Objective To construct and validate machine learning-based models to predict the risk of acute kidney injury(AKI)following percutaneous coronary intervention(PCI)in patients with acute ST-segment elevation myocardial infarction(STEMI).Methods A total of 2 315 STEMI patients who underwent PCI between January 2020 and June 2023 were included;306(13.2％)of them developed AKI.Baseline variables were screened using LASSO regression,with the optimal λ value selected via 10-fold cross-validation to identify AKI-associated features.Subsequently,eight distinct machine learning models were constructed and evaluated for their predictive performance.SHAP value analysis was employed to assess the impact of key variables on model predictions.Results LASSO regression identified seven variables significantly associated with AKI,including age,multivessel disease,preoperative creatinine,heart failure,white blood cell count,hemoglobin,and albumin levels.Among all the models,the light gradient boosting machine(LGBM)and extreme gradient boosting(XGB)demonstrated the best predictive performance,with training set AUCs being 0.899(95％CI:0.877-0.921)and 0.893(95％CI:0.868-0.918),and validation set AUCs being 0.809(95％CI:0.763-0.856)and 0.871(95％CI:0.833-0.909),respectively.SHAP analysis revealed that albumin,age,preoperative creatinine,and white blood cell count were the primary contributors to AKI risk.Conclusion This study successfully developed and validated machine learning-based predictive models capable of effectively identifying the risk of AKI following PCI in STEMI patients,thus providing valuable support for clinical decision-making.

Objective To investigate the relationship between serum IL-8,homocysteine(Hey),C-reactive protein(CRP)levels and severity of coronary lesions in patients with coronary heart disease(CHD)complicated by chronic heart failure(CHF),as well as their prognostic value.Methods A total of 118 elderly eligible patients admitted to our hospital from January 2023 to September 2024 were prospectively recruited,and according to their Gensini score,they were divided into mild,moderate and severe stenosis groups(45,50 and 23 cases,respectively).Accord-ing to the clinical outcomes after follow-up,they were divided into a good prognosis group(82 cases)and a poor prognosis group(36 cases).The serum levels of IL-8,Hcy and CRP were com-pared among the three groups of different stenosis,and Pearson correlation analysis was used to examine the relationship between the three indicators and the severity of coronary lesions.Cox regression analysis was performed to identify factors influencing poor prognosis in patients with CHD and CHF,and receiver ROC curve analysis was conducted to assess the diagnostic value of serum IL-8,Hey,and CRP levels in predicting prognosis.Results The serum levels of IL-8,Hey and CRP were gradually decreased in the severe,moderate and mild stenosis groups in turn,with statistical significances(P＜0.05).Pearson correlation analysis indicated that serum IL-8,Hcy,and CRP levels were positively correlated with the severity of coronary lesions in the patients with CHD and CHF(r=0.364,0.355,0.372,P＜0.01).Significant differences were found in age,NT-proBNP,D-D,IL-8,Hcy,and CRP levels between the good and poor prognosis groups(P＜0.05).Cox regression analysis revealed that age,NT-proBNP,D-D,IL-8,Hcy,and CRP were influencing factors for poor prognosis in patients with CHD and CHF(P＜0.05).ROC curve ana-lysis showed that the AUC value of IL-8,Hey,CRP,and their combination in predicting prognosis was 0.698,0.714,0.723 and 0.899,respectively.Conclusion In the patients with CHD and CHF,serum IL-8,Hcy,and CRP levels are associated with the severity of coronary lesion and prognosis.Moreover,combining these three indicators has significant diagnostic value for predicting patient outcomes.

Purpose Based on a variety of combinations of cranial MR Dixon images,the deep learning method is used to generate CT images,and the reconstruction efficiency is evaluated by comparing with the corresponding CT images.Materials and Methods A total of 77 cranial CT and MR images were collected retrospectively in Ruijin Hospital,Shanghai Jiaotong University School of Medicine from June to December 2021.The U-Net neural network was used for network training,with 62 cases in the training set and 15 cases in the test set.CT image reconstruction was performed using four kinds of Dixon images and a total of seven models among the various combinations.Mean absolute error,mean squared error,Pearson correlation coefficient and skull area Dice similarity coefficient were used to evaluate the image reconstruction efficiency.Results The generated CT images of the various Dixon image combination models showed strong correlation with the corresponding CT images(R>0.75,P<0.05),and the CT images reconstructed by the four-channel model had the closest value to the actual CT images[mean absolute error=147.516±30.802,mean squared error=(8.648±3.403)×104],the highest correlation coefficient(R=0.796±0.055),and the highest similarity coefficient in the cranial region(Dice similarity coefficient=0.800±0.036).Conclusion Deep learning training through Dixon images can be used to generate CT images,and the combination of four kinds of Dixon contrast images can improve the CT image reconstruction efficiency.

