Cross-Validation of Machine Learning Models for the Functional Outcome Prediction after Post-Stroke Robot-Assisted Rehabilitation.

The state of the art is still lacking an extensive analysis of which clinical characteristics are leading to better outcomes after robot-assisted rehabilitation on post-stroke patients. Prognostic machine learning-based models could promote the identification of predictive factors and be exploited as Clinical Decision Support Systems (CDSS). For this reason, the aim of this work was to set the first steps toward the development of a CDSS, by the development of machine learning models for the functional outcome prediction of post-stroke patients after upper-limb robotic rehabilitation. Four different regression algorithms were trained and cross-validated using a nested 5×10-fold cross-validation. The performances of each model on the test set were provided through the Median Average Error (MAE) and interquartile range. Additionally, interpretability analyses were performed, to evaluate the contribution of the features to the prediction. The results on the two best performing models showed a MAE of 13.6 [13.4] and 13.3 [14.8] on the Modified Barthel Index score (MBI). The interpretability analyses highlighted the Fugl-Meyer Assessment, MBI, and age as the most relevant features for the prediction of the outcome. This work showed promising results in terms of outcome prognosis after robot-assisted treatment. Further research should be planned for the development, validation and translation into clinical practice of CDSS in rehabilitation. Clinical relevance- This work establishes the premises for the development of data-driven tools able to support the clinical decision for the selection and optimisation of the robotic rehabilitation treatment.

Effects of Social Distancing on Quality of Life and Emotional-Affective Sphere of Caregivers and Older Patients Hospitalized in Rehabilitation Departments during COVID-19 Quarantine: An Observational Study.

During the COVID-19 emergency, institutional social distancing conditions were established, preventing family and caregivers' access to rehabilitation departments. Our study goal was to assess inpatients' and caregivers' anxiety, depression, and Quality of Life (QoL) during the Italian lockdown due to the pandemic. We investigated anxiety, depression, and QoL in 53 patients and 51 caregivers, using the Beck Anxiety Inventory (BAI), the Beck Depression Inventory-II (BDI-II), and the Short Form 36 Health Survey (SF36). These questionnaires were given to patients after one (T0) and two months (T1) since the hospitalization. The BAI showed that anxiety was moderate for 7.5% of patients and 23.5% of caregivers, and severe for 35.8% of patients and 17.6% of caregivers. The BDI found moderate depression in 11.3% of patients and 15.7% of caregivers, and severe depression in 34.0% of patients and 9.8% of caregivers. Depression was higher in patients than caregivers, while no differences were detected in anxiety. Compared to normative data, patients' QoL declined in all eight SF36 dimensions, while caregivers' QoL declined only in social, emotional, and mental components. Unexpectedly, patients still hospitalized at T1 showed significant improvements in both anxiety and three QoL subscores. These findings emphasize the importance of psychological support for patients and their families.

Age is negatively associated with upper limb recovery after conventional but not robotic rehabilitation in patients with stroke: a secondary analysis of a randomized-controlled trial.

BACKGROUND: There is consistent evidence that robotic rehabilitation is at least as effective as conventional physiotherapy for upper extremity (UE) recovery after stroke, suggesting to focus research on which subgroups of patients may better respond to either intervention. In this study, we evaluated which baseline variables are associated with the response after the two approaches. METHODS: This is a secondary analysis of a randomized-controlled trial comparing robotic and conventional treatment for the UE. After the assigned intervention, changes of the Fugl-Meyer Assessment UE score by ≥ 5 points classified patients as responders to treatment. Variables associated with the response were identified in a univariate analysis. Then, variables independently associated with recovery were investigated, in the whole group, and the two groups separately. RESULTS: A sample of 190 patients was evaluated after the treatment; 121 were responders. Age, baseline impairment, and neglect were significantly associated with worse response to the treatment. Age was the only independently associated variable (OR 0.967, p = 0.023). Considering separately the two interventions, age remained negatively associated with recovery (OR 0.948, p = 0.013) in the conventional group, while none of the variables previously identified were significantly associated with the response to treatment in the robotic group. CONCLUSIONS: We found that, in our sample, age is significantly associated with the outcome after conventional but not robotic UE rehabilitation. Possible explanations may include an enhanced positive attitude of the older patients towards technological training and reduced age-associated fatigue provided by robotic-assisted exercise. The possibly higher challenge proposed by robotic training, unbiased by the negative stereotypes concerning very old patients' expectations and chances to recover, may also explain our findings. TRIAL REGISTRATION NUMBER: NCT02879279.

Upper Limb Robotic Rehabilitation After Stroke: A Multicenter, Randomized Clinical Trial.

BACKGROUND AND PURPOSE: After stroke, only 12% of survivors obtain complete upper limb (UL) functional recovery, while in 30% to 60% UL deficits persist. Despite the complexity of the UL, prior robot-mediated therapy research has used only one robot in comparisons to conventional therapy. We evaluated the efficacy of robotic UL treatment using a set of 4 devices, compared with conventional therapy. METHODS: In a multicenter, randomized controlled trial, 247 subjects with subacute stroke were assigned either to robotic (using a set of 4 devices) or to conventional treatment, each consisting of 30 sessions. Subjects were evaluated before and after treatment, with follow-up assessment after 3 months. The primary outcome measure was change from baseline in the Fugl-Meyer Assessment (FMA) score. Secondary outcome measures were selected to assess motor function, activities, and participation. RESULTS: One hundred ninety subjects completed the posttreatment assessment, with a subset (n = 122) returning for follow-up evaluation. Mean FMA score improvement in the robotic group was 8.50 (confidence interval: 6.82 to 10.17), versus 8.57 (confidence interval: 6.97 to 10.18) in the conventional group, with no significant between-groups difference (adjusted mean difference -0.08, P = 0.948). Both groups also had similar change in secondary measures, except for the Motricity Index, with better results for the robotic group (adjusted mean difference 4.42, P = 0.037). At follow-up, subjects continued to improve with no between-groups differences. DISCUSSION AND CONCLUSIONS: Robotic treatment using a set of 4 devices significantly improved UL motor function, activities, and participation in subjects with subacute stroke to the same extent as a similar amount of conventional therapy. Video Abstract is available for more insights from the authors (see the Video, Supplemental Digital Content 1, available at: http://links.lww.com/JNPT/A291).