Objective:To investigate the application value of risk prediction model for acute kidney injury (AKI) after donation of cardiac death (DCD) liver transplantation based on machine learning algorithm.Methods:The retrospective cohort study was conducted. The clinicopathological data of 1 001 pairs of DCD liver transplant donors and recipients at five hospitals, including The First Affiliated Hospital of Zhejiang University School of Medicine et al, in the Chinese Liver Transplan-tation Registry from January 2015 to December 2023 were collected. Of the donors, there were 825 males and 176 females. Of the recipients, there were 806 males and 195 females, aged 52 (range, 18-75)years. There were 281 recipients included using oversampling technique, and all 1 282 recipients were divided to the training set of 897 recipients and the validation set of 385 recipients by a ratio of 7∶3 using computer-generated random numbers. Seven prediction models, including Random Forest (RF), Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), Logistic Regression (LR), Decision Tree (DT), K-Nearest Neighbors (KNN), and Categorical Boosting (CatBoost), were constructed for AKI after liver transplantation based on machine learning algorithm. Observation indicators: (1) comparison of clinicopathological characteristics between recipients with and without AKI and donors; (2) follow-up and survival of recipients with and without AKI; (3) construction and validation of nomogram prediction model of AKI after liver transplantation; (4) construction and validation of machine learning prediction model of AKI after liver transplantation. Comparison of measurement data with normal distribution between groups was conducted using the independent sample t test. Comparison of measurement data with skewed distribution between groups was conducted using the Mann-Whitney U test, and comparison among groups was conducted using the Kruskal-Wallis H test. Comparison of count data between groups was conducted using the chi-square test or corrected chi-square test. Kaplan-Meier method was used to calculate survival rates and plot survival curves. Logistic regression model was performed for univariate and multivariate analyses. The receiver operating characteristic (ROC) curve was plotted to calculate area under curve (AUC) and 95% confidence interval ( CI). The performance of prediction model was evaluated using DeLong test, accuracy, sensitivity, specificity. The calibration curve was plotted to evaluate the performance of predicted probability and actual probability. The interpretability analysis of machine learning algorithm and SHapley Additive exPlanations was used to explain the model decision separately. Results:(1) Comparison of clinicopathological characteristics between recipients with and without AKI and donors. Of 1 001 recipients, there were 360 cases with AKI and 641 cases without AKI after liver transplantation. There were significant differences in body mass index (BMI), hepatic encepha-lopathy, hepatitis B surfact antigen (HBsAg), hepatorenal syndrome (HRS) and donor diabetes, donor blood urea nitrogen, donor alanine aminotransferase, donor aspartate aminotransferase, mass of graft, volume of blood loss during liver transplantation, warm ischema time of donor liver, and operation time between recipients with and without AKI ( Z=-4.337, χ2=9.751, 9.088, H=11.142, χ2=5.286, Z=-3.360, -2.539, -3.084, -1.730, -3.497, -1.996, -2.644, P<0.05). (2) Follow-up and survival of recipients with and without AKI. All the 1 001 recipients received follow-up. The recipients with AKI after liver transplantation were followed up for 18.6(range, 0-102.3)months, and recipients without AKI after liver transplantation were followed up for 31.9(range, 0.1-105.5)months. The 1-, 3-, and 5-year overall survival rates were 72.1%, 63.5%, and 59.3% of recipients with AKI, versus 86.7%, 76.7%, and 72.5% of recipients without AKI, respectively, showing a significant difference in overall survival between them ( χ2=26.028, P<0.05). (3) Construction and validation of nomogram predic-tion model of AKI after liver transplantation. Results of multivariate analysis showed that recipient BMI, recipient creatinine, recipient HBsAg, recipient HRS, donor blood urea nitrogen, donor crea-tinine, anhepatic phase and volume of blood loss during liver transplantation were independent risk factors for AKI of recipients after liver transplantation ( odds ratio=1.113, 0.998, 0.605, 1.580, 1.047, 0.998, 1.006, 1.157, 95% CI as 1.070-1.157, 0.996-1.000, 0.450-0.812, 1.021-2.070, 1.021-1.074, 0.996-0.999, 1.000-1.012, 1.045-1.281, P<0.05). The nomogram prediction model of AKI after liver transplantation was constructed based on the results of multivariate analysis. Results of ROC curve showed that the AUC of 0.666 (95% CI as 0.637-0.696). (4) Construction and validation of machine learning prediction model of AKI after liver transplantation. Based on the Lasso regression analysis, seven machine learning algorithm prediction models, including RF, XGBoost, SVM, LR, DT, KNN, and CatBoost, were constructed, with ROC curves of the validation set plotted. The AUC of above models were 0.863, 0.841, 0.721, 0.637, 0.620, 0.708, 0.731, accuracies were 0.764, 0.782, 0.701, 0.592, 0.605, 0.605, 0.681, sensitivities were 0.764, 0.789, 0.719, 0.588, 0.694, 0.694, 0.704, specificities were 0.763, 0.774, 0.683, 0.597, 0.511, 0.511, 0.656, respectively. Delong test showed that the RF model with the highest AUC of 0.863(95% CI as 0.828-0.899). Calibration curve analysis showed the predicted probability closest to the actual probability of RF model, indicating the model with a good validation value. Further sorting of SHAP of different clinical factors based on RF model showed that recipient BMI, donor blood urea nitrogen, volume of blood loss during liver transplantation, donor age had large effects on the output outcomes. Conclusion:The nomogram prediction model and seven machine learning algorithm prediction models for AKI after DCD liver transplantation are constructed, and the RF model based on machine learning has a better predictive performance.

