Jaime Prat

Design and test of neural networks and statistical classifiers in computer-aided movement analysis: a case study on gait analysis

OBJECTIVE: To describe the methods for designing and testing diagnostic systems in movement analysis and to verify the clinical usefulness of neural networks and statistical classifiers in a case study. DESIGN: Connectionist and statistical models trained and tested with measured data. BACKGROUND: A basic need in rehabilitation and related fields is to efficiently manage the vast information obtained from a movement analysis laboratory. Many studies have dealt with the interpretation of measured variables in order to correlate objective descriptors to the presence and/or severity of specific neuromusculoskeletal disorders or their consequences. This traditional analytical approach has been complemented in the last decade by new non-linear classification tools called neural networks. METHODS: A gait analysis study on 148 lower limb arthrosis patients and 88 age-matched control subjects. Pathological and healthy gait patterns obtained from force plates wer discriminated by means of multilayer perceptrons and statistical classifiers. RESULTS: Ten input features were enough to train a multilayer perceptron with six hidden neurons. The discrimination rate of the neural net was 80% after cross-validation, significantly higher (P<0.05) than the performance of a Bayes quadratic classifier (about 75%). A great variance due to a small cross-validation set could be demonstrated. CONCLUSIONS: Strict statistical requirements must be observed for designing a neural network. Although these models attain a better performance than conventional statistical approaches, the benefits they bring are sometimes not sufficient to justify their use. Furthermore, clinicians routinely involved in critical decisions may not consider such diagnostic systems reliable enough.

Biomechanical consequences of callus development in Hoffmann, Wagner, Orthofix and Ilizarov external fixators

A theoretical analysis by a finite elements model (FEM) of some external fixators (Hoffmann, Wagner, Orthofix and Ilizarov) was carried out. This study considered a logarithmic progress of callus elastic characteristics. A standard configuration of each fixator was defined where design and application characteristics were modified. A comparison among standard configurations and influence of every variation was made with regard to displacement and load transmission at the fracture site. An experimental evaluation of standard configurations was performed with a testing machine. After experimental validation of the theoretical model was achieved, an application of physiological loads which act on a fractured limb during normal gait was analysed. A minimal contribution from an external fixator to the total rigidity of the bone-callus-fixator system was assessed when a callus showing minimum elastic characteristics had just been established. Insufficient rigidity from the fixation devices to assure an adequate immobilization during the early stages of fracture healing was verified. However, regardless of the external fixator, callus development was the overriding element for the rigidity of the fixator-bone system.

Neck motion patterns in whiplash-associated disorders: Quantifying variability and spontaneity of movement

BACKGROUND whiplash-associated disorders have usually been explored by analyzing changes in the cervical motor system function by means of static variables such as the range of motion, whereas other behavioural features such as speed, variability or smoothness of movement have aroused less interest. METHODS whiplash patients (n=30), control subjects (n=29) and a group of people faking the symptoms of whiplash-associated-disorders (Simulators, n=30) performed a cyclical flexion-extension movement. This movement was recorded by means of video-photogrammetry. The computed variables were: range of motion, maxima angular velocity and acceleration, and two additional variables that quantify the repeatability of a motion and its spontaneity. Two comparisons were made: Control vs. Patients and Patients vs. Simulators. At each comparison we used ANOVA to detect differences between groups and discriminant analysis to evaluate the ability of these variables to classify individuals. FINDINGS comparison between Controls and Patients showed significant reductions in the range of motion, and both the maximum of angular velocity and acceleration in the Patients. The most efficient discriminant model only included the range of motion and maximum angular velocity. Comparison between Patients and Simulators showed a significant reduction in all measured variables in the Simulators. The best classification model was obtained with maximum angular velocity, spontaneity and repeatability of motion. INTERPRETATION our results suggest that the pathological patterns differ from those of Controls in amplitude and speed of motion, but not in repeatability or spontaneity of movement. These variables are especially useful for detecting abnormal movement patterns.

Load transmission through the callus site with external fixation systems: Theoretical and experimental analysis

The fracture callus contribution to the total rigidity of external fixator-fractured bone element was analysed. This study was achieved from both theoretical and experimental perspectives. The theoretical study was done using the finite element method with a three-dimensional model. In this model, both the callus and the development of its elastic characteristics were considered. A series of 38 New Zealand-California white rabbits with tibial fractures treated with some external fixation system was used in this study. Such devices could reproduce either rigid or elastic features. The frame dynamization can be obtained at different fracture healing stages. Animals were classified into four series: (1) rigid fixators, (2) dynamized fixators two weeks after surgery, (3) three weeks after surgery and (4) four weeks after surgery. Tension tests were performed to evaluate callus strength. Theoretical results showed significant levels of callus load transmission (85.5%) when the callus elastic modulus is 1/100 of the elastic modulus of intact bone in an external fixator with rigid features. Experimental analysis of the callus obtained with different external fixator systems did not show differences among them. This fact implies that the immature callus theoretically modelled (E = 100 N mm-2) appears early in the rabbit fracture model (before two weeks, when first dynamization was made), for this reason no differences were found between the two types of treatment (rigid and dynamized systems). This fact questions the reliability of the dynamization process in external fixation of fractures and it implies accurate investigations in the clinical field.

