Estadística hospitalaria andaluza : (E.E.S.R.I.) : [estadística de establecimientos sanitarios con régimen de internado : 1999]

Datos a 31 de diciembre del año 1999. Publicado en la página web de la Consejería de Salud: www.juntadeandalucia.es/salud (Consejería de Salud / Profesionales / Estadísticas Sanitarias / Estadísticas Hospitalarias / Estadísticas Hospitalarias de Andalucía

El proyecto EMECAM: Estudio Multicéntrico Español sobre la Relación entre la Contaminación Atmosférica y la Mortalidad. Antecedentes, participantes, objetivos y métodología.

In recent years, a growing number of studies suggests that increases in air pollution levels may have short-term impact on human health, even at pollution levels similar to or lower than those which have been considered to be safe to date. The different methodological approaches and the varying analysis techniques employed have made it difficult to make a direct comparison among all of the findings, preventing any clear conclusions from being drawn. This has led to multicenter projects such as the APHEA (Short-Term Impact of Air Pollution on Health. A European Approach) within a European Scope. The EMECAM Project falls within the context of the aforesaid multicenter studies and has a wide-ranging projection nationwide within Spain. Fourteen (14) cities throughout Spain were included in this Project (Barcelona, Metropolitan Area of Bilbao, Cartagena, Castellón, Gijón, Huelva, Madrid, Pamplona, Seville, Oviedo, Valencia, Vigo, Vitoria and Saragossa) representing different sociodemographic, climate and environmental situations, adding up to a total of nearly nine million inhabitants. The objective of the EMECAM project is that to asses the short-term impact of air pollution throughout all of the participating cities on the mortality for all causes, on the population and on individuals over age 70, for respiratory and cardiovascular design causes. For this purpose, with an ecological, the time series data analyzed taking the daily deaths, pollutants, temperature data and other factors taken from records kept by public institutions. The period of time throughout which this study was conducted, although not exactly the same for all of the cities involved, runs in all cases from 1990 to 1996. The degree of relationship measured by means of an autoregressive Poisson regression. In the future, the results of each city will be combined by means of a meta-analysis.

Interrupción voluntaria del embarazo : Andalucía 1997 : evolución de la incidencia de I.V.E. 1991-1998 : distribución de las I.V.E. en los distritos sanitarios 1998

En port.: Unidad Estadística. Publicado en la página web de la Consejería de Salud: www.juntadeandalucia.es/salud (Consejería de Salud / Profesionales / Estadísticas Sanitarias / Estadísticas de interrupción voluntaria del embarazo > Acceso a las Estadisticas de Interrupción Voluntaria del Embarazo)

Estadísticas vitales, distribución espacial y tendencia de la mortalidad por cáncer y otras causas : Andalucía, 1976-1996

En port.: Unidad Estadística

Interrupción voluntaria del embarazo : Andalucía 1996 : evolución de la incidencia de I.V.E. : años 1991-1997 : (1997 datos provisionales]

En port.: Unidad Estadística

Effective diagnosis of Alzheimer's disease by means of large margin-based methodology.

BACKGROUND Functional brain images such as Single-Photon Emission Computed Tomography (SPECT) and Positron Emission Tomography (PET) have been widely used to guide the clinicians in the Alzheimer's Disease (AD) diagnosis. However, the subjectivity involved in their evaluation has favoured the development of Computer Aided Diagnosis (CAD) Systems. METHODS It is proposed a novel combination of feature extraction techniques to improve the diagnosis of AD. Firstly, Regions of Interest (ROIs) are selected by means of a t-test carried out on 3D Normalised Mean Square Error (NMSE) features restricted to be located within a predefined brain activation mask. In order to address the small sample-size problem, the dimension of the feature space was further reduced by: Large Margin Nearest Neighbours using a rectangular matrix (LMNN-RECT), Principal Component Analysis (PCA) or Partial Least Squares (PLS) (the two latter also analysed with a LMNN transformation). Regarding the classifiers, kernel Support Vector Machines (SVMs) and LMNN using Euclidean, Mahalanobis and Energy-based metrics were compared. RESULTS Several experiments were conducted in order to evaluate the proposed LMNN-based feature extraction algorithms and its benefits as: i) linear transformation of the PLS or PCA reduced data, ii) feature reduction technique, and iii) classifier (with Euclidean, Mahalanobis or Energy-based methodology). The system was evaluated by means of k-fold cross-validation yielding accuracy, sensitivity and specificity values of 92.78%, 91.07% and 95.12% (for SPECT) and 90.67%, 88% and 93.33% (for PET), respectively, when a NMSE-PLS-LMNN feature extraction method was used in combination with a SVM classifier, thus outperforming recently reported baseline methods. CONCLUSIONS All the proposed methods turned out to be a valid solution for the presented problem. One of the advances is the robustness of the LMNN algorithm that not only provides higher separation rate between the classes but it also makes (in combination with NMSE and PLS) this rate variation more stable. In addition, their generalization ability is another advance since several experiments were performed on two image modalities (SPECT and PET).