Objective:To apply artificial intelligence（AI）in classifying ovarian tumors on ultrasound images，and compare the diagnostic results of several sonographers with varying seniority levels.Methods:A total of 645 patients diagnosed with adnexal masses via gynecological ultrasound examination at Qilu Hospital of Shandong University from January 2021 to December 2024 were enrolled. Three deep learning architectures，i.e.，Alexnet，Densenet121，and Resnet50 were developed and used to internally test the classification effectiveness of ovarian tumors，while the optimal model was selected for external testing. Two junior sonographers and two senior sonographers were recruited to independently diagnose ovarian tumors in the external test dataset. Subsequently，the benign and malignant results of the model's predictions were disclosed to each sonographer，and their revised diagnoses on the same external test data in combination with the best AI model were recorded.Results:The optimal model achieved an accuracy of 0.941，sensitivity of 0.936，and specificity of 0.944 on the internal test dataset，and maintained robust performance on the external test dataset with accuracy of 0.891，sensitivity of 0.880，and specificity of 0.907. Compared to junior sonographers，the optimal model demonstrated significantly higher sensitivity in discriminating benign from malignant ovarian tumors（0.880 vs. 0.723，0.602；all P<0.05）. No statistically significant difference was observed in diagnostic accuracy between the optimal model and senior sonographer 1（ P=0.05）. With assistance from the optimal model，junior sonographers achieved significant improvements in both sensitivity and specificity（sensitivity：0.723 vs. 0.843，0.602 vs. 0.819；specificity：0.778 vs. 0.833，0.685 vs. 0.741；all P<0.05）. Conclusions:The optimal model achieves comparable performance to that of senior sonographers in ovarian tumor classification. With model assistance，the diagnostic performance of junior sonographers is significantly improved.

Objective:To apply artificial intelligence（AI）in classifying ovarian tumors on ultrasound images，and compare the diagnostic results of several sonographers with varying seniority levels.Methods:A total of 645 patients diagnosed with adnexal masses via gynecological ultrasound examination at Qilu Hospital of Shandong University from January 2021 to December 2024 were enrolled. Three deep learning architectures，i.e.，Alexnet，Densenet121，and Resnet50 were developed and used to internally test the classification effectiveness of ovarian tumors，while the optimal model was selected for external testing. Two junior sonographers and two senior sonographers were recruited to independently diagnose ovarian tumors in the external test dataset. Subsequently，the benign and malignant results of the model's predictions were disclosed to each sonographer，and their revised diagnoses on the same external test data in combination with the best AI model were recorded.Results:The optimal model achieved an accuracy of 0.941，sensitivity of 0.936，and specificity of 0.944 on the internal test dataset，and maintained robust performance on the external test dataset with accuracy of 0.891，sensitivity of 0.880，and specificity of 0.907. Compared to junior sonographers，the optimal model demonstrated significantly higher sensitivity in discriminating benign from malignant ovarian tumors（0.880 vs. 0.723，0.602；all P<0.05）. No statistically significant difference was observed in diagnostic accuracy between the optimal model and senior sonographer 1（ P=0.05）. With assistance from the optimal model，junior sonographers achieved significant improvements in both sensitivity and specificity（sensitivity：0.723 vs. 0.843，0.602 vs. 0.819；specificity：0.778 vs. 0.833，0.685 vs. 0.741；all P<0.05）. Conclusions:The optimal model achieves comparable performance to that of senior sonographers in ovarian tumor classification. With model assistance，the diagnostic performance of junior sonographers is significantly improved.

OBJECTIVE To explore the predictive factors of cefoperazone/sulbactam-induced thrombocytopenia in adult inpatients， and to establish and validate the nomogram prediction model. METHODS Data of adult inpatients treated with cefoperazone/sulbactam in Xi’an Central Hospital from Jun. 30th， 2021 to Jun. 30th， 2023 were retrospectively collected. The training set and internal validation set were randomly constructed in a 7∶3 ratio. Singler factor and multifactor Logistic regression analysis were used to screen the independent predictors of cefoperazone/sulbactam-induced thrombocytopenia. The nomogram was drawn by using “RMS” of R 4.0.3 software， and the predictive performance of the model was evaluated by the receiver operating characteristic curve and C-index curve. Hosmer-Lemeshow goodness-of-fit test was used to evaluate the calibration degree of the model. Using the same standard， the clinical data of hospitalized patients receiving cefoperazone/sulbactam in Xi’an First Hospital in the same period were collected for external validation of the nomogram prediction model. RESULTS A total of 1 045 patients in Xi’an Central Hospital were included in this study， among which 67 patients suffered from cefoperazone/sulbactam-induced thrombocytopenia， with an incidence of 6.41%. After the false positive patients were excluded， 473 patients were included finally， including 331 in the training set and 142 in theinternal validation set. Multifactor Logistic regression analysis showed that age [OR＝1.043， 95%CI （1.017， 1.070）]， estimated glomerular filtration rate （eGFR） [OR＝0.988，95%CI（0.977， 0.998）]， baseline platelet （PLT） [OR＝0.989， 95%CI（0.982， 0.996）]， nutritional risk [OR＝3.863， 95%CI（1.884， 7.921）] and cumulative defined daily doses （DDDs） [OR＝1.082， 95%CI（1.020， 1.147）] were independent predictors for cefoperazone/sulbactam-induced thrombocytopenia （P＜0.05）. The C-index values of the training set and the internal validation set were 0.824 [95%CI （0.759， 0.890）] and 0.828 [95%CI （0.749， 0.933）]， respectively. The results of the Hosmer-Lemeshow test showed that χ 2 values were 0.441 （P＝0.802） and 1.804 （P＝0.406）. In the external validation set， the C-index value was 0.808 [95%CI （0.672， 0.945）]， the χ 2 value of the Hosmer-Lemeshow test was 0.899 （P＝0.638）. CONCLUSIONS The independent predictors of cefoperazone/sulbactam-induced thrombocytopenia include age， baseline PLT， eGFR， nutritional risk and cumulative DDDs. The model has good predictive efficacy and extrapolation ability， which can help clinic identify the potential risk of cefoperazone/sulbactam-induced thrombocytopenia quickly and accurately.

