Search

Abstract Introduction The current study investigates the utilization and performance of machine learning (ML) algorithms in the cognitive task of finding the correlation between numerical parameters of the human brain activation during gaming. We hypothesize that our integrated feature extraction platform is able to distinguish between different psychosomatic conditions in the gaming process as measured by the functional near‐infrared brain imaging technique. Methods For demonstration, the decision‐making process was constructed in the experiment environment that combined gaming simulator, such as the Iowa Gaming Task (IGT), with functional near‐infrared spectroscopy (fNIRS) as the neuroimaging technique. Features of fNIRS levels were extracted, averaged, and synchronized by time with the IGT dataset to predict the task score inside ML algorithms, such as multiple regression, classification and regression trees, support vector machine, artificial neural network, and random forest. For findings validation, the experiment data were resampled by training and testing sets. Further, a training dataset was used to train the ML algorithms, and prediction accuracy was estimated by repeated cross‐validation methods and compared by R squared and root mean square error (RMSE). The model with the best accuracy was used with the testing dataset and finalized the experiment. Results During the experiment, the highest correlation was identified in the fourth block between the oxy‐hemoglobin signal and IGT score in average value (0.24) and signal feature (0.57). Such relationship is due to block 4 characterization as “conceptual” period when participants task experience reaches the maximum, and rewards raise accordingly. Simultaneously, ML algorithms, constructed based on training data set, demonstrate acceptable performance, and RMSE as the primary performance metric dynamically increases from block 1 to block 5, from the state of uncertainty and unknown to the certainty and risky. In contrast, R squared decreases during the same transition. In most IGT blocks, the best fitted model was determined as support vector machine with radial bases function kernel, and predictions were made with the highest accuracy (lowest RMSE) than in training models. Conclusion Obtained findings showed the applicability and capability of ML models as a powerful technique to evaluate the cognitive neuroimaging task result. Moreover, in terms of features it was identified that the hemodynamic response reacts to the acceleration decision‐making process and raises more significance than it was observed before.

BACKGROUND AND AIMS: Acute hepatitis C infection usually ends in chronic infection, while in a minority of patients it is spontaneously cleared. The current population-based study is performed on a large cohort in Golestan province of Iran to examine the demographic correlates of Spontaneous Hepatitis C Clearance. METHODS: Serum samples used in this study had been stored in biorepository of Golestan Cohort Study. These samples were evaluated for anti hepatitis C Virus by third generation Enzyme-linked immunosorbent assay (ELISA). Subjects who tested positive were then invited and tested by Recombinant Immunoblot Assay (RIBA) and Ribonucleic Acid Polymerase Chain Reaction test (PCR). If tested positive for RIBA, subjects were recalled and the two tests were re-done after 6 months. Those subjects who again tested positive for RIBA but negative for PCR were marked as cases of spontaneous clearance. RESULTS: 49,338 serum samples were evaluated. The prevalence of Chronic Hepatitis C Virus (CHCV) infection based on PCR results was 0.31%. Among those who had acquired hepatitis C, the rate of SC was 38%. In multivariate analysis, illicit drug use both Injecting Use (OR = 3.271, 95% CI: 1.784-6.000, p-value

BACKGROUND & AIMS: There is a worldwide epidemic of obesity among adolescents who subsequently are at increased risk for the development of non alcoholic fatty liver disease (NAFLD). The serum alanine aminotransferase (ALT) is the most frequently used test for screening these individuals, but no age and gender-specific upper limits of normal (ULN) based on healthy population data in children are available. The objective of the present study was to define ULN for ALT in healthy children in order to use this as a tool for case finding. METHODS: A total of 975 school children (aged 7-18 years) were included in the study cohort. Highly significant correlations (all p

About 8% of the general population suffers from autoimmune diseases, from which 78% are women. One of the most important causes of thyroid diseases is autoimmunity in origin, and it seems that people with thyroid diseases present more signs of asthma. This study was therefore designed to investigate the frequency of autoimmune thyroid diseases in women suffering from bronchial asthma. In a cross-sectional study, 100 women with asthma and 100 women as control group were tested for thyroid function and anti-thyroid peroxidase antibody (anti-TPO Ab) measurements. The asthmatic patients were selected based on having chronic cough, dyspnea, wheezing and clinical examination of the chest. The diagnosis was confirmed by pulmonary function tests. Blood tests were done by electrochemiluminescence immunoassay method. No hyperthyroid patient was found in either group. Serum TSH and Total T4 levels were not statistically different between the two groups, but serum anti-TPO Ab levels in women with asthma (74±13.6 IU/ml) was significantly higher than control group (45.24±10.56 IU/ml). After adjusting the effect of age and BMI, the relationship between asthma and anti- TPO Ab (>50 IU/ml) was statistically significant (OR=3.3, P

The aim of this study was to evaluate the in vitro antimicrobial activity of a methanolic extract of Salvadora persica solution on Helicobacter pylori isolated from duodenal ulcer. Over 22 strains of H. pylori were isolated from duodenal ulcer from August 2010 to June 2011. The S. persica stem was purchased from a local herb market and finely powdered. Extraction was performed with 60% methanol using a soxhlet extractor for 48 h until the solvent turned colorless while being incubated in an oven at 40°C for 48 h till dried. Dry powder was used to determine antimicrobial activity by the agar ditch method. Minimum inhibitory concentration (MIC) and minimal bactericidal concentration (MBC) of the extract were determined by the agar dilution method. At concentrations of 10, 100, 200, 500 µg/mL, no zone of inhibition around the ditches was observed while a clear zone of inhibition (12 mm) was detected at 1000 µg/mL concentration for all the isolates. The best antimicrobial activity was observed at MIC 1000 µg/mL (P≤0.05). Furthermore, 10 out of 22 isolates were inhibited at 750 µg/mL of the extract. The MBC results showed that at a concentration of 1000 µg/mL all cells were dead while at a concentration of 750 µg/mL of S. persica a few H. pylori cells were still able to form colonies on Brucella agar supplemented with sheep red blood cells and antibiotics. From the above results it can be concluded that high concentration of S.persica could inhibit the growth of H. pylori and MIC and MBC were similar at that concentration.