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).

Diets based on virgin olive oil or fish oil but not on sunflower oil prevent age-related alveolar bone resorption by mitochondrial-related mechanisms.

BACKGROUND/OBJECTIVES Aging enhances frequency of chronic diseases like cardiovascular diseases or periodontitis. Here we reproduced an age-dependent model of the periodontium, a fully physiological approach to periodontal conditions, to evaluate the impact of dietary fat type on gingival tissue of young (6 months old) and old (24 months old) rats. METHODS/FINDINGS Animals were fed life-long on diets based on monounsaturated fatty acids (MUFA) as virgin olive oil, n-6 polyunsaturated fatty acids (n-6PUFA), as sunflower oil, or n-3PUFA, as fish oil. Age-related alveolar bone loss was higher in n-6PUFA fed rats, probably as a consequence of the ablation of the cell capacity to adapt to aging. Gene expression analysis suggests that MUFA or n-3PUFA allowed mitochondria to maintain an adequate turnover through induction of biogenesis, autophagy and the antioxidant systems, and avoiding mitochondrial electron transport system alterations. CONCLUSIONS The main finding is that the enhanced alveolar bone loss associated to age may be targeted by an appropriate dietary treatment. The mechanisms involved in this phenomenon are related with an ablation of the cell capacity to adapt to aging. Thus, MUFA or n-3PUFA might allow mitochondrial maintaining turnover through biogenesis or autophagy. They might also be able to induce the corresponding antioxidant systems to counteract age-related oxidative stress, and do not inhibit mitochondrial electron transport chain. From the nutritional and clinical point of view, it is noteworthy that the potential treatments to attenuate alveolar bone loss (a feature of periodontal disease) associated to age could be similar to some of the proposed for the prevention and treatment of cardiovascular diseases, a group of pathologies recently associated with age-related periodontitis.

Comparison of oxidative stress markers in HIV-infected patients on efavirenz or atazanavir/ritonavir-based therapy.

INTRODUCTION Chronic low-grade inflammation and immune activation may persist in HIV patients despite effective antiretroviral therapy (ART). These abnormalities are associated with increased oxidative stress (OS). Bilirubin (BR) may have a beneficial role in counteracting OS. Atazanavir (ATV) inhibits UGT1A1, thus increasing unconjugated BR levels, a distinctive feature of this drug. We compared changes in OS markers in HIV patients on ATV/r versus efavirenz (EFV)-based first-line therapies. MATERIALS AND METHODS Cohort of the Spanish Research Network (CoRIS) is a multicentre, open, prospective cohort of HIV-infected patients naïve to ART at entry and linked to a biobank. We identified hepatitis C virus/hepatitis B virus (HCV/HBV) negative patients who started first-line ART with either ATV/r or EFV, had a baseline biobank sample and a follow-up sample after at least nine months of ART while maintaining initial regimen and being virologically suppressed. Lipoprotein-associated Phospholipase A2 (Lp-PLA2), Myeloperoxidase (MPO) and Oxidized LDL (OxLDL) were measured in paired samples. Marker values at one year were interpolated from available data. Multiple imputations using chained equations were used to deal with missing values. Change in the OS markers was modelled using multiple linear regressions adjusting for baseline marker values and baseline confounders. Correlations between continuous variables were explored using Pearson's correlation tests. RESULTS 145 patients (97 EFV; 48 ATV/r) were studied. Mean (SD) baseline values for OS markers in EFV and ATV/r groups were: Lp-PLA2 [142.2 (72.8) and 150.1 (92.8) ng/mL], MPO [74.3 (48.2) and 93.9 (64.3) µg/L] and OxLDL [76.3 (52.3) and 82.2 (54.4) µg/L]. After adjustment for baseline variables patients on ATV/r had a significant decrease in Lp-PLA2 (estimated difference -16.3 [CI 95%: -31.4, -1.25; p=0.03]) and a significantly lower increase in OxLDL (estimated difference -21.8 [-38.0, -5.6; p<0.01] relative to those on EFV, whereas no differences in MPO were found. Adjusted changes in BR were significantly higher for the ATV/r group (estimated difference 1.33 [1.03, 1.52; p<0.01]). Changes in BR and changes in OS markers were significantly correlated. CONCLUSIONS In virologically suppressed patients on stable ART, OS was lower in ATV/r-based regimens compared to EFV. We hypothesize these changes could be in part attributable to increased BR plasma levels.