Prognostic Value of Procalcitonin, CRP, Serum Amyloid A, Lactate and IL-6 Markers in Liver Transplant Patients Admitted to ED with Suspected Infection.

BACKGROUND/AIM: Infections are one of the most important causes of mortality and morbidity after liver transplantation as in all transplantations. Infectious complications are known to be among the preventable causes with appropriate diagnosis and treatment. So early prediction of the risk of infections will provide an effective approach to determine the local antimicrobial resistance and prevention of specific risk factors. The aim of this study was to deterimne whether specific markers are useful or not to deterimne a suspected infection in patients that have undergone liver transplantation. PATIENTS AND METHODS: The study included 65 patients with liver transplantation admitted to emergency room with suspicion of infection. These patient's CRP, procalsitonin (PCT), lactate, SAA and IL-6 levels were initially measured in the emergency department. The patients were classified to three categories according to culture results; culture-negative, culture-positive and control group. Studying parameters were investigated according to whether the culture was positive or negative in these patients. RESULTS: CRP, PCT, lactate, SAA and IL-6 levels were significanlty high in patients with suspected infeciton when compared to the control group (p<0.05). CRP, PCT and IL-6 levels were higher in the culture-positive group than in the culture-negative group and there was a significant variation (p<0.05). When suspecting an infection evaluating the parameters CRP, PCT and IL-6 was very meaningfull (p<0.05). CONCLUSION: We can use CRP, PCT, lactate, SAA and IL-6 parameters to identify presence of infection at the liver transplantation patients admitted to the emergency department with suspected infection. If CRP, PCT and IL-6 levels are significantly high we can guess the patient's positive culture.

Application of knowledge discovery process on the prediction of stroke.

OBJECTIVE: Stroke is a prominent life-threatening disease in the world. The current study was performed to predict the outcome of stroke using knowledge discovery process (KDP) methods, artificial neural networks (ANN) and support vector machine (SVM) models. MATERIALS AND METHODS: The records of 297 (130 sick and 167 healthy) individuals were acquired from the databases of the department of emergency medicine. Nine predictors (coronary artery disease, diabetes mellitus, hypertension, history of cerebrovascular disease, atrial fibrillation, smoking, the findings of carotid Doppler ultrasonography [normal, plaque, plaque+stenosis≥50%], the levels of cholesterol and C-reactive protein) were used for predicting the stroke. Feature selection based on the Cramer's V test was carried out for reducing the predictors. Multilayer perceptron (MLP) ANN and SVM with radial basis function (RBF) kernel were used for the prediction based on the selected predictors. RESULTS: The accuracy values were 81.82% for ANN and 80.38% for SVM in the training dataset (n=209), and 85.9% for ANN and 84.62% for SVM in the testing dataset (n=78), respectively. ANN and SVM models yielded area under curve (AUC) values of 0.905 and 0.899 in the training dataset, and 0.928 and 0.91 in the testing dataset, consecutively. CONCLUSION: The findings of the current study pointed out that ANN had more predictive performance when compared with SVM in predicting stroke. The proposed ANN model would be useful when making clinical decisions regarding stroke.