Robust Nonlinear Mapping of Soil Contamination Using Support Regression

Spatial data analysis mapping and visualization is of great importance in various fields: environment, pollution, natural hazards and risks, epidemiology, spatial econometrics, etc. A basic task of spatial mapping is to make predictions based on some empirical data (measurements). A number of state-of-the-art methods can be used for the task: deterministic interpolations, methods of geostatistics: the family of kriging estimators (Deutsch and Journel, 1997), machine learning algorithms such as artificial neural networks (ANN) of different architectures, hybrid ANN-geostatistics models (Kanevski and Maignan, 2004; Kanevski et al., 1996), etc. All the methods mentioned above can be used for solving the problem of spatial data mapping. Environmental empirical data are always contaminated/corrupted by noise, and often with noise of unknown nature. That's one of the reasons why deterministic models can be inconsistent, since they treat the measurements as values of some unknown function that should be interpolated. Kriging estimators treat the measurements as the realization of some spatial randomn process. To obtain the estimation with kriging one has to model the spatial structure of the data: spatial correlation function or (semi-)variogram. This task can be complicated if there is not sufficient number of measurements and variogram is sensitive to outliers and extremes. ANN is a powerful tool, but it also suffers from the number of reasons. of a special type ? multiplayer perceptrons ? are often used as a detrending tool in hybrid (ANN+geostatistics) models (Kanevski and Maignank, 2004). Therefore, development and adaptation of the method that would be nonlinear and robust to noise in measurements, would deal with the small empirical datasets and which has solid mathematical background is of great importance. The present paper deals with such model, based on Statistical Learning Theory (SLT) - Support Vector Regression. SLT is a general mathematical framework devoted to the problem of estimation of the dependencies from empirical data (Hastie et al, 2004; Vapnik, 1998). SLT models for classification - Support Vector Machines - have shown good results on different machine learning tasks. The results of SVM classification of spatial data are also promising (Kanevski et al, 2002). The properties of SVM for regression - Support Vector Regression (SVR) are less studied. First results of the application of SVR for spatial mapping of physical quantities were obtained by the authorsin for mapping of medium porosity (Kanevski et al, 1999), and for mapping of radioactively contaminated territories (Kanevski and Canu, 2000). The present paper is devoted to further understanding of the properties of SVR model for spatial data analysis and mapping. Detailed description of the SVR theory can be found in (Cristianini and Shawe-Taylor, 2000; Smola, 1996) and basic equations for the nonlinear modeling are given in section 2. Section 3 discusses the application of SVR for spatial data mapping on the real case study - soil pollution by Cs137 radionuclide. Section 4 discusses the properties of the modelapplied to noised data or data with outliers.

Prospective study of the barriers to nutritional support in a paediatric intensive care unit : P16

Introduction and aim: Children hospitalised in a paediatric intensive care unit (PICU) are mainly fed by nutritional support (NS) which may often be interrupted. The aims of the study were to verify the relationship between prescribed (PEI) and actual energy intake (AEI) and to identify the reasons for NS interruption. Methods: Prospective study in a PICU. PEI and AEI from day 1 to 15, type of NS (enteral, parenteral, mixed), position of the feeding tube, interruptions in NS and reasons for these were noted. Inter - ruptions were classified in categories of barriers and their frequency and duration were analysed. Results: Fifteen children (24 ± 25.2 months) were studied for 84 days. The NS was exclusively enteral (69%) or mixed (31%). PEI were significantly higher than AEI (54.7 ± 32.9 vs 49.2 ± 33.6 kcal/kg, p = 0.0011). AEI represented 93% of the PEI. Ninety-eight interruptions were noted and lasted 189 h, i.e. 9.4% of the evaluated time. The most frequent barriers were nursing procedures, respiratory physiotherapy and unavailability of intravenous access. The longest were caused by the necessity to stop NS for surgery or diagnostic studies, to treat burns or to carry out medical procedures. Conclusion: AEI in PICU were inferior by 7% to PEI, considerably lower than in adult studies. Making these results available to medical staff for greater anticipation and compensation could reduce NS interruptions. Starving protocols should be reconsidered.

Performance of noninvasive ventilation algorithms on ICU ventilators during pressure support: a clinical study.

