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).

ELOVL6 Genetic Variation Is Related to Insulin Sensitivity: A New Candidate Gene in Energy Metabolism

BACKGROUND: The elongase of long chain fatty acids family 6 (ELOVL6) is an enzyme that specifically catalyzes the elongation of saturated and monounsaturated fatty acids with 12, 14 and 16 carbons. ELOVL6 is expressed in lipogenic tissues and it is regulated by sterol regulatory element binding protein 1 (SREBP-1). OBJECTIVE: We investigated whether ELOVL6 genetic variation is associated with insulin sensitivity in a population from southern Spain. DESIGN: We undertook a prospective, population-based study collecting phenotypic, metabolic, nutritional and genetic information. Measurements were made of weight and height and the body mass index (BMI) was calculated. Insulin resistance was measured by homeostasis model assessment. The type of dietary fat was assessed from samples of cooking oil taken from the participants' kitchens and analyzed by gas chromatography. Five SNPs of the ELOVL6 gene were analyzed by SNPlex. RESULTS: Carriers of the minor alleles of the SNPs rs9997926 and rs6824447 had a lower risk of having high HOMA_IR, whereas carriers of the minor allele rs17041272 had a higher risk of being insulin resistant. An interaction was detected between the rs6824447 polymorphism and the intake of oil in relation with insulin resistance, such that carriers of this minor allele who consumed sunflower oil had lower HOMA_IR than those who did not have this allele (P = 0.001). CONCLUSIONS: Genetic variations in the ELOVL6 gene were associated with insulin sensitivity in this population-based study.

The Endocannabinoid System as Pharmacological Target Derived from Its CNS Role in Energy Homeostasis and Reward. Applications in Eating Disorders and Addiction

The endocannabinoid system (ECS) has been implicated in many physiological functions, including the regulation of appetite, food intake and energy balance, a crucial involvement in brain reward systems and a role in psychophysiological homeostasis (anxiety and stress responses). We first introduce this important regulatory system and chronicle what is known concerning the signal transduction pathways activated upon the binding of endogenous cannabinoid ligands to the Gi/0-coupled CB1 cannabinoid receptor, as well as its interactions with other hormones and neuromodulators which can modify endocannabinoid signaling in the brain. Anorexia nervosa (AN) and bulimia nervosa (BN) are severe and disabling psychiatric disorders, characterized by profound eating and weight alterations and body image disturbances. Since endocannabinoids modulate eating behavior, it is plausible that endocannabinoid genes may contribute to the biological vulnerability to these diseases. We present and discuss data suggesting an impaired endocannabinoid signaling in these eating disorders, including association of endocannabinoid components gene polymorphisms and altered CB1-receptor expression in AN and BN. Then we discuss recent findings that may provide new avenues for the identification of therapeutic strategies based on the endocannabinod system. In relation with its implications as a reward-related system, the endocannabinoid system is not only a target for cannabis but it also shows interactions with other drugs of abuse. On the other hand, there may be also a possibility to point to the ECS as a potential target for treatment of drug-abuse and addiction. Within this framework we will focus on enzymatic machinery involved in endocannabinoid inactivation (notably fatty acid amide hydrolase or FAAH) as a particularly interesting potential target. Since a deregulated endocannabinoid system may be also related to depression, anxiety and pain symptomatology accompanying drug-withdrawal states, this is an area of relevance to also explore adjuvant treatments for improving these adverse emotional reactions.