No abstract

PVT properties are very important in the reservoir engineering computations. There are many empirical approaches for predicting various PVT properties using regression models. Last decade, researchers utilized neural networks to develop more accurate PVT correlations. These achievements of neural networks open the door to both machine learning and data mining techniques to play a major role in both oil and gas industry. Unfortunately, the developed neural networks correlations have some limitations as they were originally developed for certain ranges of reservoir fluid characteristics and geographical area with similar fluid compositions. Accuracy of such correlations is often limited and global correlations are usually less accurate compared to local correlations. Recently, support vector machines have been proposed as a new intelligence framework for both prediction and classification based on both structure risk minimization criterion and soft margin hyperplane. This new framework dealt with kernel neuron functions instead of sigmoid-like ones, which allows projection to higher planes and solves more complex nonlinear problems. It has featured in a wide range of medical and business journals, often with promising results. The objective of this research is to assess the benefit of support vector machines as decision making tools in the field of oil and gas industry. To demonstrate the usefulness of the support vector machines technique in petroleum engineering area, we describe both the steps and the use of support vector machine modeling approach for predicting the PVT properties of crude oil systems. A comparative study will be carried out to compare their performance with the performance of the neural networks, nonlinear regression, and the empirical correlations algorithms. A preliminary results show that the performance of support vector machines will be accurate, reliable, and outperform most of the existing approaches. Future work can be achieved by using this new framework as a modeling approach for solving oil and gas industry problems, such as, permeability and porosity prediction, identify liquid-holdup flow regimes, and other reservoir characterization. Introduction Reservoir fluid properties are very important in petroleum engineering computations, such as, material balance calculations, well test analysis, reserve estimates, inflow performance calculations, and numerical reservoir simulations. Ideally, these properties are determined from laboratory studies on samples collected from the bottom of the wellbore or at the surface. Such experimental data are, however, very costly to obtain. Therefore, the solution is to use the empirically derived correlations to predict PVT properties, Osman et al.38. There are many empirical correlations for predicting PVT properties, most of them were developed using equations of state (EOS) or linear/non-linear multiple regression or graphical techniques or feedforward neural networks (ANN or FFN). However, they often do not perform very accurate and suffer from a number of drawbacks. Each correlation was developed for a certain range of reservoir fluid characteristics and geographical area with similar fluid compositions and API oil gravity. Thus, the accuracy of such correlations is critical and not often known in advance. Among those PVT properties is the bubble point pressure (bpp), Oil Formation Volume Factor (Bob), which is defined as the volume of reservoir oil that would be occupied by one stock tank barrel oil plus any dissolved gas at the bubble point pressure and reservoir temperature. Precise prediction of Bob is very important in reservoir and production computations. The objective of this study is to develop a new support vector machines prediction model for both bpp and Bob based on the kernel function scheme using worldwide experimental PVT data.

No abstract

The study evaluated endocrinal and metabolic response to sepsis and its applicability for the prediction of outcome of septic patients. Patients were 39 adult with severe infections and within 24 h after onset of suspected clinical tissue hypoperfusion. At enrollment patients were evaluated for acute physiology and chronic health evaluation II score (APACHE II) and Glasgow Coma Scale (GCS). Global hemodynamic parameters including systolic blood pressure (SBP), heart rate (HR) and central venous pressure (CVP) were recorded and monitored. All patients were managed at ICU due to Surviving Sepsis Campaign guidelines. ELISA estimated serum copeptin, macrophage migration inhibitory factor (MIF) and total cortisol (TC) and blood la ctate levels. Study outcome was survival rate via 28 days (28-D SR) and best predictor for it. The results showed that 22 patients passed total hospital stay uneventfully for a total survival rate of 56.4%. Seventeen patients died; 10 during ICU stay and 7 during word stay. At admission serum markers levels were significantly higher in survivors and nonsurvivors compared to controls and in non-survivors compared to survivors. Survival showed negative significant correlation with age, high blood lactate and serum copeptin, TC and MIF levels. Survival showed positive significant correlation with SBP, CVP and urine output. ROC curve and Regression analyses defined high at admission serum copeptin and blood lactate levels as significant predictors for mortality of septic patients.

Introduction: Coronavirus disease 2019 (COVID-19) is an outbreak due to SARS-CoV-2, declared by the World Health Organization (WHO) as a global pandemic in March 2020. Patients with underlying diseases, such as those with end-stage kidney disease (ESKD) on dialysis, are at greater risk. Objectives: The aim of our study to assess the outbreak and impact of COVID-19 on dialysis patients. Patients and Methods: Our study prospectively assessed and followed 442 patients with ESKD undergoing dialysis [390 patients on maintenance hemodialysis (HD) and 52 patients on peritoneal dialysis (PD)] for outbreak and impact of COVID-19 on these patients during the period from April 22, 2020 until March 23, 2021 in Al Khezam dialysis center, Kuwait. Age, gender, nationality, original kidney disease, history of hypertension (HTN), diabetes mellitus (DM), ischemic heart disease (IHD), congestive heart failure (CHF), bronchial asthma (BA), chronic obstructive pulmonary disease (COPD), history of pulmonary embolism (PE) and source of infection were analyzed. Symptoms as fever, fatigue, cough, loss of smell and taste and chest pain were recorded, the need for ICU admission, mechanical ventilation (MV), extracorporeal membrane oxygenation (ECMO), medications were recorded. The need to shift to continuous renal replacement therapy (CRRT) and outcomes (complications and mortality) were analyzed. Results: Our study reported that 102 out of 442 (23%) dialysis patients [97 out of 390 (24.8%) HD patients and 5 out of 52 (9.6%) PD patients] got infected with COVID-19 and reinfection reported in 4 out of 97 (4%) COVID-19 HD patients. Around 27% of COVID-19 HD patients had fever, 19% had fatigue, 8% had cough, 4% had loss of smell, 4% had loss of taste, 4% had chest pain and 40% of COVID-19 PD patients had fever. Fifteen out of 97 (15 %) COVID-19 HD patients needed ICU admission, 12 out of 97 (12 %) COVID-19 HD patients needed MV. A 33 out of 97 (34%) COVID-19 HD patients and 4 out of 5 (80%) COVID-19 PD patients needed to switch to CRRT. Mortality was 17 (15 HD and 2 PD) out of 102 (16.6 %) COVID-19 dialysis patients and common causes of death were sepsis, myocardial infarction (MI), heart failure and PE. Conclusion: Outbreak and mortality of COVID-19 infection is high in ESKD patients undergoing dialysis compared with general populations. Strict protocol for prevention of COVID-19 should be undertaken in dialysis centers and encourage of home dialysis and highly protective COVID-19 vaccination priority for dialysis patients.