Prediction of pulp exposure risk of carious pulpitis based on deep learning / 华西口腔医学杂志

OBJECTIVES@#This study aims to predict the risk of deep caries exposure in radiographic images based on the convolutional neural network model, compare the prediction results of the network model with those of senior dentists, evaluate the performance of the model for teaching and training stomatological students and young dentists, and assist dentists to clarify treatment plans and conduct good doctor-patient communication before surgery.@*METHODS@#A total of 206 cases of pulpitis caused by deep caries were selected from the Department of Stomatological Hospital of Tianjin Medical University from 2019 to 2022. According to the inclusion and exclusion criteria, 104 cases of pulpitis were exposed during the decaying preparation period and 102 cases of pulpitis were not exposed. The 206 radiographic images collected were randomly divided into three groups according to the proportion: 126 radiographic images in the training set, 40 radiographic images in the validation set, and 40 radiographic images in the test set. Three convolutional neural networks, visual geometry group network (VGG), residual network (ResNet), and dense convolutional network (DenseNet) were selected to analyze the rules of the radiographic images in the training set. The radiographic images of the validation set were used to adjust the super parameters of the network. Finally, 40 radiographic images of the test set were used to evaluate the performance of the three network models. A senior dentist specializing in dental pulp was selected to predict whether the deep caries of 40 radiographic images in the test set were exposed. The gold standard is whether the pulp is exposed after decaying the prepared hole during the clinical operation. The prediction effect of the three network models (VGG, ResNet, and DenseNet) and the senior dentist on the pulp exposure of 40 radiographic images in the test set were compared using receiver operating characteristic (ROC) curve, area under the ROC curve (AUC), accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F1 score to select the best network model.@*RESULTS@#The best network model was DenseNet model, with AUC of 0.97. The AUC values of the ResNet model, VGG model, and the senior dentist were 0.89, 0.78, and 0.87, respectively. Accuracy was not statistically different between the senior dentist (0.850) and the DenseNet model (0.850)(P>0.05). Kappa consistency test showed moderate reliability (Kappa=0.6>0.4, P<0.05).@*CONCLUSIONS@#Among the three convolutional neural network models, the DenseNet model has the best predictive effect on whether deep caries are exposed in imaging. The predictive effect of this model is equivalent to the level of senior dentists specializing in dental pulp.

Analysis of clinical characteristics and warning factors in SARS-CoV-2 variants infection / 中国热带医学

@#Abstract: Objective To investigate the influence of the variation of SARS-CoV-2 on the clinical feature, and to provide early warning signs for the variation of SARS-CoV-2 in clinical work. Methods From Jan 2, 2021 to Jun 30, 2021, a total of 105 COVID-19 patients were included in the study using a case-control method. Nasal swab samples were collected from the study subjects, the viral genes were sequenced, and patients were divided into Delta variant group and non-Delta variant group according to their gene sequences. Clinically relevant data were collected from the two groups, and indicators such as days of hospitalization, age distribution, lymphocytes, neutrophils, B lymphocytes, NK cells, IL-4, and IL-10 were compared; subgroup analysis was performed based on the number of days of viral negativity in the study subjects as the basis for grouping, and differences in immunological characteristics were compared, including lymphocytes, neutrophils, B lymphocytes, NK cells, IL-4, IL-10, etc. Results The theoretical hospitalization days of Delta variant group were (22.2±8.33) d, which were significantly longer than (17.6±10.50) d of non-Delta variant group (t=2.396, P<0.05). The total lymphocyte count and IL-4 of Delta variant group were (1.22±0.86) ×109/L and (0.80±0.23) ng/mL, which were significantly lower than corresponding (1.91±0.70) ×109/L and (1.59±0.59) ng/mL of non-Delta variant group (t=4.329, 9.072, P<0.05), while IL-10 was (7.16±7.77) ng/mL, which was significantly higher than (4.26±3.91) ng/mL of non-Delta mutation group (t=1.980, P<0.05). Subgroup analysis showed that the total lymphocyte count and IL-4 concentration in Delta variant group were (1.04±0.60) ×109/L and (0.74±0.25) ng/ml, which were significantly lower than corresponding (1.62±0.56) ×109/L and (1.56±0.52) ng/mL in non-Delta variant group, in patients with delayed discharge (P<0.05). Conclutions SARS-CoV-2 variant has an impact on clinical manifestations. The patient's B cell count and IL-10 concentration increased or IL-2 and IL-4 concentration decreased within 12 hours of admission indicated variant virus infection. The decrease of total lymphocyte count, especially T lymphocyte reduction, strongly suggests discharge delay due to viral clearance disorder.

Protective effects of N-acetyl-L-cysteine against binge drinking-induced fatty liver in mice / 中华劳动卫生职业病杂志

Objective@#To investigate the roles of N-acetyl-L-cysteine (NAC) against binge drinking-induced fatty liver in mice.@*Methods@#SPF male C57BL/6 mice were randomly divided into 3 groups, i.e. control group, model group, and NAC/ethanol group (n=10). Mice in model and NAC/ethanol groups were exposed to 3 doses of ethanol (6 g/kg bw) to induced fatty liver, while mice in control group received equal volume and equal energy of maltodextrin solution. NAC was administered to mice at 1 h before ethanol exposure (100 mg/kg bw, i.p.). The mice were sacrificed at 6 h after the last ethanol exposure. The liver and epididymal adipose tissues were collected. Histopathological examination and biochemical assay kit were used to evaluate the fat accumulation, while Western-blot was performed to detect the protein levels of some key factors involved in fat metabolism in liver and adipose tissues.@*Results@#Compored with control group mice, the liver index and liver weight were significantly increased compared with model group, the liver index and TG level in NAC/ethanol group mice were all significantly decreased (P<0.05). Histological examination showed NAC effectively suppressed binge drinking-induced fat accumulation in mice liver. In addition, NAC had no significant effects on the protein levels of peroxisome proliferator-activated receptor-α (PPAR-α), Acy-CoA oxidase (ACOX), sterol regulatory element binding protein 1 c (SREBP-1c) and fatty acid synthase (FAS). Furthermore, the protein levels of hormone sensitive lipase (HSL) did not significantly differ among 3 groups, whereas NAC prevented binge drinking-induced increase of HSL phosphorylation at ser563 and ser660.@*Conclusion@#NAC could effectively attenuate binge drinking-induced fatty liver, which might be associated with the inhibition of lipid mobilization by suppressing the phosphorylation of HSL.