Neurally Adjusted Ventilatory Assist (NAVA) improves the matching of diaphragmatic electrical activity and tidal volume in comparison to pressure support (PS) under non invasive ventilation

INTRODUCTION. Patient-ventilator asynchrony is a frequent issue in non invasivemechanical ventilation (NIV) and leaks at the patient-mask interface play a major role in itspathogenesis. NIV algorithms alleviate the deleterious impact of leaks and improve patient-ventilator interaction. Neurally adusted ventilatory assist (NAVA), a neurally triggered modethat avoids interferences between leaks and the usual pneumatic trigger, could further improvepatient-ventilator interaction in NIV patients.OBJECTIVES. To evaluate the feasibility ofNAVAin patients receiving a prophylactic postextubationNIV and to compare the respective impact ofPSVandNAVAwith and withoutNIValgorithm on patient-ventilator interaction.METHODS. Prospective study conducted in 16 beds adult critical care unit (ICU) in a tertiaryuniversity hospital. Over a 2 months period, were included 17 adult medical ICU patientsextubated for less than 2 h and in whom a prophylactic post-extubation NIV was indicated.Patients were randomly mechanically ventilated for 10 min with: PSV without NIV algorithm(PSV-NIV-), PSV with NIV algorithm (PSV-NIV+),NAVAwithout NIV algorithm (NAVANIV-)and NAVA with NIV algorithm (NAVA-NIV+). Breathing pattern descriptors, diaphragmelectrical activity, leaks volume, inspiratory trigger delay (Tdinsp), inspiratory time inexcess (Tiexcess) and the five main asynchronies were quantified. Asynchrony index (AI) andasynchrony index influenced by leaks (AIleaks) were computed.RESULTS. Peak inspiratory pressure and diaphragm electrical activity were similar in thefour conditions. With both PSV and NAVA, NIV algorithm significantly reduced the level ofleak (p\0.01). Tdinsp was not affected by NIV algorithm but was shorter in NAVA than inPSV (p\0.01). Tiexcess was shorter in NAVA and PSV-NIV+ than in PSV-NIV- (p\0.05).The prevalence of double triggering was significantly lower in PSV-NIV+ than in NAVANIV+.As compared to PSV,NAVAsignificantly reduced the prevalence of premature cyclingand late cycling while NIV algorithm did not influenced premature cycling. AI was not affectedby NIV algorithm but was significantly lower in NAVA than in PSV (p\0.05). AIleaks wasquasi null with NAVA and significantly lower than in PSV (p\0.05).CONCLUSIONS. NAVA is feasible in patients receiving a post-extubation prophylacticNIV. NAVA and NIV improve patient-ventilator synchrony in different manners. NAVANIV+offers the best patient-ventilator interaction. Clinical studies are required to assess thepotential clinical benefit of NAVA in patients receiving NIV.

Multi-scale support vector algorithms for hot spot detection and modelling

The algorithmic approach to data modelling has developed rapidly these last years, in particular methods based on data mining and machine learning have been used in a growing number of applications. These methods follow a data-driven methodology, aiming at providing the best possible generalization and predictive abilities instead of concentrating on the properties of the data model. One of the most successful groups of such methods is known as Support Vector algorithms. Following the fruitful developments in applying Support Vector algorithms to spatial data, this paper introduces a new extension of the traditional support vector regression (SVR) algorithm. This extension allows for the simultaneous modelling of environmental data at several spatial scales. The joint influence of environmental processes presenting different patterns at different scales is here learned automatically from data, providing the optimum mixture of short and large-scale models. The method is adaptive to the spatial scale of the data. With this advantage, it can provide efficient means to model local anomalies that may typically arise in situations at an early phase of an environmental emergency. However, the proposed approach still requires some prior knowledge on the possible existence of such short-scale patterns. This is a possible limitation of the method for its implementation in early warning systems. The purpose of this paper is to present the multi-scale SVR model and to illustrate its use with an application to the mapping of Cs137 activity given the measurements taken in the region of Briansk following the Chernobyl accident.

NAVA enhances tidal volume and diaphragmatic electro-myographic activity matching: a Range90 analysis of supply and demand.

