R. Bravo

Novel approach for spastic hemiplegia classification through the use of support vector machines

The use of computer based classification methods for spastic hemiplegia (SH) is a relatively new approach. Before and still, the classification is primarily done by specialized physicians through manual template matching on kinematics plots of the sagittal plane data from the affected limb generated by gait laboratories. In the past, several methods for computer based automation of this classification have been attempted. This paper introduces the use of support vector machine (SVM) as a model that contributes to this process. The results obtained from the use of SVM are quite efficient considering the data set utilized involves patients from an array of ages and both sex. It should be mentioned that even though the number of patients is not trivial; the percentages of accurate classification represented are promising. Since the SVM method improves its accuracy with an increased number of training cases, this approach has the advantage of becoming more accurate with time. Many more significant discoveries are expect from the introduction of SVM in the analysis of SH and further studies of gait related pathologies are expected to contribute as well.

Classification of normal and His bundle branch block subjects in Chagas myocarditis using P-R segment features analysis

It has been already reported that a large number of patients suffering Chagasic myocarditis show left and/or right His bundle blocks (HBB) due to a deterioration of A-V conduction during the chronic stage of the disease. His-Purkinje activity can be observed in the P-R segment as high frequency activity at the end of the P wave (P), in the the averaged and filtered high resolution ECG signal. In this work, in the P-R segment, temporal and energetic features were measured as a way to determine the conditions of the His-Purkinje system. P activity was observed and delimited for normal and chagasic subjects on averaged and high pass filtered XYZ recordings. Time intervals, means and RMS values were calculated and used as input features of a classification and neural-net based decision map generating algorithm. Mean and RMS value of the signal in most of the subintervals where greater in normals. Energetic parameters where the most significant ones in terms of differentiation between normals and chagasic. The proposed analysis could lead to the development of a non-invasive and low cost methodology for the early detection of A-V conduction problems in Chagas disease.

Physiologic analysis of breathing signals of cerebral palsy characterization

This work covers a physiologic analysis of breathing signals of patients with Cerebral Palsy (CP), to verify and to upgrade the reported definition of the breathing indicators (Velocity, Expenditure and Energy Cost) of the mentioned pathology. This development is obtained according to the surrounding patient environment, and before the creation and implementation of the Cerebral Palsy and Energy Protocol (CPEP), for the acquisition of records adapted to the neuromuscular deficiency. This work includes the design and development of a breathing database that feeds an interface that allows the visualization of the physical parameters of a patient and their respective signals, such as Rf: Breathing frequency; GE: Energy Expenditure; CE: Energy Cost; VE: Ventilation; VO/sub 2/: Oxygen Consumption; VCO/sub 2/: CO/sub 2/ Transportation; Ti, Te, Ttot, Ti/Ttot: Breathing Times; VD: Dead volume; VT: Total volume and V: Gait velocity.