Ivana Milovanović

Classification of walking patterns in Parkinson's disease patients based on inertial sensor data

The gait disturbances in Parkinsons disease (PD) patients occur occasionally and intermittently, appearing in a random, inexplicable manner. These disturbances include festinations, shuffling, and complete freezing of gait (FOG). Alternation of walking pattern decreases the quality of life and may result in falls. In order to recognize disturbances during walking in PD patients, we recorded gait kinematics with wireless inertial measurement system and designed an algorithm for automatic recognition and classification of walking patterns. The algorithm combines a perceptron neural network with simple signal processing and rule-based classification. In parallel, gait was recorded with video camera. Medical experts identified FOG episodes from videos and their results were used for comparison and validation of this method. The summary result shows that the error in recognition and classification of walking patterns is up to 16%.

Principal Component Analysis of Gait Kinematics Data in Acute and Chronic Stroke Patients

We present the joint angles analysis by means of the principal component analysis (PCA). The data from twenty-seven acute and chronic hemiplegic patients were used and compared with data from five healthy subjects. The data were collected during walking along a 10-meter long path. The PCA was applied on a data set consisting of hip, knee, and ankle joint angles of the paretic and the nonparetic leg. The results point to significant differences in joint synergies between the acute and chronic hemiplegic patients that are not revealed when applying typical methods for gait assessment (clinical scores, gait speed, and gait symmetry). The results suggest that the PCA allows classification of the origin for the deficit in the gait when compared to healthy subjects; hence, the most appropriate treatment can be applied in the rehabilitation.

Reproducibility of “BUDA” multisensor system for gait analysis

Gait analysis is important element in therapy and rehabilitation of hemiplegic individuals. We developed a simple, portable sensor system, which can be used for recording of gait signals, as well as for estimation of important gait parameters like joint angles, ground reaction forces, and various temporal parameters. In order to assess robustness of the system in everyday use in different environmental conditions and to see how it reacts to atypical gait patterns, we recorded signals from five healthy and five hemiplegic subjects, repeating the experiment on several consecutive days. We compared angles between adjacent leg segments and used Pearsons correlation coefficient as a measure of similarity. We obtained a high correlation for healthy persons, and a notably smaller correlation for hemiplegics.

Radial Basis Function (RBF) networks for improved gait analysis

The gait analysis is an important component for assessment of rehabilitation of individuals with paralyzed legs. One measure of recovery is the resemblance of muscular activities to patterns characteristic for healthy individuals. We present a method for estimation of muscular activities based on accelerometers, force sensing resistors and Radial Basis Function (RBF) neural networks. This method eliminates the need to record the EMG during walking, being very difficult, especially if electrical stimulation is applied as the orthotic assistive system. The input for the training of RBF network were data from accelerometers and force sensing resistors (FSR), and output data were electromyographic (EMG) activities recorded from major joint flexor and extensor muscles. In order to assess the quality of mapping we used correlation of recorded and RBF predicted EMG signals from data used for training of RBF network, and data not used for training (validation data). The correlations were between 0.9 and 0.94 when network was tested with validation data.

Muscle synergies with Walkaround® postural support vs. “cane/therapist” assistance

BACKGROUND The main clinical measures of walking recovery in stroke patients were compared for training assisted by Walkaround® postural support (WPS) and conventional (CON) support by a cane/therapist. OBJECTIVE We attributed the differences between the trainings to modified muscular synergies that occurred during assistance by WPS. METHODS We studied the muscle activities of the primary knee and ankle joint movers in the paretic and non-paretic legs of sub-acute stroke patients during assisted walking with WPS and CON. Recorded signals were compared to normative data that were recorded during speed-matched gait trials in healthy subjects. The specific measures were the relative contribution of individual muscles, levels of cocontraction, and the timing of the maximum electromyography (EMG) activity during the walking sessions. RESULTS We found that, for most patients, the individual contribution of muscles were more similar to the healthy with the WPS assistance. In parallel, the cocontraction of the rectus femoris muscles in both legs was lower (by up to 39 %) during walking assisted by WPS than by cane/therapist gait support); the results from this case series (10 patients) showed that WPS might be the superior training scheme. CONCLUSIONS These findings indicated that assistance by WPS changed the motor control output relative to CON assistance in most patients.

22. Gait synergies – Clinical measurement of the kinematics and polymyography

increased risk of falls. Dual tasking paradigm relies upon executive function and the ability to divide attention. It has been tested in otherwise healthy older adults as well as in patients diagnosed with different neurodegenerative disorders, mainly Parkinson’s disease (PD). On the other hand, depression is one of the major non-motor symptoms of the PD, and it has been shown that depressed patients score worse on executive function tests. Comparison of gait patterns in depressed and non-depressed PD patients in dual-task conditions and correlation to cognitive tests results shows that stride time was significantly longer and stride time variability was significantly larger in depressed PD patients in repeated measures across different dual task conditions. Also, depressed patients had significantly longer double-support time and shorter swing-time when expressed as a percentage of the cycle time.

Walkaround® Assisted Walking of Stroke Patients

We describe here the differences in kinematics, ground force reactions, and temporal parameters of the gait of stroke patients walking assisted by a walking assist (e.g., cane) or therapist, and supported by a powered walking frame termed Walkaround®. The Walkaround® prevents from falling and supports trunk orientation by means of an ergonomic lumbar belt attached to the rigid wheeled frame by a suspensor system. The term powered relates to the electrical drives on the rear wheels that provide externally controlled mobility. The assessment of walking was done by a wireless system that estimates joint angles and distribution of ground force reactions. Ten stroke patients participated in this study and walked over the level ground over the distance of 6 meters. The Walkaround ® allows significantly faster walking, improves the symmetry, and increases the range of joint angels. The users felt safer and the therapists were relieved from the physical effort of supporting stroke patients when walking within the Walkaround®.