Chronic hepatitis B（CHB）is one of the major challenges in the global public health field. As of 2022，approximately 254 million people worldwide were infected with the hepatitis B virus（HBV）. CHB is one of the main causes of liver cirrhosis and hepatocellular carcinoma（HCC）. Nucleos（t）ide analogs（NAs）and interferon therapy can delay the progression of liver fibrosis by inhibiting viral replication，but they cannot completely avoid the problem of heterogeneous treatment responses. Some patients are in a state of low-level viremia（LLV）during treatment. The persistent LLV state can induce chronic inflammation and the progression of liver fibrosis，ultimately increase the risk of HCC. In patients with poor treatment responses，the continuous active viral replication can induce immune disorders，accelerate the evolution of fibrosis to the decompensated stage of liver cirrhosis，and increase the risk of patient death. This article aims to review the definition，mechanisms，and impact on treatment outcomes of LLV and suboptimal response based on the latest research，provide a basis for optimizing antiviral therapy for CHB.

Chronic hepatitis B（CHB）is one of the major challenges in the global public health field. As of 2022，approximately 254 million people worldwide were infected with the hepatitis B virus（HBV）. CHB is one of the main causes of liver cirrhosis and hepatocellular carcinoma（HCC）. Nucleos（t）ide analogs（NAs）and interferon therapy can delay the progression of liver fibrosis by inhibiting viral replication，but they cannot completely avoid the problem of heterogeneous treatment responses. Some patients are in a state of low-level viremia（LLV）during treatment. The persistent LLV state can induce chronic inflammation and the progression of liver fibrosis，ultimately increase the risk of HCC. In patients with poor treatment responses，the continuous active viral replication can induce immune disorders，accelerate the evolution of fibrosis to the decompensated stage of liver cirrhosis，and increase the risk of patient death. This article aims to review the definition，mechanisms，and impact on treatment outcomes of LLV and suboptimal response based on the latest research，provide a basis for optimizing antiviral therapy for CHB.

Objective:To establish an artificial intelligence-based surgical selection system utilizing deep learning to assist in the decision-making process for lumbar endoscopic surgery.Methods:General data of 1,110 patients who underwent percutaneous transforaminal endoscopic discectomy, 804 patients who underwent percutaneous interlaminar endoscopic discectomy, 923 patients who underwent mobile microendoscopic discectomy and 623 patients who underwent unilateral biportal endoscopic in Tianjin Hospital from January 2018 to June 2023 were included in the study. Clinical outcomes were assessed using the visual analogue scale (VAS) for leg and back pain, the Oswestry disability index (ODI), and MacNab criteria both before surgery and 12 months postoperatively. Using a random number table method, patients were divided into a training dataset (2,768 cases) and a test dataset (692 cases) at a ratio of 4∶1. Patient clinical symptoms, physical signs, and multi-modal imaging data were input into a deep learning model. This model was structured into three main modules: intervertebral disc detection, surgical necessity identification, and surgical recommendation. The final surgical method was determined using a convolutional neural network incorporating U-Net for segmentation and ResNet for classification. The accuracy and recall rates of each module were evaluated using the test dataset.Results:Compared to preoperative values, all patients showed significant improvements at the 12-month postoperative follow-up. For patients who underwent percutaneous transforaminal endoscopic discectomy, percutaneous interlaminar endoscopic discectomy, mobile microendoscopic discectomy, and unilateral biportal endoscopic surgery, the VAS scores for leg pain decreased from 7.69±0.80, 7.82±0.88, 7.62±0.69, and 7.56±1.00 preoperatively to 1.44±1.09, 1.35±0.82, 1.51±1.08, and 1.43±0.91 postoperatively. Similarly, the VAS scores for back pain decreased from 5.73±0.83, 6.17±0.99, 6.11±0.88, and 6.46±0.95 to 0.93±0.75, 1.01±0.67, 1.40±0.72, and 1.27±0.70, respectively. Additionally, the ODI significantly decreased from 39.91%±4.50%, 40.05%±8.05%, 47.08%±9.50%, and 44.43%±4.71% preoperatively to 5.77%±2.22%, 6.05%±2.31%, 8.51%±2.16%, and 9.51%±3.70% postoperatively, with all differences being statistically significant ( P<0.05). The excellent rate according to the MacNab criteria was 93.12% (3,222/3,460). In the deep learning model, the multi-modal data of 2,768 patients were input in the training set for deep learning to form a surgical identification and operation recommendation system, and the preoperative data of 692 patients were input in the test set to compare with the final operation method. In the intervertebral disc location module, the accuracy of location and designation of the five lumbar intervertebral discs was 97.1%(672/692). In the module of intervertebral disc need for surgery, the accuracy was 94.8%(3,280/3,460) and the recall rate was 91.9%(636/692). As for patients, the accuracy rate was 91.9%(636/692). In the operation recommendation module, the accuracy rate of operation recommendation based on intervertebral disc was 89.5%(569/636), and the accuracy rate of surgical recommendation based on patient was 82.2%(569/692). Conclusion:In this study, an artificial intelligent surgical procedures selection system based on deep learning was established, which could effectively integrate relevant data and accurately guide the selection of lumbar endoscopic surgery.

Objective:To compare the diagnostic values of C-TIRADS, ACR-TIRADS and EU-TIRADS.Methods:According to the classification methods of the 3 guidelines, the ultrasonographic features of 283 thyroid nodules from 266 patients in Sir Run Run Shaw Hospital from January 2019 to June 2020 were analyzed retrospectively. The pathological results were taken as the gold standard, the malignant percentage of different classification was calculated, the ROC curve was plotted, the area under the ROC curve (AUC) and the best diagnostic cut-off value were calculated, and the diagnostic values of the three guidelines were compared. According to the FNA recommendations of the guidelines, the recommended number of thyroid nodules and the detection rate of malignant nodules in different guidelines were analyzed.Results:The AUCs of C-TIRADS, ACR-TIRADS and EU-TIRADS were 0.80, 0.66, 0.61, respectively. The AUC of C-TIRADS was higher than those of ACR-TIRADS and EU-TIRADS ( P<0.001, P<0.001). The best diagnostic cutoff values of C-TIRADS, ACR-TIRADS and EU-TIRADS were 4C, 5 and 5, respectively. Under the critical points, the sensitivities of the 3 guidelines were 95.27%, 98.10%, 99.53%, the specificities were 54.17%, 33.33%, 20.83%, respectively. There was no significant difference in the number of FNA recommendations among the 3 guidelines(all P>0.05), their FNA recommendations were highly consistent (Kappa>0.9). Conclusions:The diagnostic value of C-TIRADS in the classification of benign and malignant thyroid nodules is higher than those of ACR-TIRADS and EU-TIRADS. The best critical value for diagnosis of thyroid nodules is C-TIRADS 4C. The three guidelines are similar in the number of FNA recommendations and the detection rate of malignancy.