Forecasting oil consumption with attention-based IndRNN optimized by adaptive differential evolution.

Accurate prediction of oil consumption plays a dominant role in oil supply chain management. However, because of the effects of the coronavirus disease 2019 (COVID-19) pandemic, oil consumption has exhibited an uncertain and volatile trend, which leads to a huge challenge to accurate predictions. The rapid development of the Internet provides countless online information (e.g., online news) that can benefit predict oil consumption. This study adopts a novel news-based oil consumption prediction methodology-convolutional neural network (CNN) to fetch online news information automatically, thereby illustrating the contribution of text features for oil consumption prediction. This study also proposes a new approach called attention-based JADE-IndRNN that combines adaptive differential evolution (adaptive differential evolution with optional external archive, JADE) with an attention-based independent recurrent neural network (IndRNN) to forecast monthly oil consumption. Experimental results further indicate that the proposed news-based oil consumption prediction methodology improves on the traditional techniques without online oil news significantly, as the news might contain some explanations of the relevant confinement or reopen policies during the COVID-19 period.

Interpretable tourism volume forecasting with multivariate time series under the impact of COVID-19.

This study proposes a novel interpretable framework to forecast the daily tourism volume of Jiuzhaigou Valley, Huangshan Mountain, and Siguniang Mountain in China under the impact of COVID-19 by using multivariate time-series data, particularly historical tourism volume data, COVID-19 data, the Baidu index, and weather data. For the first time, epidemic-related search engine data is introduced for tourism demand forecasting. A new method named the composition leading search index-variational mode decomposition is proposed to process search engine data. Meanwhile, to overcome the problem of insufficient interpretability of existing tourism demand forecasting, a new model of DE-TFT interpretable tourism demand forecasting is proposed in this study, in which the hyperparameters of temporal fusion transformers (TFT) are optimized intelligently and efficiently based on the differential evolution algorithm. TFT is an attention-based deep learning model that combines high-performance forecasting with interpretable analysis of temporal dynamics, displaying excellent performance in forecasting research. The TFT model produces an interpretable tourism demand forecast output, including the importance ranking of different input variables and attention analysis at different time steps. Besides, the validity of the proposed forecasting framework is verified based on three cases. Interpretable experimental results show that the epidemic-related search engine data can well reflect the concerns of tourists about tourism during the COVID-19 epidemic.

Interpretable tourism demand forecasting with temporal fusion transformers amid COVID-19.

An innovative ADE-TFT interpretable tourism demand forecasting model was proposed to address the issue of the insufficient interpretability of existing tourism demand forecasting. This model effectively optimizes the parameters of the Temporal Fusion Transformer (TFT) using an adaptive differential evolution algorithm (ADE). TFT is a brand-new attention-based deep learning model that excels in prediction research by fusing high-performance prediction with time-dynamic interpretable analysis. The TFT model can produce explicable predictions of tourism demand, including attention analysis of time steps and the ranking of input factors' relevance. While doing so, this study adds something unique to the literature on tourism by using historical tourism volume, monthly new confirmed cases of travel destinations, and big data from travel forums and search engines to increase the precision of forecasting tourist volume during the COVID-19 pandemic. The mood of travelers and the many subjects they spoke about throughout off-season and peak travel periods were examined using a convolutional neural network model. In addition, a novel technique for choosing keywords from Google Trends was suggested. In other words, the Latent Dirichlet Allocation topic model was used to categorize the major travel-related subjects of forum postings, after which the most relevant search terms for each topic were determined. According to the findings, it is possible to estimate tourism demand during the COVID-19 pandemic by combining quantitative and emotion-based characteristics.

Forecasting the U.S. oil markets based on social media information during the COVID-19 pandemic.

