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).

Estudio comparativo del estatus clínico-nutricional en mujeres obesas posmenopáusicas incluídas en un programa de pérdida de peso basado en platos preparados.

INTRODUCTION Few studies have evaluated the efficacy and reliability of weight loss-focussed prepared food dishes in obese post-menopausal women. OBJECTIVE To compare the efficacy of a weight loss programme based on a balanced hypocaloric diet using prepared dishes* with that of a similar programme based on standard commercially available foods and with a non-intervened control group. A further aim was to evaluate the subjectivity of participants in the preparation of the diet-adjusted dishes based on usually consumed products. SUBJECTS Obese post-menopausal women aged between 55 and 65 years. DESIGN Controlled longitudinal interventional study. METHOD The sample of 75 female volunteers were divided into three groups of 25 women: a control group, who continued to consume their usual non-dietary adjusted meals (CG), an intervened group, treated with a diet adjusted to their individual requirements and based on standard commercially available food (SG), and another intervened group, treated with a similarly adjusted diet but based on prepared dishes (PG). Data were gathered on anthropometric variables, consumption habits and physical activity levels, and clinical-nutritional controls were conducted at the start and every two weeks to the end of the 8-week study in order to evaluate biochemical changes. RESULTS The weight loss was slightly higher in the prepared-dishes group (PG) than in the standard food diet group (SG), but the difference was not statistically significant, whereas it was considerably higher in both groups than in the non-dietary adjusted control group (CG) and this difference was highly significant (losses of 7.60 kg in PG and 7.01 kg in SG versus 2.10 kg in CG (p < 0.01). However, the PG showed a significantly higher (p < 0.01) loss of fatty mass and abdominal circumference versus the SG women. CONCLUSION More weight was lost by the two groups treated with a diet based on prepared dishes or usual food items in comparison to untreated controls, but the diet based on prepared dishes obtained more reliable and higher quality outcomes, achieving a positive change at fatty compartment level and in the abdominal circumference.