Virulence properties and antimicrobial resistance of Pseudomonas aeruginosa isolated from cave waters at Roraima Tepui, Guayana Highlands.

Pseudomonas aeruginosa is a prominent member of emerging waterborne pathogens. The environmental reservoirs of multi-resistant phenotypes and other virulence factors in this bacterium are poorly understood. Our study aimed to determine the virulence properties of P. aeruginosa isolated from Roraima Sur Cave (RSC) waters at Guayana Highlands. Based on the best identification at species level by biochemical tests, 16S rRNA sequencing and phylogenetic inferences, one RSC isolate named LG11 was characterized for virulence properties in comparison with P. aeruginosa reference strains. PCR amplification of alginate, elastase, exoenzyme S, exotoxin A, neuraminidase and Quorum-Sensing genes showed a high virulence potential in LG11. This isolate demonstrated multi-resistance to ceftriaxone, tigecycline and imipenem. Pyocyanin production was greater in LG11 (0·478 µg ml-1 ) than the strain ATCC 10145 (0·316 µg ml-1 ), but the highest pigment concentration (2·140 µg ml-1 ) was displayed by the clinical strain CVCM 937 (P = 0·000175). Pronounced biomass production on granite and glass (P < 0·05) and well-developed biofilms indicated the ability of P. aeruginosa from RSC to colonize surfaces found in human and healthcare environments. These data suggest that waters from pristine ecosystems such as RSC could be reservoirs of this opportunistic bacterium carrying important virulence properties with potential epidemiological implications. SIGNIFICANCE AND IMPACT OF THE STUDY: This study shows for the first time the occurrence of virulence genes and multi-resistance to antimicrobials in Pseudomonas aeruginosa isolated from cave waters at Guayana Highlands. These findings, together with the biofilm formation on surfaces found in human and healthcare settings, suggest public health risks and the potential of these virulence properties to be transferred from or to native populations in waters. Our results provide important insights to the current knowledge of P. aeruginosa in the environment, setting the basis for future studies driven to assess reservoirs of multi-resistant bacteria and virulence features unknown in pristine ecosystems.

Cognitive and clinical predictors of a long-term course in obsessive compulsive disorder: A machine learning approach in a prospective cohort study.

BACKGROUND: Obsessive compulsive disorder (OCD) is a disabling illness with a chronic course, yet data on long-term outcomes are scarce. This study aimed to examine the long-term course of OCD in patients treated with different approaches (drugs, psychotherapy, and psychosurgery) and to identify predictors of clinical outcome by machine learning. METHOD: We included outpatients with OCD treated at our referral unit. Demographic and neuropsychological data were collected at baseline using standardized instruments. Clinical data were collected at baseline, 12 weeks after starting pharmacological treatment prescribed at study inclusion, and after follow-up. RESULTS: Of the 60 outpatients included, with follow-up data available for 5-17 years (mean = 10.6 years), 40 (67.7 %) were considered non-responders to adequate treatment at the end of the study. The best machine learning model achieved a correlation of 0.63 for predicting the long-term Yale-Brown Obsessive Compulsive Scale (Y-BOCS) score by adding clinical response (to the first pharmacological treatment) to the baseline clinical and neuropsychological characteristics. LIMITATIONS: Our main limitations were the sample size, modest in the context of traditional ML studies, and the sample composition, more representative of rather severe OCD cases than of patients from the general community. CONCLUSIONS: Many patients with OCD showed persistent and disabling symptoms at the end of follow-up despite comprehensive treatment that could include medication, psychotherapy, and psychosurgery. Machine learning algorithms can predict the long-term course of OCD using clinical and cognitive information to optimize treatment options.

An extensive experimental survey of regression methods.

Regression is a very relevant problem in machine learning, with many different available approaches. The current work presents a comparison of a large collection composed by 77 popular regression models which belong to 19 families: linear and generalized linear models, generalized additive models, least squares, projection methods, LASSO and ridge regression, Bayesian models, Gaussian processes, quantile regression, nearest neighbors, regression trees and rules, random forests, bagging and boosting, neural networks, deep learning and support vector regression. These methods are evaluated using all the regression datasets of the UCI machine learning repository (83 datasets), with some exceptions due to technical reasons. The experimental work identifies several outstanding regression models: the M5 rule-based model with corrections based on nearest neighbors (cubist), the gradient boosted machine (gbm), the boosting ensemble of regression trees (bstTree) and the M5 regression tree. Cubist achieves the best squared correlation ( R2) in 15.7% of datasets being very near to it, with difference below 0.2 for 89.1% of datasets, and the median of these differences over the dataset collection is very low (0.0192), compared e.g. to the classical linear regression (0.150). However, cubist is slow and fails in several large datasets, while other similar regression models as M5 never fail and its difference to the best R2 is below 0.2 for 92.8% of datasets. Other well-performing regression models are the committee of neural networks (avNNet), extremely randomized regression trees (extraTrees, which achieves the best R2 in 33.7% of datasets), random forest (rf) and ε-support vector regression (svr), but they are slower and fail in several datasets. The fastest regression model is least angle regression lars, which is 70 and 2,115 times faster than M5 and cubist, respectively. The model which requires least memory is non-negative least squares (nnls), about 2 GB, similarly to cubist, while M5 requires about 8 GB. For 97.6% of datasets there is a regression model among the 10 bests which is very near (difference below 0.1) to the best R2, which increases to 100% allowing differences of 0.2. Therefore, provided that our dataset and model collection are representative enough, the main conclusion of this study is that, for a new regression problem, some model in our top-10 should achieve R2 near to the best attainable for that problem.

A new approach for TU complex characterization.

In this paper, we present a new TU complex detection and characterization algorithm that consists of two stages; the first is a mathematical modeling of the electrocardiographic segment after QRS complex; the second uses classic threshold comparison techniques, over the signal and its first and second derivatives, to determine the significant points of each wave. Later, both T and U waves are morphologically classified. Amongst the principal innovations of this algorithm is the inclusion of U-wave characterization and a mathematical modeling stage, that avoids many of the problems of classic techniques when there is a low signal-to-noise ratio or when wave morphology is atypical. The results of the algorithm validation with the recently appeared QT database are also shown. For T waves these results are better when compared to other existing algorithms. U-wave results cannot be contrasted with other algorithms as, to our knowledge, none are available. Examples showing the causes of principal discrepancies between our algorithm and the QT database annotations are also given, and some ways of attempting to improve and benefit from the proposed algorithm are suggested.

MART: a multichannel ART-based neural network.

This paper describes MART, an ART-based neural network for adaptive classification of multichannel signal patterns without prior supervised learning. Like other ART-based classifiers, MART is especially suitable for situations in which not even the number of pattern categories to be distinguished is known a priori; its novelty lies in its truly multichannel orientation, especially its ability to quantify and take into account during pattern classification the different changing reliability of the individual signal channels. The extent to which this ability can reduce the creation of spurious or duplicate categories (a major problem for ART-based classifiers of noisy signals) is illustrated by evaluation of its performance in classifying QRS complexes in two-channel ECG traces which were taken from the MIT-BIH database and contaminated with noise.