Brent Crude Oil Price Forecast Utilizing Deep Neural Network Architectures.

Brent crude oil is considered as one of the most important sources of crude oil pricing in the worldwide market, and it is used to set the price of two-thirds of the traded crude oil supplies in the world. To predict the price of Brent crude oil, LSTM and Bi-LSTM methods are applied, which are the architecture of the recursive neural network. Initially, the database creates the appropriate data for the period January 2015 to March 2021 from Brent crude oil price signals and daily data from a financial market, and then, the modeling process is performed via the use of MATLAB software. Also, about 90% of the data are for training and the remaining for validation and comparison. Using LSTM and Bi-LSTM neural networks, the network architecture has been worked on, and by adding the number of layers and changing the solvers (SGDM, RMSProp, and Adam), the errors of different models are compared with each other. Nonlinear techniques of artificial neural networks and deep learning were used for modeling. Then, the network architecture was worked on and the model error rate was evaluated by comparing different layers and solvents such as SGDM, RMSProp, and Adam. The superiority of SGDM solvent over others was shown, and finally, it can be mentioned as the superior method of modeling of price forecasting in Brent crude oil field. The results show that the model with two layers of LSTM and SGDM solver has less error and better accuracy.

Impact of Race and Socioeconomic Status on Outcomes in Patients Hospitalized with COVID-19.

BACKGROUND: The impact of race and socioeconomic status on clinical outcomes has not been quantified in patients hospitalized with coronavirus disease 2019 (COVID-19). OBJECTIVE: To evaluate the association between patient sociodemographics and neighborhood disadvantage with frequencies of death, invasive mechanical ventilation (IMV), and intensive care unit (ICU) admission in patients hospitalized with COVID-19. DESIGN: Retrospective cohort study. SETTING: Four hospitals in an integrated health system serving southeast Michigan. PARTICIPANTS: Adult patients admitted to the hospital with a COVID-19 diagnosis confirmed by polymerase chain reaction. MAIN MEASURES: Patient sociodemographics, comorbidities, and clinical outcomes were collected. Neighborhood socioeconomic variables were obtained at the census tract level from the 2018 American Community Survey. Relationships between neighborhood median income and clinical outcomes were evaluated using multivariate logistic regression models, controlling for patient age, sex, race, Charlson Comorbidity Index, obesity, smoking status, and living environment. KEY RESULTS: Black patients lived in significantly poorer neighborhoods than White patients (median income: $34,758 (24,531-56,095) vs. $63,317 (49,850-85,776), p < 0.001) and were more likely to have Medicaid insurance (19.4% vs. 11.2%, p < 0.001). Patients from neighborhoods with lower median income were significantly more likely to require IMV (lowest quartile: 25.4%, highest quartile: 16.0%, p < 0.001) and ICU admission (35.2%, 19.9%, p < 0.001). After adjusting for age, sex, race, and comorbidities, higher neighborhood income ($10,000 increase) remained a significant negative predictor for IMV (OR: 0.95 (95% CI 0.91, 0.99), p = 0.02) and ICU admission (OR: 0.92 (95% CI 0.89, 0.96), p < 0.001). CONCLUSIONS: Neighborhood disadvantage, which is closely associated with race, is a predictor of poor clinical outcomes in COVID-19. Measures of neighborhood disadvantage should be used to inform policies that aim to reduce COVID-19 disparities in the Black community.