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).

El proyecto EMECAS: protocolo del estudio multicéntrico en España de los efectos a corto plazo de la contaminación atmosférica sobre la salud.

The EMECAM Project demonstrated the short-term effect of air pollution on the death rate in 14 cities in Spain throughout the 1990-1995 period. The Spanish Multicentre Study on Health Effects of Air Pollution (EMECAS) is broadening these objectives by incorporating more recent data, information on hospital disease admissions and totaling 16 Spanish cities. This is an ecological time series study in which the response variables are the daily deaths and the emergency hospitalizations due to circulatory system diseases and respiratory diseases among the residents in each city. Pollutants analyses: suspended particles, SO2, NO2, CO and O3. Control variables: meteorological, calendar, seasonality and influenza trend and incidence. Statistical analysis: estimate of the association in each city by means of the construction of generalized additive Poisson regression models and metanalysis for obtaining combined estimators. The EMECAS Project began with the creation of three working groups (Exposure, Epidemiology and Analysis Methodology) which defined the protocol. The average levels of pollutants were below those established under the current regulations for sulfur dioxide, carbon monoxide and ozone. The NO2 and PM10 values were around those established under the regulations (40 mg/m3). This is the first study of the relationship between air pollution and disease rate among one group of Spanish cities. The pollution levels studied are moderate for some pollutants, although for others, especially NO2 and particles, these levels could entail a problem with regard to complying with the regulations in force.