Sensorimotor conflict tests in an immersive virtual environment reveal subclinical impairments in mild traumatic brain injury.

Current clinical tests lack the sensitivity needed for detecting subtle balance impairments associated with mild traumatic brain injury (mTBI). Patient-reported symptoms can be significant and have a huge impact on daily life, but impairments may remain undetected or poorly quantified using clinical measures. Our central hypothesis was that provocative sensorimotor perturbations, delivered in a highly instrumented, immersive virtual environment, would challenge sensory subsystems recruited for balance through conflicting multi-sensory evidence, and therefore reveal that not all subsystems are performing optimally. The results show that, as compared to standard clinical tests, the provocative perturbations illuminate balance impairments in subjects who have had mild traumatic brain injuries. Perturbations delivered while subjects were walking provided greater discriminability (average accuracy ≈ 0.90) than those delivered during standing (average accuracy ≈ 0.65) between mTBI subjects and healthy controls. Of the categories of features extracted to characterize balance, the lower limb accelerometry-based metrics proved to be most informative. Further, in response to perturbations, subjects with an mTBI utilized hip strategies more than ankle strategies to prevent loss of balance and also showed less variability in gait patterns. We have shown that sensorimotor conflicts illuminate otherwise-hidden balance impairments, which can be used to increase the sensitivity of current clinical procedures. This augmentation is vital in order to robustly detect the presence of balance impairments after mTBI and potentially define a phenotype of balance dysfunction that enhances risk of injury.

Monitoring mobility assistive device use in post-stroke patients.

Mobility assistive devices (MAD) such as canes can improve mobility and allow independence in the performance of mobility-related tasks. The use of MAD is often prescribed for stroke survivors. Despite their acknowledged qualities, MAD in real life conditions are typically underutilized, misused and abandoned. Ecologically sound, evidence based outcome measures need to be developed so as to capture the inherent complexities behind real life use of MAD and identify markers and mitigators of a successful integration of MAD into the daily activities of stroke survivors. In this study, we used accelerometers, gyroscopes, and a load cell to identify the task a patient was performing and examine the use of the cane in the context of the task.

Identification of tasks performed by stroke patients using a mobility assistive device.

Many stroke patients are prescribed canes or other mobility assistive devices. Once taken home, these mobility assistive devices are often abandoned or misused. A means for assessing the use of the cane in the home and community settings is required to assist clinicians in the prescription of these devices. In this study, we propose the use of wearable sensors to identify tasks performed by stroke patients with a mobility assistive device. Subjects performed ten tasks with a three-axis accelerometer attached to their ankle and a neural network was trained to identify the task being performed. Results from 15 stroke patients indicated that these motor tasks can be reliably identified with a median sensitivity of 90 % at a median specificity of 95%. These results indicate that it is possible to use a single module with a three-axis accelerometer attached to the ankle to reliably identify motor tasks associated with the use of a cane. Therefore, we envision that the methodology presented in this paper could be used to evaluate the use of a cane in the context of the task being performed.

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

OBJECTIVE: Although variable-damping knee prostheses offer some improvements over mechanically passive prostheses to transfemoral amputees, there is insufficient evidence that such prostheses provide advantages at self-selected walking speeds. In this investigation, we address this question by comparing two variable-damping knees, the hydraulic-based Otto Bock C-leg and the magnetorheological-based Ossur Rheo, with the mechanically passive, hydraulic-based Mauch SNS. DESIGN: For each prosthesis, metabolic data were collected on eight unilateral amputees walking at self-selected speeds across an indoor track. Furthermore, kinetic, kinematic, and electromyographic data were collected while walking at self-selected speeds across a 10-m walkway in a laboratory. RESULTS: When using the Rheo, metabolic rate decreases by 5% compared with the Mauch and by 3% compared with the C-leg. Furthermore, for the C-leg and Rheo knee devices, we observe biomechanical advantages over the mechanically passive Mauch. These advantages include an enhanced smoothness of gait, a decrease in hip work production, a lower peak hip flexion moment at terminal stance, and a reduction in peak hip power generation at toe-off. CONCLUSION: The results of this study indicate that variable-damping knee prostheses offer advantages over mechanically passive designs for unilateral transfemoral amputees walking at self-selected ambulatory speeds, and the results further suggest that a magnetorheological-based system may have advantages over hydraulic-based designs.

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

BACKGROUND: 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. METHODS: 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. RESULTS: 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. CONCLUSION: 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.

Data mining techniques to detect motor fluctuations in Parkinson's disease.

The purpose of this paper is to present preliminary evidence that data mining and artificial intelligence systems may allow one to recognize the presence and severity of motor fluctuations in patients with Parkinson's disease (PD). We hypothesize that movement disorders in late-stage PD present with identifiable and predictable features that can be derived from accelerometer (ACC) and surface electromyographic (EMG) signals recorded during the execution of a standardized set of motor assessment tasks. Although this paper focuses on a specific clinical application requiring advanced analysis techniques, the approach can be generalized to numerous applications in which data mining and other techniques can be used to analyze large data sets derived from wearable sensors.