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 analyze the implementation of MPOWER tobacco control policies in different regions and populations in China,as well as the impact of perceptions of tobacco control policies on individual smoking behavior and quit intentions,to promote the fairness of policy implementation and protection for vulnerable groups.Methods A multivariable regression model was constructed utilizing raw data from the China Adult Tobacco Survey to analyze disparities in perceived MPOWER policy implementation among various social demographics and its impact on smoking behavior and quitting intentions.Results Regarding protection from tobacco smoke(P),local economic level,urban-rural divide were significantly correlated with awareness of comprehensive smoking bans.For offering help to quit smoking(O),local tobacco industry revenue and individual age were associated with the doctor's advice for quitting.As to the warning about the harm of tobacco(W),economic level,geography and urban-rural disparity were correlated with the visibility of health warnings.About the tobacco advertising,promotion and sponsorship(E),geography was related to the exposure to tobacco advertisements,local tobacco industry revenue was associated with the tobacco promotion.For tobacco taxes(R),education level and age were significantly correlated with tobacco affordability.People who perceived comprehensive smoking bans(OR=0.69,95%CI:0.59-0.81)was associated with less smoking behavior,while people perceiving tobacco promotional activities(OR=2.51,95%CI:2.00-3.17)were more likely to smoke.Additionally,people who perceived comprehensive smoking bans(OR=1.70,95%CI:1.25-2.31)and health warning(OR=2.09,95%CI:1.48-3.01)had higher intention to quit smoking.Conclusion In economically disadvantaged regions and among specific socially vulnerable groups(such as low-income individuals,rural residents,and the elderly)in China,the perception of tobacco control policy implementation is relatively low,the perception of tobacco control policies can influence smoking behavior and quitting intentions.Legislative and enforcement efforts should be increased targeting these groups with lower perceptions of the policies to enhance the fairness of tobacco control measures.

Objective To compare TyG index between the patients with CHF and ADHF to eluci-date the metabolic difference between these two stages.Methods A total of 1156 HF patients ad-mitted in Taizhou People's Hospital between January 2020 and December 2022 were enrolled,and according to 2021 ESC Guidelines for Diagnosis and Treatment of Acute and Chronic Heart Fail-ure,they were divided into CHF group(365 cases)and ADHF group(791 cases).The clinical da-ta,results of laboratory tests,and cardiovascular history were collected,and TyG index was calcu-lated.All-cause death outcome was observed in ADHF patients during a follow-up of 1 year.Results The TyG index was significantly lower in the ADHF group than the CHF group[8.27(7.99,8.62)vs 8.35(8.04,8.75),P=0.001].In the ADHF group,the TyG index was positively correlated with SBP,DBP,TC,TG,LDL-C,FPG,HbA1c,BMI,and LVEF,and negatively with age(P＜0.01).In the CHF group,the index was positively correlated with DBP,TC,TG,LDL-C,FPG,BMI,and HbA1c,and negatively with age(P＜0.05,P＜0.01).Both univariate and multiva-riate logistic regression analyses indicated that the TyG index was a protective factor for ADHF(OR=0.647,95％CI:0.503～0.832,P=0.001;OR=0.694,95％CI:0.536～0.898,P=0.005).Multivariate logistic regression analysis showed that the index in ADHF patients was a protective factor for one-year all-cause mortality(OR=0.483,95％CI:0.254-0.916;P=0.026).Conclusion TyG index might be regarded as an important marker for assessing the metabolic status in HF patients and predicting the prognosis in ADHF patients.

Objective To construct a hybrid decision-making model that integrates knowledge-driven and data-driven approaches,and to apply it to the etiological diagnosis of ventricular tachycardia(VT).Methods Clinical practice guidelines,expert consensus documents,and medical literature in the field of ar-rhythmia diseases from 2018 to 2023 were retrieved as knowledge sources.Retrospective electronic medical re-cord data of VT patients from Fuwai Hospital,Chinese Academy of Medical Sciences & Peking Union Medical College,from 2013 to 2023 were collected as the dataset.A knowledge-driven model was constructed using a knowledge-rule-based approach to establish clinical pathways.A three-class machine learning model for VT eti-ology diagnosis was developed based on real-world data,and the best-performing model was selected as the rep-resentative of the data-driven approach.The machine learning model was embedded into the decision nodes of the clinical pathway in the form of custom operators,forming the hybrid model.The precision,recall,and F1 score of the three models were evaluated.Results Three clinical practice guidelines were included as knowl-edge sources for the knowledge-driven model.A total of 1305 patient records were collected as the dataset,and five machine learning models were constructed,with the XGBoost model performing the best.The hybrid model adopted a knowledge-driven decision-making framework,embedding the XGBoost model into the decision nodes of a two-level classification.The precision,recall,and F1 scores of the three models were as follows:the knowledge-driven model achieved 80.4％,79.1％,and 79.7％;the data-driven model achieved 88.4％,88.5％,and 88.4％;and the hybrid model achieved 90.4％,90.2％,and 90.3％.Conclusions The hybrid model integrating knowledge-driven and data-driven approaches demonstrated higher accuracy,and all its deci-sion outcomes were based on evidence-based practices,aligning more closely with the actual diagnostic reason-ing of clinicians.Further rigorous validation is needed to assess the feasibility of widely applying the hybrid model in the medical field.

