Cerebrovascular diseases, including stroke, are historically considered diseases of old adults so only in a few studies has “return to work” (RTW) been considered as an index of rehabilitative outcome. At the moment, data on RTW in patients with stroke are highly variable: four different reviews reported the following ranges: 11–85%, 19–73%, 22–53%, and 40–45%. The absence of re-integration to work after a stroke is shown to be associated with an increase of cardiac disorders and depression, with a higher level of mortality, with social isolation and with insufficient adaptive skills. The aim of this study was to verify the effectiveness of technological treatment, performed with optic (SonicHand) and wearable (Riablo™) systems providing auditory and visual biofeedback, on RTW in patients with stroke. RTW was found to be associated with a higher independence in the activities of daily living (assessed by the Modified Barthel Index). No significant differences were found between technological versus conventional rehabilitation in terms of RTW, despite the former showing a higher odds ratio than the latter (OR = 9 vs. 6). Assistive devices were mainly used in patients who had not returned to work. Finally, quality of life was found higher in those patients who returned to work with the same conditions (work duties and time) as before stroke.

No abstract

A potential dramatic effect of long-term disability due to stroke is the inability to return to work. An accurate prognosis and the identification of the parameters inflating the possibility of return to work after neurorehabilitation are crucial. Many factors may influence it, such as mobility and, in particular, walking ability. In this pilot study, two emerging technologies have been combined with the aim of developing a prognostic tool for identifying patients able to return to work: a wearable inertial measurement unit for gait analysis and an artificial neural network (ANN). Compared with more conventional statistics, the ANN showed a higher accuracy in identifying patients with respect to healthy subjects (90.9 vs. 75.8%) and also in identifying the subjects unable to return to work (93.9 vs. 81.8%). In this last analysis, the duration of double support phase resulted the most important input of the ANN. The potentiality of the ANN, developed also in other fields such as marketing on social networks, could allow a powerful support for clinicians that today should manage a large amount of instrumentally recorded parameters in patients with stroke.

Many activities may elicit a biomechanical overload. Among these, lifting loads can cause work-related musculoskeletal disorders. Aspiring to improve risk prevention, the National Institute for Occupational Safety and Health (NIOSH) established a methodology for assessing lifting actions by means of a quantitative method based on intensity, duration, frequency and other geometrical characteristics of lifting. In this paper, we explored the machine learning (ML) feasibility to classify biomechanical risk according to the revised NIOSH lifting equation. Acceleration and angular velocity signals were collected using a wearable sensor during lifting tasks performed by seven subjects and further segmented to extract time-domain features: root mean square, minimum, maximum and standard deviation. The features were fed to several ML algorithms. Interesting results were obtained in terms of evaluation metrics for a binary risk/no-risk classification; specifically, the tree-based algorithms reached accuracies greater than 90% and Area under the Receiver operating curve characteristics curves greater than 0.9. In conclusion, this study indicates the proposed combination of features and algorithms represents a valuable approach to automatically classify work activities in two NIOSH risk groups. These data confirm the potential of this methodology to assess the biomechanical risk to which subjects are exposed during their work activity.

After a stroke event, most survivors suffer from arm paresis, poor motor control and other disabilities that make activities of daily living difficult, severely affecting quality of life and personal independence. This randomized controlled trial aimed at evaluating the efficacy of a music-based sonification approach on upper limbs motor functions, quality of life and pain perceived during rehabilitation. The study involved 65 subacute stroke individuals during inpatient rehabilitation allocated into 2 groups which underwent usual care dayweek) respectively of standard upper extremity motor rehabilitation or upper extremity treatment with sonification techniques. The Fugl-Meyer Upper Extremity Scale, Box and Block Test and the Modified Ashworth Scale were used to perform motor assessment and the McGill Quality of Life-it and the Numerical Pain Rating Scale to assess quality of life and pain. The assessment was performed at baseline, after 2 weeks, at the end of treatment and at follow-up (1 month after the end of treatment). Total scores of the Fugl-Meyer Upper Extremity Scale (primary outcome measure) and hand and wrist sub scores, manual dexterity scores of the affected and unaffected limb in the Box and Block Test, pain scores of the Numerical Pain Rating Scale (secondary outcomes measures) significantly improved in the sonification group compared to the standard of care group (time*group interaction < 0.05). Our findings suggest that music-based sonification sessions can be considered an effective standardized intervention for the upper limb in subacute stroke rehabilitation.