Showing papers by "Paolo Bonato published in 2005"

Advances in wearable technology and applications in physical medicine and rehabilitation.

Abstract: The development of miniature sensors that can be unobtrusively attached to the body or can be part of clothing items, such as sensing elements embedded in the fabric of garments, have opened countless possibilities of monitoring patients in the field over extended periods of time. This is of particular relevance to the practice of physical medicine and rehabilitation. Wearable technology addresses a major question in the management of patients undergoing rehabilitation, i.e. have clinical interventions a significant impact on the real life of patients? Wearable technology allows clinicians to gather data where it matters the most to answer this question, i.e. the home and community settings. Direct observations concerning the impact of clinical interventions on mobility, level of independence, and quality of life can be performed by means of wearable systems. Researchers have focused on three main areas of work to develop tools of clinical interest: 1)the design and implementation of sensors that are minimally obtrusive and reliably record movement or physiological signals, 2)the development of systems that unobtrusively gather data from multiple wearable sensors and deliver this information to clinicians in the way that is most appropriate for each application, and 3)the design and implementation of algorithms to extract clinically relevant information from data recorded using wearable technology. Journal of NeuroEngineering and Rehabilitation has devoted a series of articles to this topic with the objective of offering a description of the state of the art in this research field and pointing to emerging applications that are relevant to the clinical practice in physical medicine and rehabilitation.

A clinical comparison of variable-damping and mechanically passive prosthetic knee devices.

Abstract: Johansson JL, Sherrill DM, Riley PO, Bonato P, Herr H: A clinical comparison of variable-damping and mechanically passive prosthetic knee devices. Am J Phys Med Rehabil 2005;84:563–575.Objective:Although variable-damping knee prostheses offer some improvements over mechanically passive prost

An EMG-position controlled system for an active ankle-foot prosthesis: an initial experimental study

Abstract: Although below-knee prostheses have been commercially available for some time, today's devices are completely passive, and consequently, their mechanical properties remain fixed with walking speed and terrain. To improve the current performance of below-knee prostheses, we study the feasibility of using the amputee's residual limb EMG signals to control the ankle position of an active ankle-foot prosthesis. We propose two control schemes to predict the amputee's intended ankle position: a neural network approach and a muscle model approach. We test these approaches using EMG data measured from an amputee for several target ankle movement patterns. We find that both controllers demonstrate the ability to predict desired ankle movement patterns qualitatively. In the current implementation, the biomimetic EMG-controller demonstrates a smoother and more natural movement pattern than that demonstrated by the neural network approach, suggesting that a biologically-motivated, model-based approach may offer certain advantages in the control of active ankle prostheses.

Using hierarchical clustering methods to classify motor activities of COPD patients from wearable sensor data.

Abstract: Advances in miniature sensor technology have led to the development of wearable systems that allow one to monitor motor activities in the field. A variety of classifiers have been proposed in the past, but little has been done toward developing systematic approaches to assess the feasibility of discriminating the motor tasks of interest and to guide the choice of the classifier architecture. A technique is introduced to address this problem according to a hierarchical framework and its use is demonstrated for the application of detecting motor activities in patients with chronic obstructive pulmonary disease (COPD) undergoing pulmonary rehabilitation. Accelerometers were used to collect data for 10 different classes of activity. Features were extracted to capture essential properties of the data set and reduce the dimensionality of the problem at hand. Cluster measures were utilized to find natural groupings in the data set and then construct a hierarchy of the relationships between clusters to guide the process of merging clusters that are too similar to distinguish reliably. It provides a means to assess whether the benefits of merging for performance of a classifier outweigh the loss of resolution incurred through merging. Analysis of the COPD data set demonstrated that motor tasks related to ambulation can be reliably discriminated from tasks performed in a seated position with the legs in motion or stationary using two features derived from one accelerometer. Classifying motor tasks within the category of activities related to ambulation requires more advanced techniques. While in certain cases all the tasks could be accurately classified, in others merging clusters associated with different motor tasks was necessary. When merging clusters, it was found that the proposed method could lead to more than 12% improvement in classifier accuracy while retaining resolution of 4 tasks. Hierarchical clustering methods are relevant to developing classifiers of motor activities from data recorded using wearable systems. They allow users to assess feasibility of a classification problem and choose architectures that maximize accuracy. By relying on this approach, the clinical importance of discriminating motor tasks can be easily taken into consideration while designing the classifier.

