RESUMO
Numerical weather prediction ensembles are routinely used for operational weather forecasting. The members of these ensembles are individual simulations with either slightly perturbed initial conditions or different model parameterizations, or occasionally both. Multi-member ensemble output is usually large, multivariate, and challenging to interpret interactively. Forecast meteorologists are interested in understanding the uncertainties associated with numerical weather prediction; specifically variability between the ensemble members. Currently, visualization of ensemble members is mostly accomplished through spaghetti plots of a single mid-troposphere pressure surface height contour. In order to explore new uncertainty visualization methods, the Weather Research and Forecasting (WRF) model was used to create a 48-hour, 18 member parameterization ensemble of the 13 March 1993 "Superstorm". A tool was designed to interactively explore the ensemble uncertainty of three important weather variables: water-vapor mixing ratio, perturbation potential temperature, and perturbation pressure. Uncertainty was quantified using individual ensemble member standard deviation, inter-quartile range, and the width of the 95% confidence interval. Bootstrapping was employed to overcome the dependence on normality in the uncertainty metrics. A coordinated view of ribbon and glyph-based uncertainty visualization, spaghetti plots, iso-pressure colormaps, and data transect plots was provided to two meteorologists for expert evaluation. They found it useful in assessing uncertainty in the data, especially in finding outliers in the ensemble run and therefore avoiding the WRF parameterizations that lead to these outliers. Additionally, the meteorologists could identify spatial regions where the uncertainty was significantly high, allowing for identification of poorly simulated storm environments and physical interpretation of these model issues.
RESUMO
OBJECTIVE: To determine whether a prototype artificial intelligence system can identify volume of hemorrhage in a porcine model of controlled hemorrhagic shock. DESIGN: Prospective in vivo animal model of hemorrhagic shock. SETTING: Research foundation animal surgical suite; computer laboratories of collaborating industry partner. SUBJECTS: Nineteen, juvenile, 25- to 35-kg, male and female swine. INTERVENTIONS: Anesthetized animals were instrumented for arterial and systemic venous pressure monitoring and blood sampling, and a splenectomy was performed. Following a 1-hr stabilization period, animals were hemorrhaged in aliquots to 10, 20, 30, 35, 40, 45, and 50% of total blood volume with a 10-min recovery between each aliquot. Data were downloaded directly from a commercial monitoring system into a proprietary PC-based software package for analysis. MEASUREMENTS AND MAIN RESULTS: Arterial and venous blood gas values, glucose, and cardiac output were collected at specified intervals. Electrocardiogram, electroencephalogram, mixed venous oxygen saturation, temperature (core and blood), mean arterial pressure, pulmonary artery pressure, central venous pressure, pulse oximetry, and end-tidal CO(2) were continuously monitored and downloaded. Seventeen of 19 animals (89%) died as a direct result of hemorrhage. Stored data streams were analyzed by the prototype artificial intelligence system. For this project, the artificial intelligence system identified and compared three electrocardiographic features (R-R interval, QRS amplitude, and R-S interval) from each of nine unknown samples of the QRS complex. We found that the artificial intelligence system, trained on only three electrocardiographic features, identified hemorrhage volume with an average accuracy of 91% (95% confidence interval, 84-96%). CONCLUSIONS: These experiments demonstrate that an artificial intelligence system, based solely on the analysis of QRS amplitude, R-R interval, and R-S interval of an electrocardiogram, is able to accurately identify hemorrhage volume in a porcine model of lethal hemorrhagic shock. We suggest that this technology may represent a noninvasive means of assessing the physiologic state during and immediately following hemorrhage. Point of care application of this technology may improve outcomes with earlier diagnosis and better titration of therapy of shock.