Upper extremity (UE) impairment is a common consequence of stroke, restricting daily activities. Clinical assessments such as the Fugl–Meyer Assessment (FMA) and the Action Research Arm Test (ARAT) are widely used but are typically therapist-administered. Inertial measurement units (IMUs) provide a portable, objective method to quantify upper limb kinematics and may therefore support scalable tele-rehabilitation. Yet, evidence on their reliability, validity, and clinical relevance remains limited. This study evaluated the test–retest reliability, discriminant validity (vs. healthy controls), and convergent validity (correlation with FMA and ARAT) of eleven IMU-derived kinematic metrics during a standardized drinking task in individuals with subacute stroke. Fifteen stroke patients and fifteen healthy controls performed the task wearing four IMUs on the upper limb and sternum. Both joint and end-point kinematics were derived using the Madgwick sensor fusion algorithm. Reliability was assessed through intraclass correlation coefficients (ICCs), discriminant validity through linear mixed models (LMMs), and convergent validity through Pearson’s correlations and regression models. Most metrics showed good to excellent reliability (ICC≥0.75), except for shoulder abduction (ICC=0.18) and maximum elbow angular velocity (ICC=0.65). All but shoulder abduction demonstrated significant discriminant validity. Movement time and measures of smoothness correlated moderately to strongly (r≥.67) with ARAT and FMA. These findings indicate that IMU-derived metrics during a standardized drinking task provide reliable, valid, and clinically meaningful insights into post-stroke motor status, and may offer supplementary information for movement assessment beyond conventional clinical scales.

Home-based rehabilitation is essential for stroke survivors, facilitating motor recovery and improving activities-of-daily-life performance. Recent advances in wearable technologies and machine learning promise to revolutionize home-based arm rehabilitation by providing detailed movement analysis. However, machine learning algorithms for arm movement identification are predominantly trained and tested in the same environments. Their ability to generalize to novel environments remains largely unknown, hindering practical applications. This paper investigates the ability of two established machine learning models to generalize a structured, lab-based environment to a more realistic, semi-structured kitchen environment. Twelve healthy participants performed various arm activities, involving three arm movement types (reaching, lifting, and pronation/supination). In addition to evaluating the generalization of movement identification, we compared algorithm performance for two different sensor configurations: four Inertial Measurement Units (IMUs) on the arm versus a single IMU on the wrist. We employed a Random Forest (RF) classifier and a hybrid deep learning model combining convolutional and recurrent neural networks, evaluating both subject-specific and group approaches. Trained in the structured environment, the RF classifier predicted activities in the semi-structured environment with 86.54% (subject-specific) and 77.37% (group) balanced accuracy, based on the four-sensor configuration, while the hybrid model reached 87.96% and 82.96% accuracy. The accuracy was lower with a single wrist IMU; the RF classifier showed a smaller decrease than the hybrid model. Our findings demonstrate that the investigated arm movement identification algorithms generalize well across environments even with the minimal sensor configuration, indicating the potential for future applications in home-based stroke rehabilitation.

Three-dimensional (3D) cameras used for gait assessment obviate the need for bodily markers or sensors, making them particularly interesting for clinical applications. Due to their limited field of view, their application has predominantly focused on evaluating gait patterns within short walking distances. However, assessment of gait consistency requires testing over a longer walking distance. The aim of this study is to validate the accuracy for gait assessment of a previously developed method that determines walking spatiotemporal parameters and kinematics measured with a 3D camera mounted on a mobile robot base (ROBOGait). Walking parameters measured with this system were compared with measurements with Xsens IMUs. The experiments were performed on a non-linear corridor of approximately 50 m, resembling the environment of a conventional rehabilitation facility. Eleven individuals exhibiting normal motor function were recruited to walk and to simulate gait patterns representative of common neurological conditions: Cerebral Palsy, Multiple Sclerosis, and Cerebellar Ataxia. Generalized estimating equations were used to determine statistical differences between the measurement systems and between walking conditions. When comparing walking parameters between paired measures of the systems, significant differences were found for eight out of 18 descriptors: range of motion (ROM) of trunk and pelvis tilt, maximum knee flexion in loading response, knee position at toe-off, stride length, step time, cadence; and stance duration. When analyzing how ROBOGait can distinguish simulated pathological gait from physiological gait, a mean accuracy of 70.4%, a sensitivity of 49.3%, and a specificity of 74.4% were found when compared with the Xsens system. The most important gait abnormalities related to the clinical conditions were successfully detected by ROBOGait. The descriptors that best distinguished simulated pathological walking from normal walking in both systems were step width and stride length. This study underscores the promising potential of 3D cameras and encourages exploring their use in clinical gait analysis.

Trunk motor control is essential for the proper functioning of the upper extremities and is an important predictor of gait capacity in children with delayed development. Early diagnosis and intervention could increase the trunk motor capabilities in later life, but current tools used to assess the level of trunk motor control are largely subjective and many lack the sensitivity to accurately monitor development and the effects of therapy. Inertial measurement units could yield an objective quantitative assessment that is inexpensive and easy-to-implement. We hypothesized that root mean square of jerk, a proxy for movement smoothness, could be used to distinguish age and thereby presumed motor development. We attached a sensor to the trunks of six young children with no known developmental deficits. Root mean square of jerk decreases with age, up to 24 months, and is correlated to a more established method, i.e., center-of-pressure velocity, as well as other standard inertial measurement unit outputs. This metric therefore shows potential as a method to differentiate trunk motor control levels.