Evaluation of Home-Based Rehabilitation Sensing Systems with Respect to Standardised Clinical Tests

Abstract

With increased demand for tele-rehabilitation, many autonomous home-based rehabilitation systems have appeared recently. Many of these systems, however, suffer from lack of patient acceptance and engagement or fail to provide satisfactory accuracy; both are needed for appropriate diagnostics. This paper first provides a detailed discussion of current sensor-based home-based rehabilitation systems with respect to four recently established criteria for wide acceptance and long engagement. A methodological procedure is then proposed for the evaluation of accuracy of portable sensing home-based rehabilitation systems, in line with medically-approved tests and recommendations. For experiments, we deploy an in-house low-cost sensing system meeting the four criteria of acceptance to demonstrate the effectiveness of the proposed evaluation methodology. We observe that the deployed sensor system has limitations in sensing fast movement. Indicators of enhanced motivation and engagement are recorded through the questionnaire responses with more than 83% of the respondents supporting the system's motivation and engagement enhancement. The evaluation results demonstrate that the deployed system is fit for purpose with statistically significant ( c > 0.99, R 2 > 0.94, ICC > 0.96) and unbiased correlation to the golden standard. Author Contributions: Conceptualization, I.V.; methodology, I.V.; software, I.V.; validation, I.V.; formal analysis, I.V.; investigation, I.V.; resources, I.V.; data curation, I.V.; writing-original draft preparation, I.V.; writing-review and editing, L.S., V.S. and A.L.M.; visualization, I.V.; supervision, V.S. and L.S.; project administration, I.V.; funding acquisition, V.S. All authors have read and agreed to the published version of the manuscript.

Individualised Responsible Artificial Intelligence for Home-Based Rehabilitation

“…In terms of patient evaluation for home-based rehabilitation progress monitoring, two medical tests are identified in [1]. These are the Timed Up and Go (TUG) and the Five Time Sit To Stand (FTSTS) tests.…”

“…We require a dataset that can be used both to monitor progress of activities relevant to rehabilitation and also to diagnose both individual difficulties and medical conditions or comorbidities. We leverage on the small experimental dataset of [1], where a sensor-based platform was introduced for data collection and analysis of the two medical tests used in subject evaluation, namely TUG and FTSTS. A thorough review of patient evaluation medical tests and their relation to home-based rehabilitation is presented in [1].…”

“…Modern healthcare and socioeconomic reasons in the post-COVID-19 world require home-based rehabilitation without specialist assistance. As discussed in detail in [1], the need for home-based rehabilitation is multifaceted, from patient psychology to reduced hospital funding per patient. Approximately 50,000 patients are discharged for home-based rehabilitation every year in England alone [2].…”

“…According the review in [1], patient motivation and engagement have a critical impact on the success [3] of home-based rehabilitation, as there are no frequent checks from a supervising person. Many current approaches are abandoned within the first 90 days of use because the lack motivating and engaging user interfaces [4].…”

“…The motivation is linked to goal setting and it depends on individual achievements [5]. Thus, the technology must be co-created with the end user to both adapt to the individual and provide relevant and achievable goals through a dialogic approach to simple motivational user feedback [1].…”