Objective:To investigate the application value of risk prediction model for acute kidney injury (AKI) after donation of cardiac death (DCD) liver transplantation based on machine learning algorithm.Methods:The retrospective cohort study was conducted. The clinicopathological data of 1 001 pairs of DCD liver transplant donors and recipients at five hospitals, including The First Affiliated Hospital of Zhejiang University School of Medicine et al, in the Chinese Liver Transplan-tation Registry from January 2015 to December 2023 were collected. Of the donors, there were 825 males and 176 females. Of the recipients, there were 806 males and 195 females, aged 52 (range, 18-75)years. There were 281 recipients included using oversampling technique, and all 1 282 recipients were divided to the training set of 897 recipients and the validation set of 385 recipients by a ratio of 7∶3 using computer-generated random numbers. Seven prediction models, including Random Forest (RF), Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), Logistic Regression (LR), Decision Tree (DT), K-Nearest Neighbors (KNN), and Categorical Boosting (CatBoost), were constructed for AKI after liver transplantation based on machine learning algorithm. Observation indicators: (1) comparison of clinicopathological characteristics between recipients with and without AKI and donors; (2) follow-up and survival of recipients with and without AKI; (3) construction and validation of nomogram prediction model of AKI after liver transplantation; (4) construction and validation of machine learning prediction model of AKI after liver transplantation. Comparison of measurement data with normal distribution between groups was conducted using the independent sample t test. Comparison of measurement data with skewed distribution between groups was conducted using the Mann-Whitney U test, and comparison among groups was conducted using the Kruskal-Wallis H test. Comparison of count data between groups was conducted using the chi-square test or corrected chi-square test. Kaplan-Meier method was used to calculate survival rates and plot survival curves. Logistic regression model was performed for univariate and multivariate analyses. The receiver operating characteristic (ROC) curve was plotted to calculate area under curve (AUC) and 95% confidence interval ( CI). The performance of prediction model was evaluated using DeLong test, accuracy, sensitivity, specificity. The calibration curve was plotted to evaluate the performance of predicted probability and actual probability. The interpretability analysis of machine learning algorithm and SHapley Additive exPlanations was used to explain the model decision separately. Results:(1) Comparison of clinicopathological characteristics between recipients with and without AKI and donors. Of 1 001 recipients, there were 360 cases with AKI and 641 cases without AKI after liver transplantation. There were significant differences in body mass index (BMI), hepatic encepha-lopathy, hepatitis B surfact antigen (HBsAg), hepatorenal syndrome (HRS) and donor diabetes, donor blood urea nitrogen, donor alanine aminotransferase, donor aspartate aminotransferase, mass of graft, volume of blood loss during liver transplantation, warm ischema time of donor liver, and operation time between recipients with and without AKI ( Z=-4.337, χ2=9.751, 9.088, H=11.142, χ2=5.286, Z=-3.360, -2.539, -3.084, -1.730, -3.497, -1.996, -2.644, P<0.05). (2) Follow-up and survival of recipients with and without AKI. All the 1 001 recipients received follow-up. The recipients with AKI after liver transplantation were followed up for 18.6(range, 0-102.3)months, and recipients without AKI after liver transplantation were followed up for 31.9(range, 0.1-105.5)months. The 1-, 3-, and 5-year overall survival rates were 72.1%, 63.5%, and 59.3% of recipients with AKI, versus 86.7%, 76.7%, and 72.5% of recipients without AKI, respectively, showing a significant difference in overall survival between them ( χ2=26.028, P<0.05). (3) Construction and validation of nomogram predic-tion model of AKI after liver transplantation. Results of multivariate analysis showed that recipient BMI, recipient creatinine, recipient HBsAg, recipient HRS, donor blood urea nitrogen, donor crea-tinine, anhepatic phase and volume of blood loss during liver transplantation were independent risk factors for AKI of recipients after liver transplantation ( odds ratio=1.113, 0.998, 0.605, 1.580, 1.047, 0.998, 1.006, 1.157, 95% CI as 1.070-1.157, 0.996-1.000, 0.450-0.812, 1.021-2.070, 1.021-1.074, 0.996-0.999, 1.000-1.012, 1.045-1.281, P<0.05). The nomogram prediction model of AKI after liver transplantation was constructed based on the results of multivariate analysis. Results of ROC curve showed that the AUC of 0.666 (95% CI as 0.637-0.696). (4) Construction and validation of machine learning prediction model of AKI after liver transplantation. Based on the Lasso regression analysis, seven machine learning algorithm prediction models, including RF, XGBoost, SVM, LR, DT, KNN, and CatBoost, were constructed, with ROC curves of the validation set plotted. The AUC of above models were 0.863, 0.841, 0.721, 0.637, 0.620, 0.708, 0.731, accuracies were 0.764, 0.782, 0.701, 0.592, 0.605, 0.605, 0.681, sensitivities were 0.764, 0.789, 0.719, 0.588, 0.694, 0.694, 0.704, specificities were 0.763, 0.774, 0.683, 0.597, 0.511, 0.511, 0.656, respectively. Delong test showed that the RF model with the highest AUC of 0.863(95% CI as 0.828-0.899). Calibration curve analysis showed the predicted probability closest to the actual probability of RF model, indicating the model with a good validation value. Further sorting of SHAP of different clinical factors based on RF model showed that recipient BMI, donor blood urea nitrogen, volume of blood loss during liver transplantation, donor age had large effects on the output outcomes. Conclusion:The nomogram prediction model and seven machine learning algorithm prediction models for AKI after DCD liver transplantation are constructed, and the RF model based on machine learning has a better predictive performance.

