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).

Recommendations of the GARIN group for managing non-critically ill patients with diabetes or stress hyperglycaemia and artificial nutrition.

BACKGROUND & AIMS By means of this update, the GARIN working group aims to define its position regarding the treatment of patients with diabetes or stress hyperglycaemia and artificial nutrition. In this area there are many aspects of uncertainty, especially in non-critically ill patients. METHODS Bibliographical review, and specific questions in advance were discussed and answered at a meeting in the form of conclusions. RESULTS We propose a definition of stress hyperglycaemia. The indications and access routes for artificial nutrition are no different in patients with diabetes/stress hyperglycaemia than in non-diabetics. The objective must be to keep pre-prandial blood glucose levels between 100 and 140 mg/dl and post-prandial levels between 140 and 180 mg/dl. Hyperglycemia can be prevented through systematic monitoring of capillary glycaemias and adequately calculate energy-protein needs. We recommend using enteral formulas designed for patients with diabetes (high monounsaturated fat) to facilitate metabolic control. The best drug treatment for treating hyperglycaemia/diabetes in hospitalised patients is insulin and we make recommendations for adapt the theoretical insulin action to the nutrition infusion regimen. We also addressed recommendations for future investigation. CONCLUSIONS This recommendations about artificial nutrition in patients with diabetes or stress hyperglycaemia can add value to clinical work.

Nutrición parenteral domiciliaria en España 2011 y 2012: informe del grupo de nutrición artificial domiciliaria y ambulatoria NADYA

OBJETIVE: To report the data of the Home Parenteral Nutrition (HPN) registry of the NADYA-SENPE working group for the years 2011 and 2012. METHODOLOGY: We compiled the data from the on-line registry introduced by reviewers of NADYA group responsible for monitoring of NPD introduced by since January 1, 2011 to december 31, 2012. Included fields were: age, sex, diagnosis and reason for HPN, access path, complications, beginning and end dates, complementary oral or enteral nutrition, activity level, autonomy degree, product and fungible material supply, withdrawal reason and intestinal transplant indication. RESULTS: Year 2010: 184 patients from 29 hospitals , representing a rate of 3.98 patients/million inhabitants/ year 2011, with 186 episodes were recorded NPD . During 2012, 203 patients from 29 hospitals , representing a rate of 4.39 patients/million inhabitants/year 2012 , a total of 211 episodes were recorded NPD . CONCLUSIONS: We observe an increase in registered patients with respect to previous years.Neoplasia remains as the main pathology since 2003. Although NADYA is consolidated registry and has been indispensable source of information relevant to the understanding of the progress of Home Artificial Nutrition in our country, there is ample room for improvement. Especially that refers to the registration of pediatric patients and the registration of complications.