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).

Pandemic influenza control in Europe and the constraints resulting from incoherent public health laws.

Background With the emergence of influenza H1N1v the world is facing its first 21st century global pandemic. Severe Acute Respiratory Syndrome (SARS) and avian influenza H5N1 prompted development of pandemic preparedness plans. National systems of public health law are essential for public health stewardship and for the implementation of public health policy[1]. International coherence will contribute to effective regional and global responses. However little research has been undertaken on how law works as a tool for disease control in Europe. With co-funding from the European Union, we investigated the extent to which laws across Europe support or constrain pandemic preparedness planning, and whether national differences are likely to constrain control efforts. Methods We undertook a survey of national public health laws across 32 European states using a questionnaire designed around a disease scenario based on pandemic influenza. Questionnaire results were reviewed in workshops, analysing how differences between national laws might support or hinder regional responses to pandemic influenza. Respondents examined the impact of national laws on the movements of information, goods, services and people across borders in a time of pandemic, the capacity for surveillance, case detection, case management and community control, the deployment of strategies of prevention, containment, mitigation and recovery and the identification of commonalities and disconnects across states. Results Results of this study show differences across Europe in the extent to which national pandemic policy and pandemic plans have been integrated with public health laws. We found significant differences in legislation and in the legitimacy of strategic plans. States differ in the range and the nature of intervention measures authorized by law, the extent to which borders could be closed to movement of persons and goods during a pandemic, and access to healthcare of non-resident persons. Some states propose use of emergency powers that might potentially override human rights protections while other states propose to limit interventions to those authorized by public health laws. Conclusion These differences could create problems for European strategies if an evolving influenza pandemic results in more serious public health challenges or, indeed, if a novel disease other than influenza emerges with pandemic potential. There is insufficient understanding across Europe of the role and importance of law in pandemic planning. States need to build capacity in public health law to support disease prevention and control policies. Our research suggests that states would welcome further guidance from the EU on management of a pandemic, and guidance to assist in greater commonality of legal approaches across states.

Klebsiella pneumoniae strains producing extended-spectrum beta-lactamases in Spain: microbiological and clinical features.

Extended-spectrum β-lactamases (ESBL) of the CTX-M, SHV, and TEM families were recognized in 76 (67%), 31 (27%), and 6 (5%) isolates, respectively, among 162 ESBL-producing Klebsiella pneumoniae (ESBL-Kp) strains obtained in a multicenter study in Spain. Predisposing factors for ESBL-Kp acquisition included invasive procedures, mechanical ventilation, and previous antimicrobial use.