Objective To investigate the effects of comprehensive nutrition management on glycolipid metabolism and pregnancy outcomes in patients with gestational diabetes mellitus(GDM).Methods A total of 121 pregnant women with GDM at 24-28 weeks gestation who were registered in the obstetrics department of 6 sub-central hospi-tals in China from May 2021 to July 2021 were included in this study and were randomly divided into intervention group(n=74)and control group(n=47).The intervention group received intensive comprehensive nutrition man-agement,including at least 6 outpatient interventions,individualized nutrition management and a half-day standard-ized outpatient education on gestational diabetes mellitus,continuous dynamic blood glucose monitoring and micro-blood glucose monitoring,and routine check of glycated albumin and urine every 4 weeks.Body weight,body com-position and diet and exercise implementation procedures and fetal development as well as complications were recor-ded.The control group received conventional nutritional guidance.The two groups were compared for difference in blood glucose related indicators at 37 weeks of gestation,weight gain before delivery,some lipid metabolism indica-tors,pregnancy outcomes,and oral glucose tolerance test(OGTT)at 42 days postpartum.Results Compared with the control group,the level of prenatal fasting blood glucose(P=0.006),intravenous plasma glucose(P=0.009)and blood ketone(P = 0.044)in the intervention group was significantly reduced.There was no significant difference in weight gain and weight attainment rate between the two groups.The 2-hour postpartum OGTTs of preg-nant women in the intervention group(P=0.006)were significantly lower than those in the control group,and the incidence of preeclampsia and postpartum blood loss were lower than those in the control group but no statistical difference was found.For newborns,the incidence of macrosomia(P=0.042)and planation(P=0.048)in the in-tervention group was slightly lower than that in the control group,and the results were statistically different.Other adverse pregnancy outcomes were not statistically different between the two groups.Conclusions Intensive compre-hensive nutrition management has a positive impact on the control of the blood glucose in pregnant women and im-proves the maternal and neonatal outcomes of women with GDM.

