Publications

Background: There is a pressing need for scalable healthcare solutions and a shift in the rehabilitation paradigm from hospitals to homes to tackle the increase in stroke incidence while reducing the practical and economic burden for patients, hospitals, and society. Digital health technologies can contribute to addressing this challenge; however, little is known about their effectiveness in at-home settings. In response, we have designed the RGS@home study to investigate the effectiveness, acceptance, and cost of a deep tech solution called the Rehabilitation Gaming System (RGS). RGS is a cloud-based system for delivering Al-enhanced rehabilitation using virtual reality, motion capture, and wearables that can be used in the hospital and at home. The core principles of the brain theory-based RGS intervention are to deliver rehabilitation exercises in the form of embodied, goal-oriented, and task-specific action.; Methods: The RGS@home study is a randomized longitudinal clinical trial designed to assess whether the combination of the RGS intervention with standard care is superior to standard care alone for the functional recovery of stroke patients at the hospital and at home. The study is conducted in collaboration with hospitals in Spain, Sweden, and France and includes inpatients and outpatients at subacute and chronic stages post-stroke. The intervention duration is 3 months with assessment at baseline and after 3, 6, and 12 months. The impact of RGS is evaluated in terms of quality of life measurements, usability, and acceptance using standardized clinical scales, together with health economic analysis. So far, one-third of the patients expected to participate in the study have been recruited (N = 90, mean age 60, days after stroke >= 30 days). The trial will end in July 2023.; Discussion: We predict an improvement in the patients' recovery, high acceptance, and reduced costs due to a soft landing from the clinic to home rehabilitation. In addition, the data provided will allow us to assess whether the prescription of therapy at home can counteract deterioration and improve quality of life while also identifying new standards for online and remote assessment, diagnostics, and intervention across European hospitals.

JTD Keywords: deep tech, e-health, home treatment, motor recovery, randomized clinical trial, stroke, upper extremities, virtual reality, Deep tech, E-health, Functional recovery, Home treatment, Motor recovery, Randomized clinical trial, Stroke, Upper extremities, Virtual reality, Wearables

Introduction: After a stroke, a wide range of deficits can occur with varying onset latencies. As a result, assessing impairment and recovery are enormous challenges in neurorehabilitation. Although several clinical scales are generally accepted, they are time-consuming, show high inter-rater variability, have low ecological validity, and are vulnerable to biases introduced by compensatory movements and action modifications. Alternative methods need to be developed for efficient and objective assessment. In this study, we explore the potential of computer-based body tracking systems and classification tools to estimate the motor impairment of the more affected arm in stroke patients. Methods: We present a method for estimating clinical scores from movement parameters that are extracted from kinematic data recorded during unsupervised computer-based rehabilitation sessions. We identify a number of kinematic descriptors that characterise the patients' hemiparesis (e.g., movement smoothness, work area), we implement a double-noise model and perform a multivariate regression using clinical data from 98 stroke patients who completed a total of 191 sessions with RGS. Results: Our results reveal a new digital biomarker of arm function, the Total Goal-Directed Movement (TGDM), which relates to the patients work area during the execution of goal-oriented reaching movements. The model's performance to estimate FM-UE scores reaches an accuracy of R-2: 0.38 with an error (sigma: 12.8). Next, we evaluate its reliability (r = 0.89 for test-retest), longitudinal external validity (95% true positive rate), sensitivity, and generalisation to other tasks that involve planar reaching movements (R-2: 0.39). The model achieves comparable accuracy also for the Chedoke Arm and Hand Activity Inventory (R-2: 0.40) and Barthel Index (R-2: 0.35). Conclusions: Our results highlight the clinical value of kinematic data collected during unsupervised goal-oriented motor training with the RGS combined with data science techniques, and provide new insight into factors underlying recovery and its biomarkers.

JTD Keywords: interactive feedback, motion classification, motion sensing, multivariate regression, posture monitoring, rehabilitation, stroke, Adult, Aged, Analytic method, Arm movement, Article, Barthel index, Brain hemorrhage, Cerebrovascular accident, Chedoke arm and hand activity inventory, Clinical protocol, Cognitive defect, Computer analysis, Controlled study, Convergent validity, Correlation coefficient, Disease severity, External validity, Female, Fugl meyer assessment for the upper extremity, Functional assessment, Functional status assessment, General health status assessment, Hemiparesis, Human, Interactive feedback, Ischemic stroke, Kinematics, Major clinical study, Male, Mini mental state examination, Motion classification, Motion sensing, Motor analog scale, Movement, Multivariate regression, Muscle function, Posture monitoring, Probability, Recovery, Rehabilitation, Reliability, Retrospective study, Stroke, Stroke patient, Test retest reliability, Therapy, Total goal directed movement, Upper extremities, Upper limb, Upper-limb, Wolf motor function test