Aspect-level sentiment analysis aims at identifying the sentiment polarity of target in the context. In most of the previous sentiment analysis models, there usually exists the problem of insufficient extraction capability of local features and long-distance dependency features. To solve the above problem, in this paper, we propose an improved model (called ADeCNN) for aspect-level sentiment analysis, by incorporating the attention mechanism into the deformable CNN model. In ADeCNN, we use deformable convolutional layers and bi-directional long short-term memory network (Bi-LSTM), combined with sentence-level attention, to extract sentiment features, and to break through the limitations of the model's long-distance dependency feature extraction capability. We then use a gated end-to-end memory network (GMemN2N) to integrate the target into the sentiment feature extraction process, so as to obtain sentiment features. And finally, we obtain the corresponding sentiment analysis results through the classifier. In addition, in order to solve the problem that the same words have large differences in the polarity of sentiments expressed in different targets, the model is also constructed with the ability to generate different attention weights based on target to assist sentiment analysis, with the aim of further enhancing the correlation between the target and the words in the sentence. We setup experiments to demonstrate the functionality effectiveness and performance gains of ADeCNN, based on the SemEval 2014 Task4 and SemEval 2017 Task4 datasets. Extensive experimental results show that ADeCNN outperforms its competitors, producing an arresting increase of the classification accuracy on all the three datasets of Laptop, Restaurant, and Twitter.

The prevention and treatment of oral diseases is more difficult in diabetic patients with poorly controlled blood glucose levels. This study aims to explore an effective, low-cytotoxicity medication for root canal treatment in diabetic patients. The antibacterial effect of the combination of Triton X-100 (TX-100) and metformin (Met) on Enterococcus faecalis (E. faecalis) was evaluated by determining the minimum inhibitory concentration (MIC), minimum bactericidal concentration required to kill 99% bacteria (MBC99) and by conducting dynamic time-killing assays. While the antibiofilm activity was measured by crystal violet (CV) assay, field emission scanning electron microscope (FE-SEM), confocal laser scanning microscope (CLSM) and colony-forming unit (CFU) counting assays. The expression of relative genes was evaluated by real-time quantitative polymerase chain reaction (RT-qPCR), and the cytotoxicity of the new combination on MC3T3-E1 cell was also tested. Results showed that the antibacterial and antibiofilm activities of Met could be significantly enhanced by very low concentrations of TX-100 in both normal and high-glucose conditions, with a much lower cytotoxicity than 2% chlorhexidine (CHX). Thus, the TX-100 + Met combination may be developed as a promising and effective root canal disinfectant for patients with diabetes.

BackgroundIdentification of multigland disease (MGD) in primary hyperparathyroidism (PHPT) patients is essential for minimally invasive surgical decision-making.ObjectiveTo develop a nomogram based on US findings and clinical factors to predict MGD in PHPT patients.Materials and MethodsPatients with PHPT who underwent surgery between March 2021 and January 2022 were consecutively enrolled. Biochemical and clinicopathologic data were recorded. US images were analyzed to extract US features. Logistic regression analyses were used to identify the risk factors for MGD. The nomogram was constructed based on the factors. Nomogram performance was evaluated by area under the receiver operating characteristic curve (AUC), calibration curve, the Hosmer–Lemeshow test, and decision curve analysis.ResultsA total of 102 PHPT patients were included. 82 (80.4%) had the single-gland disease (SGD) and 20 (19.6%) had MGD. Using multivariate analysis, the MGD was positively correlated with age (OR = 1.033, 96%CI = 0.985-1.092), PTH level (OR = 1.001, 95% CI = 1.000–1.002), MEN-1 (OR = 29.730, 95% CI = 3.089-836.785), US size (OR = 1.198, 95% CI = 0.647–2.088) and US texture (cystic-solid) (OR = 5.357, 95% CI = 0.499–62.912). And negatively correlated with gender (OR = 0.985, 95% CI = 0.190–4.047), calcium level (OR = 0.453, 95% CI = 0.070–2.448), and symptoms(yes) (OR = 0.935, 95%CI = 0.257–3.365). The nomogram showed good discrimination with an AUC of 0.77 (0.68-0.85) and good agreement for predicting MGD in PHPT patients. And 65 points was recommended as a cut-off value with a specificity of 0.94 and a sensitivity of 0.50.ConclusionUS provided useful features for evaluating MGD. Combining the US and clinical features in a nomogram showed good diagnostic performance for predicting MGD.

Purpose：To study the value of ultrasound in the diagnosis of juxtaglomerular cell tumor (JGCT). Methods: From January 2005 to July 2020, fifteen patients diagnosed as JGCT by surgical pathology in Peking Union Medical College Hospital were collected. All patients underwent preoperative ultrasound examination. The clinical, laboratory, ultrasound, computed tomography (CT), surgical, and pathological features of the patients were analyzed retrospectively. Results: The 15 patients were 5 males and 10 females with a median age of 29 years (10~72 years). 14 of them had hypertension and one had normal blood pressure. The tumors were all solitary, with a median diameter of 1.5 cm (0.9-5.9 cm). Among the fifteen patients, eleven were corrected detected by preoperative ultrasound, and four were missed. There was a significant difference in tumor size (2.64±1.48 cm vs. 1.23±0.21 cm) and whether the tumor protruded outward (9/11 vs. 0/4) between the ultrasound-detected group and the ultrasound-missed group (p=0.010, p=0.011). Of the 11 tumors detected by ultrasound, four were extremely hypoechoic, two were hypoechoic, three were isoechoic, and two were hyperechoic. Color Doppler showed no blood flow in five tumors no more than 2cm, and mild blood flow in six tumors more than 2cm. Conclusions: JGCT is rare, and has characteristic clinical manifestations. Diagnosis should be suspected in case of secondary hypertension, particularly in young women, if no renal vascular cause is found. Ultrasound, combined with clinical manifestations, was helpful for the diagnosis.