Stomach exuberance and spleen deficiency are common pathogenesis of many metabolic diseases. Through analyzing the pathogenesis of stomach exuberance and spleen deficiency， it is believed that its essence is stomach heat and spleen deficiency. Stomach heat includes gastrointestinal heat， spleen and stomach damp-heat， and spleen deficiency is divided into deficiency of spleen yin， deficiency of spleen qi ， and deficiency of spleen yang. It is suggested that the metabolic diseases of stomach-exuberance and spleen-deficiency syndrome can be divided into three categories，i.e. stomach-heat and spleen yin-deficiency， stomach-heat and spleen qi-deficiency， and stomach-heat and spleen yang-deficiency， and the main treatment methods are clearing and draining heat， nourishing yin and moistening intestine， clearing dampness and heat， strengthening spleen and qi， clearing dampness and heat， strengthening spleen and warming yang， respectively， with prescriptions as Maziren Pills （麻子仁丸）， Qinlian Pingwei Powder （芩连平胃散）， and Jiawei Lianli Decoction （加味连理汤） accordingly.

Objective To evaluate the effects of long voyage on crew's cardiac function.Methods A total of 47 crew members from a shipyard during the maintenance period of two ships with the same type from October 2017 to April 2018 were selected as research subjects.They were divided into experimental group(n=24)and control group(n=23).The first test was performed in all subjects within 5 days of enrollment.The experimental group participated in a 34-day seagoing voyage after the first test,while the control group continued to live on land and do regular physical exercise.All the subjects were tested again within 5 days after sailing.The submaximal exercise test was conducted according to the standard Bruce protocol.High definition impedance cardiogram was synchronously used to record heart rate and stroke output(SV)at rest.SV was continuously recorded to obtain its maximum value(SVmax)and the change of SV during exercise was analyzed.The exercise time,SV threshold,and SV threshold time were also recorded.Results There were no significant differences in the age,height,or weights at the beginning or end of the study between the two groups(P>0.05).At the end of the study,the exercise time of the experimental group was significantly shorter than that of the control group and the control group was prolonged(P<0.01).There was no significant difference in the SV threshold time,HR at rest,average resting SV,or SVmax between the two groups at enrollment(P>0.05).The SV threshold time at the end of the study was significantly shorter than that at enrollment in the experimental group,and there was a significant difference in the SV threshold time at the end of the study between the two groups(P<0.01).At the end of the study,the resting HR of the experimental group was significantly higher than that at enrollment and that of the control group(P<0.05);there were significant differences in the mean SV at rest and SVmax between groups and between intra-groups(P<0.05).Conclusion Long voyage can reduce the aerobic capacity and cardiac reserve of crew,and the preservation of aerobic exercise can improve the cardiac function and cardiac reserve.

Objective:To observe the multi-modal fundus imaging features of subretinal drusenoid deposit (SDD) in age-related macular degeneration (AMD), and observe image features.Methods:A prospective clinical study. From December 2019 to December 2023, 65 patients (104 eyes) with a diagnosis of AMD-SDD by spectral domain optical coherence tomography (SD-OCT) examination in Shandong Eye Hospital were included. All eyes were examined by best corrected visual acuity (BCVA), traditional color fundus photography (CFP), ultra-wide-angle scanning laser fundus imaging (UWF), multicolor scanning laser fundus imaging (MC) and SD-OCT. The standard MC images were obtained by using Spectralis HRA+OCT for MC examination. The multi-mode image characteristics of SDD were analyzed retrospectively. Area under curve (AUC) was used to evaluate the sensitivity and specificity of CFP, MC and UWF in detecting SDD.Results:Among 65 patients with SDD, 29 cases of males (52 eyes) and 36 cases of females (52 eyes) was included. There were 26 patients with unilateral SDD and 39 patients with bilateral SDD. The average age was (71.74±10.97) years. The early, middle and late stages of AMD were 31 (29.8%, 31/104), 24 (23.1%, 24/104), 49 (47.1%, 49/104) eyes, respectively. The SDD detected by CFP, MC and UWF was 76 (73.1%, 76/104), 94 (90.4%, 94/104), 96 (92.3%, 96/104) eyes. CFP showed that the edge of SDD in the macular area was blurred. UWF showed that the dot and the ribbon SDD were light yellow pale discrete deposits and light yellow interlaced network deposits respectively. MC showed the dot SDD had a strong yellow-green circular reflection, while the edge of the ribbon SDD was surrounded by a weak reflection, and the boundary was clear. SD-OCT showed that SDD had strong reflection signal, which was located between the retinal pigment epithelium layer and the photoreceptor cell layer. The dot SDD could break through the ellipsoid zone and caused slight uplift or interruption of the external membrane, showing a cone-like strong reflection signal. While the ribbon SDD showed a continuous "hill-like" protrusion, which hardly broke through ellipsoid zone. The sensitivity and specificity of CFP, MC and UWF for SDD were 73.1%, 90.4%, 92.3% and 61.1%, 94.4% and 83.3%, respectively.Conclusions:MC and UWF show high sensitivity and specificity in diagnosing AMD-SDD, which is superior to CFP. SD-OCT can effectively reveal the location and morphoLogical characteristics of SDD under retina.