Faces of emotion in human-computer interaction

Abstract: The study of users' emotional behavior in the Human-Computer Interaction (HCI) field has received increasing attention during the last few years. Our work in this area focuses on the relationship between user emotions and perceived usability problems. Specifically, we propose to observe users' spontaneous facial expressions as a method to identify adverse-event occurrences at the user interface level.This paper reports on the results of an experiment designed to investigate the association between adverse-event occurrences during a word processing task and users' facial expressions monitored using electromyogram (EMG) sensor devices. The results suggest that an increase of task difficulty is related to an increase in specific facial muscle activity, thus creating a baseline for future developments using camera-based monitoring of facial activities.

Visual EMG Biofeedback to Improve Ankle Function in Hemiparetic Gait

Abstract: Spasticity in stroke patients interferes with coordinated muscle firing patterns of the lower extremity leading to gait abnormalities. The goal of this study was to improve ankle function during walking by augmenting treadmill gait retraining with a visual EMG biofeedback technique. Eight stroke patients who could ambulate between 0.5 and 0.9 m/s participated in the study. The training consisted of 12 sessions of treadmill walking during which the activity of the tibialis anterior and gastrocnemius lateralis muscles of the affected side was displayed on a computer screen. Targets were shown to indicate to the subject when to activate the monitored muscles. Gait evaluations were performed before and after the training period to test the hypothesis that ankle mechanics improved following the intervention. Improvements in gait function were characterized by changes in temporal gait parameters and lower extremity kinematics and kinetics. Subjects showed an increase in gait speed, time of single leg support on the affected side, ankle power generation at push-off and a reduction in knee extensor moment. These results indicate that treadmill gait retraining augmented via visual EMG-biofeedback facilitates improvements in hemiparetic gait

Quantitative Measures of Functional Upper Limb Movement in Persons after Stroke

Abstract: Stroke disables many older adults each year. This disease impairs the motor functions of survivors, and rehabilitation intervention is a critical part of recovery. Quantitative assessment techniques could be a valuable guide to this intervention. In this study, we propose the use of linear and nonlinear features to assess subjects after a stroke with upper limb motor impairment These features capture differences in accelerometer signals that mark patterns associated with functional movements performed by individuals with different severity of functional limitation and motor impairment. Our results indicate that the severity of functional deficit and motor impairment can be identified by quantifying the accelerometer signals for movements of the arm and hand while performing a functional reaching task

Advanced Analysis of Wearable Sensor Data to Adjust Medication Intake in Patients with Parkinson's Disease

Abstract: The objective of this pilot work is to identify characteristics and measure severity of motor fluctuations in patients with Parkinson's disease (PD) based on wearable sensor data. Improved methods of assessing longitudinal changes in PD would enable optimization of treatment and maximization of patient function. We hypothesize that motor fluctuations accompanying late-stage PD present with predictable features of accelerometer signals recorded during execution of standardized motor tasks. Six patients (age 46-75) with diagnosis of idiopathic PD and levodopa-related motor fluctuations were studied. Subjects performed motor tasks in a "practically-defined OFF" state, and then at 30 minute intervals after medication intake. At each interval, data from 8 uniaxial accelerometers on the upper and lower limbs were recorded continuously, and subjects were videotaped. Features representing motion characteristics such as intensity, rate, regularity, and coordination were derived from the sensor data, and clinical scores were assigned for each task by review of the videotapes. Cluster analysis was performed on feature sets that were expected to reflect severity of parkinsonian symptoms (e.g. bradykinesia) and motor complications (e.g. dyskinesias). Two-dimensional data projections revealed clusters corresponding to the degree of dyskinesia and bradykinesia indicated by clinical scores. These preliminary results support our hypothesis that wearable sensors are sensitive to changing patterns of movement throughout the medication intake cycle, and that automated recognition of motor states using these recordings is feasible