Neurally adjusted ventilatory assist (NAVA) is a ventilation assist mode that delivers pressure in proportionality to electrical activity of the diaphragm (Eadi). Compared to pressure support ventilation (PS), it improves patient-ventilator synchrony and should allow a better expression of patient's intrinsic respiratory variability. We hypothesize that NAVA provides better matching in ventilator tidal volume (Vt) to patients inspiratory demand. 22 patients with acute respiratory failure, ventilated with PS were included in the study. A comparative study was carried out between PS and NAVA, with NAVA gain ensuring the same peak airway pressure as PS. Robust coefficients of variation (CVR) for Eadi and Vt were compared for each mode. The integral of Eadi (ʃEadi) was used to represent patient's inspiratory demand. To evaluate tidal volume and patient's demand matching, Range90 = 5-95 % range of the Vt/ʃEadi ratio was calculated, to normalize and compare differences in demand within and between patients and modes. In this study, peak Eadi and ʃEadi are correlated with median correlation of coefficients, R > 0.95. Median ʃEadi, Vt, neural inspiratory time (Ti_ ( Neural )), inspiratory time (Ti) and peak inspiratory pressure (PIP) were similar in PS and NAVA. However, it was found that individual patients have higher or smaller ʃEadi, Vt, Ti_ ( Neural ), Ti and PIP. CVR analysis showed greater Vt variability for NAVA (p < 0.005). Range90 was lower for NAVA than PS for 21 of 22 patients. NAVA provided better matching of Vt to ʃEadi for 21 of 22 patients, and provided greater variability Vt. These results were achieved regardless of differences in ventilatory demand (Eadi) between patients and modes.

Local adaptation and matching habitat choice in female barn owls with respect to melanic coloration.

Local adaptation is a major mechanism underlying the maintenance of phenotypic variation in spatially heterogeneous environments. In the barn owl (Tyto alba), dark and pale reddish-pheomelanic individuals are adapted to conditions prevailing in northern and southern Europe, respectively. Using a long-term dataset from Central Europe, we report results consistent with the hypothesis that the different pheomelanic phenotypes are adapted to specific local conditions in females, but not in males. Compared to whitish females, reddish females bred in sites surrounded by more arable fields and less forests. Colour-dependent habitat choice was apparently beneficial. First, whitish females produced more fledglings when breeding in wooded areas, whereas reddish females when breeding in sites with more arable fields. Second, cross-fostering experiments showed that female nestlings grew wings more rapidly when both their foster and biological mothers were of similar colour. The latter result suggests that mothers should particularly produce daughters in environments that best match their own coloration. Accordingly, whiter females produced fewer daughters in territories with more arable fields. In conclusion, females displaying alternative melanic phenotypes bred in habitats providing them with the highest fitness benefits. Although small in magnitude, matching habitat selection and local adaptation may help maintain variation in pheomelanin coloration in the barn owl.

A Survey of Active Learning Algorithms for Supervised Remote Sensing Image Classification

Defining an efficient training set is one of the most delicate phases for the success of remote sensing image classification routines. The complexity of the problem, the limited temporal and financial resources, as well as the high intraclass variance can make an algorithm fail if it is trained with a suboptimal dataset. Active learning aims at building efficient training sets by iteratively improving the model performance through sampling. A user-defined heuristic ranks the unlabeled pixels according to a function of the uncertainty of their class membership and then the user is asked to provide labels for the most uncertain pixels. This paper reviews and tests the main families of active learning algorithms: committee, large margin, and posterior probability-based. For each of them, the most recent advances in the remote sensing community are discussed and some heuristics are detailed and tested. Several challenging remote sensing scenarios are considered, including very high spatial resolution and hyperspectral image classification. Finally, guidelines for choosing the good architecture are provided for new and/or unexperienced user.

Structural prediction of peptides bound to MHC class I.

