Gait quality assessment using self-organising artificial neural networks.

In this study, the challenge to maximise the potential of gait analysis by employing advanced methods was addressed by using self-organising neural networks to quantify the deviation of patients' gait from normal. Data including three-dimensional joint angles, moments and powers of the two lower limbs and the pelvis were used to train Kohonen artificial neural networks to learn an abstract definition of normal gait. Subsequently, data from patients with gait problems were presented to the network which quantified the quality of gait in the form of a single curve by calculating the quantisation error during the gait cycle. A sensitivity analysis involving the manipulation of gait variables' weighting was able to highlight specific causes of the deviation including the anatomical location and the timing of wrong gait patterns. Use of the quantisation error can be regarded as an extension of previously described gait indices because it measures the goodness of gait and additionally provides information related to the causes underlying gait deviations.

Visualisation of gait data with Kohonen self-organising neural maps.

Self-organising artificial neural networks were used to reduce the complexity of joint kinematic and kinetic data, which form part of a typical instrumented gait assessment. Three-dimensional joint angles, moments and powers during the gait cycle were projected from the multi-dimensional data space onto a topological neural map, which thereby identified gait stem-patterns. Patients were positioned on the map in relation to each other and this enabled them to be compared from their gait patterns. The visualisation of large amounts of complex data in a two-dimensional map labelled with gait patterns is a step towards more objective analysis protocols which may enhance decision making.

Design features of portable wheelchair ramps and their implications for curb and vehicle access.

This study evaluated a range of portable wheelchair ramps to highlight the effect of different product features on ease of use when wheelchair users climb curbs or access vehicles. Twelve portable ramps were evaluated. Although all the ramps were designed to load powered wheelchairs into motor vehicles, they were manufactured in different designs. The ramps were based on a "singlewide" platform or "channel" design. Some ramps had fixed dimensions, whereas others could be reduced in size because they were telescopic or designed to allow folding. Overall, the ramps could be divided into four subgroups on the basis of their key features. These were horizontally and longitudinally folding ramps, telescopic ramps, and ramps with fixed dimensions. The telescopic ramps could be subdivided into "U"-shaped gutter ramps and reverse profile ramps. Product appraisals and trials involving wheelchair users and caregivers of wheelchair users were done to evaluate each of these ramp designs. Although wheelchair ramps are available in a wide range of designs and configurations, we found that no single ramp design successfully met the needs of all wheelchair users or their caregivers. The evaluation highlighted a number of specific problems and potential hazards. Some ramps were found to move during a maneuver, showed poor stability when used with some vehicles, or were too narrow to allow wheelchair castors to pass through the channel without jamming. Some features, such as handles and locking mechanisms, influenced the ease with which the caregivers could use the ramps. Wheelchair users preferred the wide platform ramps because they were able to drive up these with ease and little preparation. The caregivers preferred folding or telescopic channel ramps because these were easier to handle and store.

Trunk movement in Parkinson's disease during rising from seated position.

Parkinson's disease (PD) is associated with particular difficulties rising from a seated position. Little is known about the mechanisms of sit-to-stand in this condition. We sought to define trunk movement during sit-to-stand in a group of patients with PD. Six patients and seven normal volunteers were studied using a six camera ELITE motion analysis system (BTS, Milan, Italy), which permitted data collection in the coronal, sagittal, and transverse planes. Retroreflective markers were positioned along the spine at C7, T3, T6, T9, T12, L3, and the sacrum. Whole-trunk kinematics and the movement at the six different trunk markers were recorded during rising. PD patients have a significantly greater degree of trunk flexion than controls, showing a significant increase in angular velocity of the trunk in the sagittal plane. The total range of movement of trunk rotation was significantly smaller in the PD group, but lateral movement in the trunk was greater than normal. These data suggest that patients with early PD compensate for their difficulties rising from a chair by generating greater trunk flexion at higher angular velocity, thus developing greater forward momentum. This process results in a decrease in the duration of the unstable transitional phase of sit-to-stand, allowing PD patients to reach the upright position as easily and safely as possible. Small rotational movements are an effective way to maintain the centre of mass within the base of support during sit-to-stand. This mechanism appears to be denied to the PD patients who may use increased movements in the coronal plane as an alternative strategy.