Evaluating Rehabilitation Progress Using Motion Features Identified by Machine Learning.

Evaluating progress throughout a patient's rehabilitation episode is critical for determining the effectiveness of the selected treatments and is an essential ingredient in personalised and evidence-based rehabilitation practice. The evaluation process is complex due to the inherently large human variations in motor recovery and the limitations of commonly used clinical measurement tools. Information recorded during a robot-assisted rehabilitation process can provide an effective means to continuously quantitatively assess movement performance and rehabilitation progress. However, selecting appropriate motion features for rehabilitation evaluation has always been challenging. This paper exploits unsupervised feature learning techniques to reduce the complexity of building the evaluation model of patients' progress. A new feature learning technique is developed to select the most significant features from a large amount of kinematic features measured from robotics, providing clinically useful information to health practitioners with reduction of modeling complexity. A novel indicator that uses monotonicity and trendability is proposed to evaluate kinematic features. The data used to develop the feature selection technique consist of kinematic data from robot-aided rehabilitation for a population of stroke patients. The selected kinematic features allow for human variations across a population of patients as well as over the sequence of rehabilitation sessions. The study is based on data records pertaining to 41 stroke patients using three different robot assisted exercises for upper limb rehabilitation. Consistent with the literature, the results indicate that features based on movement smoothness are the best measures among 17 kinematic features suitable to evaluate rehabilitation progress.

Mindfulness-based interventions for people diagnosed with a current episode of an anxiety or depressive disorder: a meta-analysis of randomised controlled trials.

OBJECTIVE: Mindfulness-based interventions (MBIs) can reduce risk of depressive relapse for people with a history of recurrent depression who are currently well. However, the cognitive, affective and motivational features of depression and anxiety might render MBIs ineffective for people experiencing current symptoms. This paper presents a meta-analysis of randomised controlled trials (RCTs) of MBIs where participants met diagnostic criteria for a current episode of an anxiety or depressive disorder. METHOD: Post-intervention between-group Hedges g effect sizes were calculated using a random effects model. Moderator analyses of primary diagnosis, intervention type and control condition were conducted and publication bias was assessed. RESULTS: Twelve studies met inclusion criteria (n = 578). There were significant post-intervention between-group benefits of MBIs relative to control conditions on primary symptom severity (Hedges g = -0.59, 95% CI = -0.12 to -1.06). Effects were demonstrated for depressive symptom severity (Hedges g = -0.73, 95% CI = -0.09 to -1.36), but not for anxiety symptom severity (Hedges g = -0.55, 95% CI = 0.09 to -1.18), for RCTs with an inactive control (Hedges g = -1.03, 95% CI = -0.40 to -1.66), but not where there was an active control (Hedges g = 0.03, 95% CI = 0.54 to -0.48) and effects were found for MBCT (Hedges g = -0.39, 95% CI = -0.15 to -0.63) but not for MBSR (Hedges g = -0.75, 95% CI = 0.31 to -1.81). CONCLUSIONS: This is the first meta-analysis of RCTs of MBIs where all studies included only participants who were diagnosed with a current episode of a depressive or anxiety disorder. Effects of MBIs on primary symptom severity were found for people with a current depressive disorder and it is recommended that MBIs might be considered as an intervention for this population.