Objective To develop and validate a deep learning model based on chest CT images to accurately distinguish between drug-resistant(DR-TB)and-sensitive tuberculosis(DS-TB).Methods A retrospective study was conducted on 722 cases of confirmed secondary tuberculosis admitted in our center from January 2019 to December 2022.According to the results of antimicrobial susceptibility test,they were divided into 357 DS-TB cases and 365 DR-TB cases.Pre-existing U-Net segmentation model was employed to segment the lung parenchyma regions in CT images.The dataset was randomly partitioned into a training set and a testing set in an 8:2 ratio.Six 3D deep learning architectures(3D Swin Transformer,3D ShuffleNet v2,3D ViT,3D MobileNet v2,3D DenseNet,and 3D ResNet18)were employed to evaluate the discriminative efficiency between DS-TB and DR-TB.Hyperparameters were optimized by five-fold cross-validation on the training set to construct the optimal model.The performance of the constructed model was assessed using area under the curve(AUC),sensitivity,specificity,positive predictive value(PPV),negative predictive value(NPV),and F1-score.Six radiologists independently evaluated DR-TB identification on the test set,and their performance was compared with the best-performing deep learning model.Results The AUC value in DR-TB prediction was 0.583,0.704,0.698,0.758,0.736,and 0.841,respectively,for 3D Swin Transformer,3D ShuffleNet v2,3D ViT,3D MobileNet v2,3D DenseNet,and 3D ResNet18.The 3D ResNet18 model demonstrated optimal performance,achieving a sensitivity of 0.935(95%CI:0.880～0.987),a specificity of 0.642(95%CI:0.492～0.757),a PPV of 0.750(95%CI:0.663～0.835),an NPV of 0.896(95%CI:0.809～0.976),an AUC value of 0.841,and a F1-score of 0.832.The radiologists got a F1-score of 0.571,0.450,0.675,0.623,0.617 and 0.635,respectively,and the F1-score of the 3D ResNet18 model is all higher than that of the radiologists.The highest-performing radiologist achieved sensitivity,specificity,PPV and NPV of 0.701(95%CI:0.605～0.802),0.567(95%CI:0.447～0.684),0.651(95%CI:0.549～0.757),and 0.623(95%CI:0.500～0.754),with all these values lower than those of the 3D ResNet18 model(P<0.05).Class activation mapping showed that the 3D ResNet18 model could focus on key lesion areas.The class activation mapping demonstrated that the 3D ResNet18 model could effectively focus on critical lesion regions.Conclusion Our 3D ResNet18 model shows the best predictive performance in identifying DR-TB,and is expected to assist clinical diagnosis for DR-TB.

Chronic hepatitis B virus （HBV） infection is a worldwide public health issue and a leading cause of liver fibrosis， liver cirrhosis， liver failure， and primary liver cancer in China. The incidence rate of nonalcoholic fatty liver disease （NAFLD） is gradually increasing with the improvement in the living standards of people and the changes in dietary structure. Population-based studies have found that HBV infection can influence the development of NAFLD， but the mechanism remains unknown. Hepatic steatosis can also influence the expression of HBV serum pathogenic indicators， and its combination with NAFLD and other metabolic dysfunction diseases can increase the risk of liver fibrosis， liver cirrhosis， and liver cancer. Chronic HBV infection is closely associated with metabolic dysfunction， and more studies are needed in the future to better understand related mechanisms， so as to provide a theoretical foundation for clinical diagnosis and treatment.

Objective:To observe the application effect of high-flow nasal canula oxygen therapy (HFNC) after extubation in patients with mechanical ventilation (MV) in the intensive care unit (ICU).Methods:A prospective study was conducted. From January 2018 to June 2020, 163 MV patients admitted to Yijishan Hospital of Wannan Medical College were enrolled, and they were divided into HFNC group (82 cases) and traditional oxygen therapy group (81 cases) according to the oxygen therapy model. The patients included in the study were given conventional treatment according to their condition. In the HFNC group, oxygen was inhaled by a nasal high-flow humidification therapy instrument. The gas flow was gradually increased from 35 L/min to 60 L/min according to the patient's tolerance, and the temperature was set at 34-37 ℃. The fraction of inspiration oxygen (FiO 2) was set according to the patient's pulse oxygen saturation (SpO 2) and SpO 2 was maintained at 0.95-0.98. A disposable oxygen mask or nasal cannula was used to inhale oxygen in the traditional oxygen therapy group, and the oxygen flow was 5-8 L/min, maintaining the patient's SpO 2 at 0.95-0.98. The differences in MV duration before extubation, total MV duration, intubation time, reintubation time, extubation failure rate, ICU mortality, ICU stay, and in-hospital stay were compared between the two groups, and weaning failure were analyzed. Results:There was no significant differences in MV duration before extubation (days: 4.33±3.83 vs. 4.15±3.03), tracheal intubation duration (days: 4.34±1.87 vs. 4.20±3.35), ICU mortality [4.9% (4/82) vs. 3.7% (3/81)] and in-hospital stay [days: 28.93 (15.00, 32.00) vs. 27.69 (15.00, 38.00)] between HFNC group and traditional oxygen therapy group (all P > 0.05). The total MV duration in the HFNC group (days: 4.48±2.43 vs. 5.67±3.84) and ICU stay [days: 6.57 (4.00, 7.00) vs. 7.74 (5.00, 9.00)] were significantly shorter than those in the traditional oxygen therapy group, the reintubation duration of the HFNC group was significantly longer than that of the traditional oxygen therapy group (hours: 35.75±10.15 vs. 19.92±13.12), and the weaning failure rate was significantly lower than that of the traditional oxygen therapy group [4.9% (4/82) vs. 16.0% (13/81), all P < 0.05]. Among the reasons for weaning failure traditional oxygen therapy group had lower ability of airway secretion clearance than that of the HFNC group [8.64% (7/81) vs. 0% (0/82), P < 0.05], there was no statistically differences in the morbidity of heart failure, respiratory muscle weakness, hypoxemia, and change of consciousness between the two groups. Conclusion:For MV patients in the ICU, the sequential application of HFNC after extubation can reduce the rate of weaning failure and the incidence of adverse events, shorten the length of ICU stay.