An ab initio structure prediction approach adapted to the peptide-major histocompatibility complex (MHC) class I system is presented. Based on structure comparisons of a large set of peptide-MHC class I complexes, a molecular dynamics protocol is proposed using simulated annealing (SA) cycles to sample the conformational space of the peptide in its fixed MHC environment. A set of 14 peptide-human leukocyte antigen (HLA) A0201 and 27 peptide-non-HLA A0201 complexes for which X-ray structures are available is used to test the accuracy of the prediction method. For each complex, 1000 peptide conformers are obtained from the SA sampling. A graph theory clustering algorithm based on heavy atom root-mean-square deviation (RMSD) values is applied to the sampled conformers. The clusters are ranked using cluster size, mean effective or conformational free energies, with solvation free energies computed using Generalized Born MV 2 (GB-MV2) and Poisson-Boltzmann (PB) continuum models. The final conformation is chosen as the center of the best-ranked cluster. With conformational free energies, the overall prediction success is 83% using a 1.00 Angstroms crystal RMSD criterion for main-chain atoms, and 76% using a 1.50 Angstroms RMSD criterion for heavy atoms. The prediction success is even higher for the set of 14 peptide-HLA A0201 complexes: 100% of the peptides have main-chain RMSD values &lt; or =1.00 Angstroms and 93% of the peptides have heavy atom RMSD values &lt; or =1.50 Angstroms. This structure prediction method can be applied to complexes of natural or modified antigenic peptides in their MHC environment with the aim to perform rational structure-based optimizations of tumor vaccines.

Extreme Precipitation Modelling Using Geostatistics and Machine Learning Algorithms

The paper presents an approach for mapping of precipitation data. The main goal is to perform spatial predictions and simulations of precipitation fields using geostatistical methods (ordinary kriging, kriging with external drift) as well as machine learning algorithms (neural networks). More practically, the objective is to reproduce simultaneously both the spatial patterns and the extreme values. This objective is best reached by models integrating geostatistics and machine learning algorithms. To demonstrate how such models work, two case studies have been considered: first, a 2-day accumulation of heavy precipitation and second, a 6-day accumulation of extreme orographic precipitation. The first example is used to compare the performance of two optimization algorithms (conjugate gradients and Levenberg-Marquardt) of a neural network for the reproduction of extreme values. Hybrid models, which combine geostatistical and machine learning algorithms, are also treated in this context. The second dataset is used to analyze the contribution of radar Doppler imagery when used as external drift or as input in the models (kriging with external drift and neural networks). Model assessment is carried out by comparing independent validation errors as well as analyzing data patterns.

Machine learning algorithms for spatial data. Case studies: Environmental pollution, natural hazards, renewable resources

This paper presents general problems and approaches for the spatial data analysis using machine learning algorithms. Machine learning is a very powerful approach to adaptive data analysis, modelling and visualisation. The key feature of the machine learning algorithms is that they learn from empirical data and can be used in cases when the modelled environmental phenomena are hidden, nonlinear, noisy and highly variable in space and in time. Most of the machines learning algorithms are universal and adaptive modelling tools developed to solve basic problems of learning from data: classification/pattern recognition, regression/mapping and probability density modelling. In the present report some of the widely used machine learning algorithms, namely artificial neural networks (ANN) of different architectures and Support Vector Machines (SVM), are adapted to the problems of the analysis and modelling of geo-spatial data. Machine learning algorithms have an important advantage over traditional models of spatial statistics when problems are considered in a high dimensional geo-feature spaces, when the dimension of space exceeds 5. Such features are usually generated, for example, from digital elevation models, remote sensing images, etc. An important extension of models concerns considering of real space constrains like geomorphology, networks, and other natural structures. Recent developments in semi-supervised learning can improve modelling of environmental phenomena taking into account on geo-manifolds. An important part of the study deals with the analysis of relevant variables and models' inputs. This problem is approached by using different feature selection/feature extraction nonlinear tools. To demonstrate the application of machine learning algorithms several interesting case studies are considered: digital soil mapping using SVM, automatic mapping of soil and water system pollution using ANN; natural hazards risk analysis (avalanches, landslides), assessments of renewable resources (wind fields) with SVM and ANN models, etc. The dimensionality of spaces considered varies from 2 to more than 30. Figures 1, 2, 3 demonstrate some results of the studies and their outputs. Finally, the results of environmental mapping are discussed and compared with traditional models of geostatistics.