NK/T cell leukemia/lymphoma is a type of malignancy originating from T cells or natural killer cells with low incidence and poor clinical prognosis. There is still no effective treatment strategy. In recent years, targeted therapy has made great progress in the treatment of hematological malignancies, including monoclonal antibody and chimeric antigen receptor T cells (CAR-T), among which CD30, CD7, CD5, CD52, CCR4 and other target antigens are effective in the treatment of NK/T cell leukemia/lymphoma, but its widespread application still faces a great challenge. This article reviews the progress of immunotherapy for NK/T cell leukemia/lymphoma.

Pouchitis is a common complication of ileal pouch anal anastomosis (IPAA) in patients with ulcerative colitis or familial adenomatous polyposis and the mechanism is unknown. The dietary factors including dietary ingredients and mode are related to the occurrence and progression of pouchitis. Dietary factors may play a potential role in changing gut microbiome and regulating immune response. Therefore, adjusting the diet can prevent and treat pouchitis. This article reviews the research progress of the influence of dietary factors on pouchitis.

Pouchitis is a common complication of ileal pouch anal anastomosis (IPAA) in patients with ulcerative colitis or familial adenomatous polyposis and the mechanism is unknown. The dietary factors including dietary ingredients and mode are related to the occurrence and progression of pouchitis. Dietary factors may play a potential role in changing gut microbiome and regulating immune response. Therefore, adjusting the diet can prevent and treat pouchitis. This article reviews the research progress of the influence of dietary factors on pouchitis.

Objective:To compare the efficacy and safety of venetoclax (VEN) combined with azacitidine (AZA) versus CAG regimen combined with decitabine (DAC) in elderly patients with relapsed acute myeloid leukemia (AML).Methods:From January 2018 to August 2020, the clinical data of forty-five elderly patients with relapse AML at the First Affiliated Hospital of Soochow University were retrospectively analyzed, including 31 males and 14 females. The median age was 66 (60-80) years old. Eighteen patients were administrated with VEN and AZA, while the other 27 were in CAG with DAC. The complete remission (CR) rate, partial remission (PR) rate, total remission rate (ORR), adverse events and overall survival (OS) were compared between the two groups.Results:At the end of the treatment, the ORR in VEN with AZA group was 77.8% (14/18); including 11 CR and 3 PR. In CAG with DAC group, the ORR was 37.0% (10/27); including 8 CR and 2 PR ( P=0.007). Subgroup analysis suggested that VEN with AZA had a higher ORR in patients stratified as intermediate and poor-risk ( P=0.013) or with DNA methylation mutations ( P=0.007). Main adverse events in both groups were bone marrow suppression, infections, nausea and vomiting, anorexia and fatigue. Grade Ⅲ-Ⅳ cytopenia developed in lower incidence of VEN with AZA group, such as leukopenia (66.7% vs. 100%, P=0.002), anemia (50.0% vs. 92.6%, P=0.002), thrombocytopenia (72.2% vs. 96.3%, P=0.031) and neutropenia (61.1% vs. 92.6%, P=0.014). In addition, less grade Ⅲ-Ⅳ infections occurred in VEN with AZA group (66.7% vs. 33.3%, P=0.028), as well as grade Ⅲ-Ⅳ gastrointestinal events (40.7% vs. 11.1%, P=0.032), grade Ⅲ-Ⅳ fatigue (55.6% vs.11.1%, P=0.003) compared with CAG with DAC group. The 1-year OS in VEN with AZA group versus CAG with DAC group was 42.9% and 31.6% respectively ( P=0.150). Conclusion:VEN combined with AZA proves favorable efficacy and tolerablity in elderly patients with relapsed AML.