Accurate oil market forecasting plays an important role in the theory and application of oil supply chain management for profit maximization and risk minimization. However, the coronavirus disease 2019 (COVID-19) has compelled governments worldwide to impose restrictions, consequently forcing the closure of most social and economic activities. The latter leads to the volatility of the oil markets and poses a huge challenge to oil market forecasting. Fortunately, the social media information can finely reflect oil market factors and exogenous factors, such as conflicts and political instability. Accordingly, this study collected vast online oil news and used convolutional neural network to extract relevant information automatically. Oil markets are divided into four categories: oil price, oil production, oil consumption, and oil inventory. A total of 16,794; 9,139; 8,314; and 8,548 news headlines were collected in four respective cases. Experimental results indicate that social media information contributes to the forecasting of oil price, oil production and oil consumption. The mean absolute percentage errors are respectively 0.0717, 0.0144 and 0.0168 for the oil price, production, and consumption prediction during the COVID-19 pandemic. Marketers must consider the impact of social media information on the oil or similar markets, especially during the COVID-19 outbreak.

Roles of Nicotinamide N-Methyltransferase in Obesity and Type 2 Diabetes.

Type 2 diabetes (T2D) is thought to be a complication of metabolic syndrome caused by disorders of energy utilization and storage and characterized by insulin resistance or deficiency of insulin secretion. Though the mechanism linking obesity to the development of T2D is complex and unintelligible, it is known that abnormal lipid metabolism and adipose tissue accumulation possibly play important roles in this process. Recently, nicotinamide N-methyltransferase (NNMT) has been emerging as a new mechanism-of-action target in treating obesity and associated T2D. Evidence has shown that NNMT is associated with obesity and T2D. NNMT inhibition or NNMT knockdown significantly increases energy expenditure, reduces body weight and white adipose mass, improves insulin sensitivity, and normalizes glucose tolerance and fasting blood glucose levels. Additionally, trials of oligonucleotide therapeutics and experiments with some small-molecule NNMT inhibitors in vitro and in preclinical animal models have validated NNMT as a promising therapeutic target to prevent or treat obesity and associated T2D. However, the exact mechanisms underlying these phenomena are not yet fully understood and clinical trials targeting NNMT have not been reported until now. Therefore, more researches are necessary to reveal the acting mechanism of NNMT in obesity and T2D and to develop therapeutics targeting NNMT.

Diagnostic Performance of PI-RADS v2, Proposed Adjusted PI-RADS v2 and Biparametric Magnetic Resonance Imaging for Prostate Cancer Detection: A Preliminary Study.

PURPOSE: To evaluate the diagnostic performance of PI-RADS v2, proposed adjustments to PI-RADS v2 (PA PI-RADS v2) and biparametric magnetic resonance imaging (MRI) for prostate cancer detection. METHODS: A retrospective cohort of 224 patients with suspected prostate cancer was included from January 2016 to November 2018. All the patients underwent a multi-parametric MR scan before biopsy. Two radiologists independently evaluated the MR examinations using PI-RADS v2, PA PI-RADS v2, and a biparametric MRI protocol, respectively. Receiver operating characteristic (ROC) curves for the three different protocols were drawn. RESULTS: In total, 90 out of 224 cases (40.18%) were pathologically diagnosed as prostate cancer. The area under the ROC curves (AUC) for diagnosing prostate cancers by biparametric MRI, PI-RADS v2, and PA PI-RADS v2 were 0.938, 0.935, and 0.934, respectively. For cancers in the peripheral zone (PZ), the diagnostic sensitivity was 97.1% for PI-RADS v2/PA PI-RADS v2 and 96.2% for biparametric MRI. Moreover, the specificity was 84.0% for biparametric MRI and 58.0% for PI-RADS v2/PA PI-RADS v2. For cancers in the transition zone (TZ), the diagnostic sensitivity was 93.4% for PA PI-RADS v2 and 88.2% for biparametric MRI/PI-RADS v2. Furthermore, the specificity was 95.4% for biparametric MRI/PI-RADS v2 and 78.0% for PA PI-RADS v2. CONCLUSIONS: The overall diagnostic performance of the three protocols showed minimal differences. For lesions assessed as being category 3 using the biparametric MRI protocol, PI-RADS v2, or PA PI-RADS v2, it was thought prostate cancer detection could be improved. Attention should be paid to false positive results when PI-RADS v2 or PA PI-RADS v2 are used.