Objective To compare TyG index between the patients with CHF and ADHF to eluci-date the metabolic difference between these two stages.Methods A total of 1156 HF patients ad-mitted in Taizhou People's Hospital between January 2020 and December 2022 were enrolled,and according to 2021 ESC Guidelines for Diagnosis and Treatment of Acute and Chronic Heart Fail-ure,they were divided into CHF group(365 cases)and ADHF group(791 cases).The clinical da-ta,results of laboratory tests,and cardiovascular history were collected,and TyG index was calcu-lated.All-cause death outcome was observed in ADHF patients during a follow-up of 1 year.Results The TyG index was significantly lower in the ADHF group than the CHF group[8.27(7.99,8.62)vs 8.35(8.04,8.75),P=0.001].In the ADHF group,the TyG index was positively correlated with SBP,DBP,TC,TG,LDL-C,FPG,HbA1c,BMI,and LVEF,and negatively with age(P＜0.01).In the CHF group,the index was positively correlated with DBP,TC,TG,LDL-C,FPG,BMI,and HbA1c,and negatively with age(P＜0.05,P＜0.01).Both univariate and multiva-riate logistic regression analyses indicated that the TyG index was a protective factor for ADHF(OR=0.647,95％CI:0.503～0.832,P=0.001;OR=0.694,95％CI:0.536～0.898,P=0.005).Multivariate logistic regression analysis showed that the index in ADHF patients was a protective factor for one-year all-cause mortality(OR=0.483,95％CI:0.254-0.916;P=0.026).Conclusion TyG index might be regarded as an important marker for assessing the metabolic status in HF patients and predicting the prognosis in ADHF patients.

AIM To investigate the promotional effects of esculin combined with bone marrow mesenchymal stem cells(BM-MSCs)transplantation on the repair of spinal cord injury(SCI)in rats.METHODS The rats were randomly divided into the sham operation group,the model group,the esculin group for gavage of 20 mg/kg esculin,the BM-MSCs group for tail vein injection of 1 mL of 1×106/mL BM-MSCs,and the combinaiton treatment group.The SCI rat model was established using Allen's method,followed by the 14 days consecutive corresponding drug administration starting from the 2nd day after modeling.On days 3,7 and 14 of drug administration,the rats had their hind limbs motor function evaluated by the BBB scoring;and their footprint experiment conducted on the 14th day after modeling.After 14 days of administration,the rats had their morphological changes of spinal cord tissue observed with HE staining and Nissl staining;their activities of SOD and GSH,and level of MDA in spinal cord tissue detected by kits;their expressions of MAP2,GAP43 and GFAP in spinal cord tissue detected by immunofluorescence;and their expressions of NQO-1,Nrf-2,Bcl-2 and Bax proteins in spinal cord tissue detected by Western blot.RESULTS Compared with the model group,the groups interved with esculin,or BM-MSCs,or the combination treatment showed improvements in hind limb function and spinal cord tissue morphology(P＜0.05);decreased MDA levels(P＜0.05);increased SOD and GSH activities(P＜0.05);increased MAP2 and GAP43 fluorescence intensity(P＜0.05);decreased GFAP fluorescence intensity(P＜0.05);increased NQO-1,Nrf-2 and Bcl-2 protein expressions(P＜0.05);and decreased Bax protein expression(P＜0.05).And the combination treatment group was observed with an even better effects(P＜0.05).CONCLUSION The combination of esculin and BM-MSCs transplantation can effectively improve the spinal cord tissue damage and hind limb function in SCI rats.This effect may be achieved by activating the Nrf-2/NQO-1 signaling pathway to inhibit oxidative stress response,thereby reducing neuronal apoptosis,blocking glial scar formation,and promoting stem cell differentiation to rebuild neurons.

