning models can help in analyzing these data. Therefore, the objective of this study is to analyze for the first time the balance of blind individuals using the mini-BESTest and inertial measurement units and to identify the activities that best differentiate between blind and sighted individuals. We use the OpenSense RT monitoring device to collect data from the inertial measurement unit, and we develop machine learning and deep learning models to predict the score of the most relevant mini-BESTest activities. In this study 29 blind and sighted individuals participated. The one-legged stance is the activity that best differentiates between blind and sighted individuals. An analysis on the acceleration data suggests that the evaluation of physiotherapists is not completely adjusted to the test criterion. Cluster analysis suggests that inertial data are not able to distinguish between three levels of evaluation. However, the performance of our models shows an F1-score of 85.6% in predicting the score evaluated by the mini-BESTest in a binary classification problem. The results of this study can help physiotherapists have a more objective evaluation of the balance of their patients and to develop tele-rehabilitation systems for blind individuals.

Use of an inertial sensor and a force platform to assess static balance in participants affected by multibacillary leprosy

INTRODUCTION

Leprosy is a chronic, slowly developing infectious disease that affects the peripheral nerves, specifically Schwann cells. Individuals with the multibacillary type exhibit a propensity for developing chronic pain and a decrease in sensitivity in the plantar region, which directly interferes with balance maintenance. The evaluation of static balance in this population is made through the measurement of the center of pressure (COP) oscillations. Therefore, there is a need to investigate the association between postural control and COP oscillations using a force platform and finding accelerations of the center of mass (COM) from inertial sensors for reliable and portable balance assessment in leprosy patients.

OBJECTIVE

To validate the application of inertial sensors for patients with leprosy by establishing a correlation with the outcomes obtained from a force platform.

METHODS

This is an observational study with a case-control design, in which 30 participants with leprosy and 30 healthy participants were recruited to evaluate static balance using an inertial sensor and a force platform. Participants underwent balance assessment under two conditions (Eyes Open: OE and Eyes Closed: CE), and data from the platform and sensor were processed using Matlab computational routines. The data were quantified using four parameters: Total Displacement (TD), Area, Antero-Posterior Displacement (APdisp), and Medio-Lateral Displacement (MLdisp).

RESULTS

The evaluated parameters showed significantly different values between the groups, where the Leprosy group exhibited significantly higher values compared to the control group, both in the OE and CE conditions for all four parameters. The sensor corroborated the differences demonstrated by the platform and followed the same trend for medio-lateral displacements and accelerations. It can be observed that the evaluated parameters exhibited a varied correlation ranging from moderate to large between the platform and the sensor. Among the four variables, MLdisp had the lowest correlation.

DISCUSSION

The results partially confirmed the first hypothesis of concurrent validation, showing a moderate to large correlation between the force platform and the inertial sensor. The second hypothesis of clinical validation was also partially confirmed, as not all group differences observed in the COP measurements from the force platform were reflected in the COM measurements from the inertial sensor. Specifically, the force platform indicated greater oscillations in participants with multibacillary leprosy compared to controls, a finding statistically confirmed by the sensor for all measures except MLdisp.

CONCLUSION

This research confirmed the concurrent validity of the inertial sensor with the force platform and its clinical validation, demonstrating that this instrument can be applied in clinical settings due to its low cost and ease of use. The findings may contribute to public health by identifying postural control tools for patients with multibacillary leprosy.

The Application of Wearable Sensors and Machine Learning Algorithms in Rehabilitation Training: A Systematic Review

The integration of wearable sensor technology and machine learning algorithms has significantly transformed the field of intelligent medical rehabilitation. These innovative technologies enable the collection of valuable movement, muscle, or nerve data during the rehabilitation process, empowering medical professionals to evaluate patient recovery and predict disease development more efficiently. This systematic review aims to study the application of wearable sensor technology and machine learning algorithms in different disease rehabilitation training programs, obtain the best sensors and algorithms that meet different disease rehabilitation conditions, and provide ideas for future research and development. A total of 1490 studies were retrieved from two databases, the Web of Science and IEEE Xplore, and finally 32 articles were selected. In this review, the selected papers employ different wearable sensors and machine learning algorithms to address different disease rehabilitation problems. Our analysis focuses on the types of wearable sensors employed, the application of machine learning algorithms, and the approach to rehabilitation training for different medical conditions. It summarizes the usage of different sensors and compares different machine learning algorithms. It can be observed that the combination of these two technologies can optimize the disease rehabilitation process and provide more possibilities for future home rehabilitation scenarios. Finally, the present limitations and suggestions for future developments are presented in the study.

Smart Lacelock Sensor for the Balance Assessment of Community-Dwelling Older People

This paper introduces a novel wearable shoe sensor named the Smart Lacelock Sensor. The sensor can be securely attached to the top of a shoe with laces and incorporates a loadcell to measure the force applied by the shoelace, providing valuable information related to ankle movement and foot loading. As the first step towards the automated balance assessment, this paper investigates the correlations between various levels of physical performance measured by the wearable Smart Lacelock Sensor and the SPPB clinical method in community-living older persons. 19 adults (age 76.84 ± 3.45 years), including those with and without recent fall history and SPPB score ranging from 4 to 12, participated in the study. The Smart Lacelock Sensor was attached to both shoes of each participant by skilled research staff, who then led them through the SPPB evaluation. The data obtained from the Smart Lacelock Sensors after the SPPB assessment were used to evaluate the deviation between the SPPB scores assigned by the research staff and the signals generated by the sensors for various participants. Results demonstrate that the standard deviation of the Smart Lacelock Sensor's loadcell response (both feet) for the side-by-side balance testing is significantly correlated (R2 = 0.68) with the SPPB score, demonstrating the capability of the Smart Lacelock Sensor in balance assessment.