Mechanical Engineering - Research Publications
Permanent URI for this collection
Search Results
1 - 2 of 2
-
ItemPromoting clinical best practice in a user-centred design study of an upper limb rehabilitation robot(Taylor & Francis, 2021-01-01)Purpose: Despite their promise to increase therapy intensity in neurorehabilitation, robotic devices have not yet seen mainstream adoption. Whilst there are a number of contributing factors, it is obvious that the treating clinician should have a clear understanding of the objectives and limitations of robotic device use. This study sought to explore how devices can be developed to support a clinician in providing clinical best practice. Methods and Materials: A user-centred design study of a robotic device was conducted, involving build-then-use iterations, where successive iterations are built based on feedback from the use cycle. This work reports results of an analysis of qualitative and quantitative data describing the use of the robotic device in the clinical sessions, and from a focus group with the treating clinicians. Results and Conclusions: The data indicated that use of the device did not result in patient goal-setting and may have resulted in poor movement quality. Therapists expected a higher level of autonomy from the robotic device, and this may have contributed to the above problems. These problems can and should be addressed through modification of both the study design and device to provide more explicit instructions to promote clinical best practice. Implications for Rehabilitation: • Encouraging clinical best practice when using evaluating prototype devices within a clinical setting is important to ensure that best practice is maintained - and can be achieved through both study and device design • Support from device developers can significantly improve the confidence of therapists during the use of that device in rehabilitation, particularly with new or prototype devices • End effector-based robotic devices for rehabilitation show potential for a wide variety of patient presentations and capabilities.
-
ItemEvaluating Rehabilitation Progress Using Motion Features Identified by Machine Learning(IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, 2021-04)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.