Dual energy computed tomography for detection of metastatic lymph nodes in patients with hepatocellular carcinoma.

BACKGROUND: Regional lymph node metastasis in patients with hepatocellular carcinoma (HCC) is not uncommon, and is often under- or misdiagnosed. Regional lymph node metastasis is associated with a negative prognosis in patients with HCC, and surgical resection of lymph node metastasis is considered feasible and efficacious in improving the survival and prognosis. It is critical to characterize lymph node preoperatively. There is currently no consensus regarding the optimal method for the assessment of regional lymph nodes in patients with HCC. AIM: To evaluate the diagnostic value of single source dual energy computed tomography (CT) in regional lymph node assessment for HCC patients. METHODS: Forty-three patients with pathologically confirmed HCC who underwent partial hepatectomy with lymphadenectomy were retrospectively enrolled. All patients underwent dual-energy CT preoperatively. Regional lymph nodes (n = 156) were divided into either a metastatic (group P, n = 52) or a non-metastasis group (group N, n = 104), and further, according to pathology, divided into an active hepatitis (group P1, n = 34; group N1, n = 73) and a non-active hepatitis group (group P2, n = 18; group N2, n = 31). The maximal short axis diameter (MSAD), iodine concentration (IC), normalized IC (NIC), and the slope of the spectral curve (λ HU) of each group in the arterial phase (AP), portal phase (PP), and delayed phase (DP) were analyzed. RESULTS: Analysis of the MSAD, IC, NIC, and λ HU showed statistical differences between groups P and N (P < 0.05) during all three phases. To distinguish benign from metastatic lymph nodes, the diagnostic efficacy of IC, NIC, and λ HU in the PP was the best among the three phases (AP, PP, and DP), with a sensitivity up to 81.9%, 83.9%, and 81.8%, and a specificity up to 82.4%, 84.1% and 84.1%, respectively. The diagnostic value of combined analyses of MSAD with IC, NIC, or λ HU in the PP was superior to the dual energy CT parameters alone, with a sensitivity up to 84.5%, 86.9%, and 86.2%, and a specificity up to 83.0%, 93.6% and 89.8%, respectively. Between groups P1 and P2 and groups N1 and N2, only IC, NIC, and λ HU between groups N1 and N2 in the PP had a statistically significant difference (P < 0.05). CONCLUSION: Dual-energy CT contributes beneficially to regional lymph node assessment in HCC patients. Combination of MSAD with IC, NIC, or λ HU values in the PP is superior to using any single parameter alone. Active hepatitis does not deteriorate the capabilities for characterization of metastatic lymph nodes.

Giant Serous Cystadenoma of the Pancreas (⩾10 cm): The Clinical Features and CT Findings.

Purpose. To report the clinical features and CT manifestations of giant pancreatic serous cystadenoma (≥10 cm). Methods. We retrospectively reviewed the clinical features and CT findings of 6 cases of this entity. Results. All 6 patients were symptomatic. The tumors were 10.2 cm-16.5 cm (median value, 13.0 cm). CT imaging revealed that all 6 cases showed microcystic appearances (n = 5) or mixed microcystic and macrocystic appearances (n = 1). Five patients with tumors at the distal end of the pancreas received distal pancreatectomy. Among these 5 patients, 2 patients underwent partial transverse colon resection or omentum resection due to close adhesion. One patient whose tumor was located in the pancreatic head underwent pancreaticoduodenectomy; however, due to encasement of the portal and superior mesenteric veins, the tumor was incompletely resected. One patient had abundant draining veins on the tumor surface and suffered large blood loss (700 mL). After 6-49 months of follow-up the 6 patients showed no tumor recurrence or signs of malignant transformation. Conclusions. Giant pancreatic serous cystadenoma necessitates surgical resection due to large size, symptoms, uncertain diagnosis, and adjacent organ compression. The relationship between the tumors and the neighboring organs needs to be carefully assessed before operation on CT image.