Optimal average path of the instantaneous helical axis in planar motions with one functional degree of freedom

This paper presents a model for determining the path of the instantaneous helical axis (IHA) that optimally represents human planar motions with one functional degree of freedom (fDOF). A human movement is said to have one fDOF when all degrees of freedom (DOFs) are coordinated such that all the kinematic variables can be expressed, across movement repetitions, as functions of only one independent DOF, except for a small natural intercycle variability quantified as lower than a prespecified value. The concept of fDOF allows taking into account that, due to motor coordination, human movements are executed in a repeatable manner. Our method uses the measurement of several repetitions of a given movement to obtain the optimal average IHA path. The starting point is a change of variables, from time to a joint position magnitude (generally an angle). In this way, instead of operating with the time-dependent single-valued trajectory of the successive cycles, our model permits the representation of any motion variable (e.g. positions and their time derivatives) as a cloud of points dependent on the joint angle. This allows the averaging to be performed over the displacements and their derivatives before determining the mean IHA path. We thus avoid the nonlinear magnification of errors and variability inherent in the IHA computation. Moreover, the IHA path can be considered as a geometric attribute of the joint and the type of motion, rather than of each single movement execution. An experiment was performed that show the accuracy and usefulness of the method.

Analysis and Adaptation of Workplaces for People with Cognitive Disabilities Using Software Tools

This paper describes the results of a study in which software tools were used to analyse and adapt workplaces occupied by people with cognitive disabilities. To do this, the work and the workers were evaluated in order to identify the most relevant problems, using the ErgoDis/IBV method. This is a computer software intended for fitting workplaces to people with disabilities. Once evaluated the workplaces, some adaptations were proposed and implemented. One of the main measures adopted was the use of PDAs to help workers in performing their tasks. After the adaptation of the workplaces, an assessment process was carried out to evaluate the adequacy of the executed measures. The results of the study were implemented in a web page in order to provide information about real cases to professionals and users.

Study of the Loss of Thermal Properties of Mountain Boots in an Expedition to Mount Everest

This paper presents the results of the research carried out during the expedition of the Polytechnic University of Valencia (UPV) in the south face of the Mount Everest. The objective of the study was to evaluate the modification of the thermal properties of two mountain boots worn during the expedition. Both boots were tested before and after the expedition using the laboratory Textile Transmission Test (TTT). This test provides information about the global thermal isolation of the footwear, the global water vapour resistance of the footwear, and the water absorption capability. A breathable/waterproof sock is used to study the transport of water. Two different models of boot were worn by the subjects (One of them developed with a high thermal isolation and the other commercial). The hours of use were 175 (60 estimated kilometers) and the mean environmental conditions were, temperature 5°C and humidity 36% RH. The results of the study showed statistically significant differences in the dry thermal insulation and the wet heat exchange, but not in the global water transfer and absorption of the boots. The results of this study show that actually there is a relevant degradation of the thermal properties with use of sport equipment for high altitudes, which can increase injury risk for sportsmen. This highlights the need to advance in the control of performance during the whole life cycle of the equipments for extreme conditions in order to reduce injury risk of on high altitude climbers.

Quantitative assessment of gait deviation. Contribution to the objective measurement of disability

Three biomechanical parameters based on force plate measurements were defined as indicators of gait deviation. Symmetry was specified as the relative difference in stance time and vertical impulse loading between both feet, constancy as the mean S.D. of the force curves for one subject under a specified gait condition and discrepancy as the average difference between the individual gait pattern and the expected force curves, normalised by the value of the S.D. in a control group. One hundred and forty four patients with osteoarthritis (OA) of the lower extremity and 144 control subjects were studied. There were 45 patients with OA of the hip, 54 of the knee and 45 of the ankle and their function was determined using the Harris Hip score, the hospital for special surgery knee score and the Mazur ankle score, respectively. The temporal asymmetry indicator was more sensitive to unilateral joint affliction, whereas the discrepancy indicators were sensitive to the presence of OA. Both correlated with the patients function as measured by the relevant clinical score. A significant increase of gait discrepancy was detected in the arthritis group when patients were asked to walk at faster speeds; whilst walking barefoot led to an unexpected reduction of intra-subject kinetic variability. Our results confirm the validity and usefulness of the gait deviation concept in patients with OA.