To evaluate the impact of noninvasive ventilation (NIV) algorithms available on intensive care unit ventilators on the incidence of patient-ventilator asynchrony in patients receiving NIV for acute respiratory failure. Prospective multicenter randomized cross-over study. Intensive care units in three university hospitals. Patients consecutively admitted to the ICU and treated by NIV with an ICU ventilator were included. Airway pressure, flow and surface diaphragmatic electromyography were recorded continuously during two 30-min periods, with the NIV (NIV+) or without the NIV algorithm (NIV0). Asynchrony events, the asynchrony index (AI) and a specific asynchrony index influenced by leaks (AIleaks) were determined from tracing analysis. Sixty-five patients were included. With and without the NIV algorithm, respectively, auto-triggering was present in 14 (22%) and 10 (15%) patients, ineffective breaths in 15 (23%) and 5 (8%) (p = 0.004), late cycling in 11 (17%) and 5 (8%) (p = 0.003), premature cycling in 22 (34%) and 21 (32%), and double triggering in 3 (5%) and 6 (9%). The mean number of asynchronies influenced by leaks was significantly reduced by the NIV algorithm (p < 0.05). A significant correlation was found between the magnitude of leaks and AIleaks when the NIV algorithm was not activated (p = 0.03). The global AI remained unchanged, mainly because on some ventilators with the NIV algorithm premature cycling occurs. In acute respiratory failure, NIV algorithms provided by ICU ventilators can reduce the incidence of asynchronies because of leaks, thus confirming bench test results, but some of these algorithms can generate premature cycling.

Soins intégrés: comment accompagner un changement de culture [Integrated care: how to support a culture change?].

The primary care center at Lausanne University Hospital trains residents to new models of integrated care. The future GPs discover new forms of collaboration with nurses, pharmacists or social workers. The collaboration model includes seeing patients together or delegating care to other providers, with the aim of improving the efficiency of a patient-centered care approach. The article includes examples of integrated care in consultation for travelers, victims of violence, pharmacist medication adherence counseling, medicosocial team work for alcohol use disorders and nurse practitioners' primary care for asylum seekers.

Personalized drug administrations using Support Vector Machine

The decision-making process regarding drug dose, regularly used in everyday medical practice, is critical to patients' health and recovery. It is a challenging process, especially for a drug with narrow therapeutic ranges, in which a medical doctor decides the quantity (dose amount) and frequency (dose interval) on the basis of a set of available patient features and doctor's clinical experience (a priori adaptation). Computer support in drug dose administration makes the prescription procedure faster, more accurate, objective, and less expensive, with a tendency to reduce the number of invasive procedures. This paper presents an advanced integrated Drug Administration Decision Support System (DADSS) to help clinicians/patients with the dose computing. Based on a support vector machine (SVM) algorithm, enhanced with the random sample consensus technique, this system is able to predict the drug concentration values and computes the ideal dose amount and dose interval for a new patient. With an extension to combine the SVM method and the explicit analytical model, the advanced integrated DADSS system is able to compute drug concentration-to-time curves for a patient under different conditions. A feedback loop is enabled to update the curve with a new measured concentration value to make it more personalized (a posteriori adaptation).

Patient-ventilator asynchrony during noninvasive pressure support ventilation and neurally adjusted ventilatory assist in infants and children.

OBJECTIVES: To document the prevalence of asynchrony events during noninvasive ventilation in pressure support in infants and in children and to compare the results with neurally adjusted ventilatory assist. DESIGN: Prospective randomized cross-over study in children undergoing noninvasive ventilation. SETTING: The study was performed in a PICU. PATIENTS: From 4 weeks to 5 years. INTERVENTIONS: Two consecutive ventilation periods (pressure support and neurally adjusted ventilatory assist) were applied in random order. During pressure support (PS), three levels of expiratory trigger (ETS) setting were compared: initial ETS (PSinit), and ETS value decreased and increased by 15%. Of the three sessions, the period allowing for the lowest number of asynchrony events was defined as PSbest. Neurally adjusted ventilator assist level was adjusted to match the maximum airway pressure during PSinit. Positive end-expiratory pressure was the same during pressure support and neurally adjusted ventilator assist. Asynchrony events, trigger delay, and cycling-off delay were quantified for each period. RESULTS: Six infants and children were studied. Trigger delay was lower with neurally adjusted ventilator assist versus PSinit and PSbest (61 ms [56-79] vs 149 ms [134-180] and 146 ms [101-162]; p = 0.001 and 0.02, respectively). Inspiratory time in excess showed a trend to be shorter during pressure support versus neurally adjusted ventilator assist. Main asynchrony events during PSinit were autotriggering (4.8/min [1.7-12]), ineffective efforts (9.9/min [1.7-18]), and premature cycling (6.3/min [3.2-18.7]). Premature cycling (3.4/min [1.1-7.7]) was less frequent during PSbest versus PSinit (p = 0.059). The asynchrony index was significantly lower during PSbest versus PSinit (40% [28-65] vs 65.5% [42-76], p < 0.001). With neurally adjusted ventilator assist, all types of asynchronies except double triggering were reduced. The asynchrony index was lower with neurally adjusted ventilator assist (2.3% [0.7-5] vs PSinit and PSbest, p < 0.05 for both comparisons). CONCLUSION: Asynchrony events are frequent during noninvasive ventilation with pressure support in infants and in children despite adjusting the cycling-off criterion. Compared with pressure support, neurally adjusted ventilator assist allows improving patient-ventilator synchrony by reducing trigger delay and the number of asynchrony events. Further studies should determine the clinical impact of these findings.