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).

Clinical and epidemiological features and prognosis of complicated pyelonephritis: a prospective observational single hospital-based study.

BACKGROUND Complicated pyelonephritis (cPN), a common cause of hospital admission, is still a poorly-understood entity given the difficulty involved in its correct definition. The aim of this study was to analyze the main epidemiological, clinical, and microbiological characteristics of cPN and its prognosis in a large cohort of patients with cPN. METHODS We conducted a prospective, observational study including 1325 consecutive patients older than 14 years diagnosed with cPN and admitted to a tertiary university hospital between 1997-2013. After analyzing the main demographic, clinical and microbiological data, covariates found to be associated with attributable mortality in univariate analysis were included in a multivariate logistic regression model. RESULTS Of the 1325 patients, 689 (52%) were men and 636 (48%) women; median age 63 years, interquartile range [IQR] (46.5-73). Nine hundred and forty patients (70.9%) had functional or structural abnormalities in the urinary tract, 215 (16.2%) were immunocompromised, 152 (11.5%) had undergone a previous urinary tract instrumentation, and 196 (14.8%) had a long-term bladder catheter, nephrostomy tube or ureteral catheter. Urine culture was positive in 813 (67.7%) of the 1251 patients in whom it was done, and in the 1032 patients who had a blood culture, 366 (34%) had bacteraemia. Escherichia coli was the causative agent in 615 episodes (67%), Klebsiella spp in 73 (7.9%) and Proteus ssp in 61 (6.6%). Fourteen point one percent of GNB isolates were ESBL producers. In total, 343 patients (25.9%) developed severe sepsis and 165 (12.5%) septic shock. Crude mortality was 6.5% and attributable mortality was 4.1%. Multivariate analysis showed that an age >75 years (OR 2.77; 95% CI, 1.35-5.68), immunosuppression (OR 3.14; 95% CI, 1.47-6.70), and septic shock (OR 58.49; 95% CI, 26.6-128.5) were independently associated with attributable mortality. CONCLUSIONS cPN generates a high morbidity and mortality and likely a great consumption of healthcare resources. This study highlights the factors directly associated with mortality, though further studies are needed in the near future aimed at identifying subgroups of low-risk patients susceptible to outpatient management.