Liver failure progresses quickly with high mortality. Non-biological artificial liver support system therapy is one of the important treatments for patients with liver failure. The basic techniques of non-biological artificial liver support system therapy include plasma exchange, plasma adsorption and continuous renal replacement therapy. In this paper, the effect and choice of these basic techniques, the treatment timing, the possible patients who may benefit, and the existing problems are summarized and discussed. We hope to provide a reference for the rational use of non-biological artificial liver support system therapy in clinical practice.

Drugs may induce hepatitis B virus (HBV) reactivation (HBV-R). Here we have reviewed the definition and harm of HBV-R, the risk drugs and their underlying mechanism, the influence factors, as well as the early intervention measures. It is shown that multiple drugs, including chemotherapy drugs, immunotherapy drugs, directly acting antivirals, cell therapy, etc., can induce HBV-R by affecting host immunity or directly activating HBV transcription factors. HBV-R could cause severe liver damage, even interruption of treatment of original diseases, affecting the prognosis of patients. Through precisely identifying risk drugs, monitoring the influence factors, and prescribing preventive anti-HBV regimen if necessary, the incidence of HBV-R can be significantly reduced. It is also suggested that clinical physicians should not only pay attention to the early identification and intervention of HBV-R, but also further study the mechanism of HBV-R in depth, especially the underlying mechanism between host, HBV and risk factors. This will help to promote the discovery of more valuable markers for risk prediction and targets for early intervention, and to further reduce the risk of HBV-R and improve the prognosis of patients.
Hepatitis B virus ; Humans ; Immunotherapy ; Risk Factors

Coagulation disorder is one of the characteristics of liver failure, leading to an unstable and vulnerable "rebalance" state of coagulation function, which may be easily broken by internal or external factors. Anticoagulants are often required during artificial liver support therapy for patients with liver failure, which may break the "rebalance" state and result in bleeding events. This article reviews the methods for evaluating coagulation status in liver failure, the features of available anticoagulants, and the advances in the application of such anticoagulants in artificial liver support therapy and discusses the anticoagulation management and selection strategy for artificial liver support therapy with reference to the selection experience of West China Hospital of Sichuan University.

Objective:To understand the management status of suspected unexpected serious adverse reaction (SUSAR) reports in clinical trial sites in China after the release of the 2020 edition of Good Clinical Practice (new GCP).Methods:The serious adverse event (SAE)/SUSAR reporting requirements files in each site as of June 30, 2021 were downloaded after logging into the "summary of SAE/SUSAR reporting requirements in national sites under the new GCP" platform on an APP named Yaoyanshe (药研社). The requirements on SUSAR reporting management from above files in each site were extracted, including the acceptance process of the SUSAR reports submitted by the clinical trial sponsor and the processing process after receiving the reports (whether the investigator is required to sign for reading and evaluating theSUSAR reports, the time limit and form/format for the investigator to submit the SUSAR reports to the clinical trial institution and the ethics committee, and the processing method in the clinical trial institution and the ethics committee after receiving the SUSAR reports). The collected data were analyzed by descriptive statistics.Results:The SUSAR reporting requirements files in the analysis were collected from 194 sites in 30 provincial administrative regions across the country. In the acceptance process of SUSAR reports submitted by the sponsor, 69.6% (135/194) of the sites required the investigators to sign for reading and evaluating the SUSAR reports, 24.2% (47/194) required the sponsor to submit the SUSAR reports to the clinical trial institution and/or ethics committee, and 6.2% (12/194) had no clear requirements. In the processing process after receiving the reports, 85.1% (165/194) of the sites required the investigators to submit the SUSAR reports to the clinical trial institution and the ethics committee at the same time, 13.4% (26/194) only required the investigators to submit them to the ethics committee, and 1.5% (3/194) had no clear requirements. Except that 1.0% (2/194) sites had no explicit requirements, for lethal/life-threatening SUSAR, 94.3% (183/194), 2.6% (5/194), and 2.1% (4/194) sites required investigators to submit the reports within 7 days, monthly, and quarterly, respectively. Except that 2.6% (5/194) sites had no explicit requirements, for non lethal/life-threatening SUSAR, 54.6% (106/194), 12.9% (25/194), 29.4% (57/194), and 0.5% (1/194) sites required investigators to submit the reports within 15 d, monthly, quarterly, and semiannually, respectively. Requirements on the form/format of SUSAR reports for investigators in submitting were different among sites. Only 12.9% (25/194) of the sites required the ethics committee to filing or meeting in handling of SUSAR reports, and 5.7% (11/194) required feedback on the handling opinions from the ethics committee.Conclusions:Requirements on SUSAR reporting are of great differences among sites. The management of SUSAR reports in some sites does not meet the requirements in the new GCP, which may affect the risk control in clinical trials and need to be further standardized.