Objective To explore the effects and mechanism of Shengxian Yixin Granules in treating ventricular remodeling in rats with myocardial infarction based on the PI3K/AKT signaling pathway.Methods A total of 60 SD rats were randomly selected six rats as the control group,and the remaining 54 rats were used as the modeling group.Sham-operation and left anterior descending coronary artery ligation were performed respectively.The modeled rats were divided into model group,Shengxian Yixin Granules group,740Y-P group and Shengxian Yixin Granules+740Y-P group,and were given corresponding intervention for 28 days.Left ventricular ejection fraction(LVEF)and left ventricular fractional shortening(LVFS)were measured by echocardiography,and left ventricular hypertrophy index was calculated,the myocardial morphology was observed by HE and Masson staining,and the protein expressions of p-PI3K,PI3K,p-AKT and AKT were detected by Western blot,RT-qPCR was used to detect the mRNA expressions of type Ⅰ collagen(Col1)and type Ⅲ collagen(Col3),and ELISA was used to detect the contents of serum cardiac troponin T(cTnT),creatine kinase-MB(CK-MB),Col1 and Col3.Results Compared with the control group,the LVEF and LVFS in the model group significantly decreased(P<0.01),the left ventricular hypertrophy index increased(P<0.01);myocardial cells were arranged disorderly,some cells were necrotic,ruptured and their nuclei were dissolved,with obvious neutrophil infiltration,the collagen fiber significantly increased,the protein expressions of p-PI3K and p-AKT in myocardial tissue significantly increased(P<0.05),and the mRNA expression of Col1 and Col3 significantly increased(P<0.01);the contents of serum cTnT,CK-MB,Col1 and Col3 significantly increased(P<0.05,P<0.01).Compared with the model group,the LVEF and LVFS in Shengxian Yixin Granules group significantly improved(P<0.05,P<0.01),and left ventricular hypertrophy index decreased(P<0.05);myocardial necrosis,neutrophil infiltration and collagen fiber deposition were reduced,the protein expressions of p-PI3K and p-AKT in myocardial tissue significantly decreased(P<0.05),and the mRNA expressions of Col1 and Col3 significantly decreased(P<0.01);the contents of serum cTnT,CK-MB,Col1 and Col3 significantly decreased(P<0.05,P<0.01).LVEF and LVFS in 740Y-P group significantly decreased(P<0.01),and left ventricular hypertrophy index increased(P<0.05);a large number of myocardial cells were necrotic and ruptured,fibers were torn obviously,and many scar tissues were formed,the protein expressions of p-PI3K and p-AKT in myocardial tissue significantly increased(P<0.05),the mRNA expressions of Col1 and Col3 significantly increased(P<0.01);the contents of serum cTnT,CK-MB,Col1 and Col3 significantly increased(P<0.05,P<0.01).Shengxian Yixin Granules+740Y-P could improve the damage of 740Y-P to the heart.Conclusion Shengxian Yixin Granules can improve ventricular remodeling in rats with heart failure,reduce myocardial fibrosis,and improve cardiac function through the PI3K/AKT signaling pathway.

Deutetrabenazine(DTBZ)is a selective oral small molecule inhibitor of vesicular monoamine transporter 2(VMAT2).Its pharmacological action works by inhibiting VMAT2,thereby reducing the release of presynaptic dopamine and alleviating tardive dyskinesia symptoms caused by long-term use of dopamine receptor antagonists.Compared with tetrabenazine,DTBZ has longer half-life,lower peak plasma concentration,and smaller plasma concentration fluctuations.Clinical studies demonstrate that DTBZ significantly improves abnormal involuntary movement in patients with tardive dyskinesia and has a favourable safety profile.Based on available clinical evidence and practical experience,this paper discuss the common questions about DTBZ including the suitable population,dose,duration of treatment,combination administration with antipsychotics,efficacy assessment and application in special populations.This article aimed to provide guidance and recommendations on clinical application of DTBZ for clinicians.

Objective To investigate the effects of ischemia time and storage periods on RNA quality in fresh-frozen breast cancer(BC)and esophageal cancer(EC)tissue samples in order to establish evidence-based protocols for biobank sample management.Methods The tumor(T)and paired normal(N)tissue samples from 6 cases of BC and 6 cases of EC were collected and cryopreserved in Biobank,Shantou Central Hospital.Mirror paraffin-embedded tissues were simultaneously prepared into sections for morphological analysis.The samples were divided into two groups of<15 min and 15-30 min according to ischemia time,and RNA quality was analyzed at 4 storage periods of 8-10 months(T1),14-16 months(T2),26-28 months(T3)and 38-40 months(T4).Results In 96 analyzed samples,93.8%(90/96)exhibited high quality(RIN≥6),with 89.6%(43/48)in BC and 97.9%(47/48)in EC.Significant differences in RIN were observed between BC group and EC group(8.050 vs.8.600,P=0.009).In EC group,RIN value was significantly negatively correlated with RNA yield(P<0.001).Moreover,RIN values of tumor-normal pairs exhibited markedly significant differences(7.550 vs.9.000,P<0.001).In contrast,no significant difference was detected in BC group(8.200 vs.7.700,P=0.348).Statistical analysis showed that RIN value was positively correlated with 28S/18S(P<0.001),but had no correlation with tumor content(P=0.676)and necrotic content(P=0.055).Neither ischemia time(<15 min vs.15-30 min:8.200 vs.8.300,P=0.932)nor storage periods(T1-T4:8.400,7.700,8.450,8.600,P=0.163)compromised RNA quality.Conclusion Organ origin and tissue type could influence RNA quality of fresh-frozen tissue samples.However,limited ischemia time(≤30 min)and long-term storage period(38-40 months)do not adversely affect RNA quality in fresh-frozen breast cancer and esophageal cancer tissue samples.

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.