Objective:To understand the management status of suspected unexpected serious adverse reaction (SUSAR) reports in clinical trial sites in China after the release of the 2020 edition of Good Clinical Practice (new GCP).Methods:The serious adverse event (SAE)/SUSAR reporting requirements files in each site as of June 30, 2021 were downloaded after logging into the "summary of SAE/SUSAR reporting requirements in national sites under the new GCP" platform on an APP named Yaoyanshe (药研社). The requirements on SUSAR reporting management from above files in each site were extracted, including the acceptance process of the SUSAR reports submitted by the clinical trial sponsor and the processing process after receiving the reports (whether the investigator is required to sign for reading and evaluating theSUSAR reports, the time limit and form/format for the investigator to submit the SUSAR reports to the clinical trial institution and the ethics committee, and the processing method in the clinical trial institution and the ethics committee after receiving the SUSAR reports). The collected data were analyzed by descriptive statistics.Results:The SUSAR reporting requirements files in the analysis were collected from 194 sites in 30 provincial administrative regions across the country. In the acceptance process of SUSAR reports submitted by the sponsor, 69.6% (135/194) of the sites required the investigators to sign for reading and evaluating the SUSAR reports, 24.2% (47/194) required the sponsor to submit the SUSAR reports to the clinical trial institution and/or ethics committee, and 6.2% (12/194) had no clear requirements. In the processing process after receiving the reports, 85.1% (165/194) of the sites required the investigators to submit the SUSAR reports to the clinical trial institution and the ethics committee at the same time, 13.4% (26/194) only required the investigators to submit them to the ethics committee, and 1.5% (3/194) had no clear requirements. Except that 1.0% (2/194) sites had no explicit requirements, for lethal/life-threatening SUSAR, 94.3% (183/194), 2.6% (5/194), and 2.1% (4/194) sites required investigators to submit the reports within 7 days, monthly, and quarterly, respectively. Except that 2.6% (5/194) sites had no explicit requirements, for non lethal/life-threatening SUSAR, 54.6% (106/194), 12.9% (25/194), 29.4% (57/194), and 0.5% (1/194) sites required investigators to submit the reports within 15 d, monthly, quarterly, and semiannually, respectively. Requirements on the form/format of SUSAR reports for investigators in submitting were different among sites. Only 12.9% (25/194) of the sites required the ethics committee to filing or meeting in handling of SUSAR reports, and 5.7% (11/194) required feedback on the handling opinions from the ethics committee.Conclusions:Requirements on SUSAR reporting are of great differences among sites. The management of SUSAR reports in some sites does not meet the requirements in the new GCP, which may affect the risk control in clinical trials and need to be further standardized.

Plasma exchange therapy is applied for treatment of severe immune diseases of multiple organ systems and severe liver diseases by removing pathogenic factors and regulating immune function. Regional citrate anticoagulation has no effect on systemic coagulation function and does not increase bleeding risk, and it is one of the optional anticoagulation methods for plasma exchange therapy. This article reviews recent literature on simple plasma exchange therapy with regional citrate anticoagulation to provide a reference for clinical application of this therapy.

Liver failure is a rapidly progressive condition with a high mortality rate. Artificial liver treatment is one of the most important treatments for liver failure. In order to ensure the smooth functioning of in vitro circulation device, anticoagulants such as heparin or low-molecular-weight heparin are often used in clinical practice. However, it induces hemorrhage, thrombocytopenia and other adverse reactions, thereby threatening the life safety of liver failure patients. Regional citrate anticoagulation does not affect the coagulation mechanism in vivo, nor does it effects platelets, so in vitro circulating anticoagulants has become the first choice anticoagulant treatment method for continuous renal replacement therapy. Combined with the current research condition at home and abroad, the research progress of the application of regional citrate anticoagulation in artificial liver to treat liver failure is discussed, covering its principle content, application status and application prospect.