Objective To construct and validate machine learning-based models to predict the risk of acute kidney injury(AKI)following percutaneous coronary intervention(PCI)in patients with acute ST-segment elevation myocardial infarction(STEMI).Methods A total of 2 315 STEMI patients who underwent PCI between January 2020 and June 2023 were included;306(13.2％)of them developed AKI.Baseline variables were screened using LASSO regression,with the optimal λ value selected via 10-fold cross-validation to identify AKI-associated features.Subsequently,eight distinct machine learning models were constructed and evaluated for their predictive performance.SHAP value analysis was employed to assess the impact of key variables on model predictions.Results LASSO regression identified seven variables significantly associated with AKI,including age,multivessel disease,preoperative creatinine,heart failure,white blood cell count,hemoglobin,and albumin levels.Among all the models,the light gradient boosting machine(LGBM)and extreme gradient boosting(XGB)demonstrated the best predictive performance,with training set AUCs being 0.899(95％CI:0.877-0.921)and 0.893(95％CI:0.868-0.918),and validation set AUCs being 0.809(95％CI:0.763-0.856)and 0.871(95％CI:0.833-0.909),respectively.SHAP analysis revealed that albumin,age,preoperative creatinine,and white blood cell count were the primary contributors to AKI risk.Conclusion This study successfully developed and validated machine learning-based predictive models capable of effectively identifying the risk of AKI following PCI in STEMI patients,thus providing valuable support for clinical decision-making.

Purpose Based on a variety of combinations of cranial MR Dixon images,the deep learning method is used to generate CT images,and the reconstruction efficiency is evaluated by comparing with the corresponding CT images.Materials and Methods A total of 77 cranial CT and MR images were collected retrospectively in Ruijin Hospital,Shanghai Jiaotong University School of Medicine from June to December 2021.The U-Net neural network was used for network training,with 62 cases in the training set and 15 cases in the test set.CT image reconstruction was performed using four kinds of Dixon images and a total of seven models among the various combinations.Mean absolute error,mean squared error,Pearson correlation coefficient and skull area Dice similarity coefficient were used to evaluate the image reconstruction efficiency.Results The generated CT images of the various Dixon image combination models showed strong correlation with the corresponding CT images(R>0.75,P<0.05),and the CT images reconstructed by the four-channel model had the closest value to the actual CT images[mean absolute error=147.516±30.802,mean squared error=(8.648±3.403)×104],the highest correlation coefficient(R=0.796±0.055),and the highest similarity coefficient in the cranial region(Dice similarity coefficient=0.800±0.036).Conclusion Deep learning training through Dixon images can be used to generate CT images,and the combination of four kinds of Dixon contrast images can improve the CT image reconstruction efficiency.

Objective To investigate the relationship between serum IL-8,homocysteine(Hey),C-reactive protein(CRP)levels and severity of coronary lesions in patients with coronary heart disease(CHD)complicated by chronic heart failure(CHF),as well as their prognostic value.Methods A total of 118 elderly eligible patients admitted to our hospital from January 2023 to September 2024 were prospectively recruited,and according to their Gensini score,they were divided into mild,moderate and severe stenosis groups(45,50 and 23 cases,respectively).Accord-ing to the clinical outcomes after follow-up,they were divided into a good prognosis group(82 cases)and a poor prognosis group(36 cases).The serum levels of IL-8,Hcy and CRP were com-pared among the three groups of different stenosis,and Pearson correlation analysis was used to examine the relationship between the three indicators and the severity of coronary lesions.Cox regression analysis was performed to identify factors influencing poor prognosis in patients with CHD and CHF,and receiver ROC curve analysis was conducted to assess the diagnostic value of serum IL-8,Hey,and CRP levels in predicting prognosis.Results The serum levels of IL-8,Hey and CRP were gradually decreased in the severe,moderate and mild stenosis groups in turn,with statistical significances(P＜0.05).Pearson correlation analysis indicated that serum IL-8,Hcy,and CRP levels were positively correlated with the severity of coronary lesions in the patients with CHD and CHF(r=0.364,0.355,0.372,P＜0.01).Significant differences were found in age,NT-proBNP,D-D,IL-8,Hcy,and CRP levels between the good and poor prognosis groups(P＜0.05).Cox regression analysis revealed that age,NT-proBNP,D-D,IL-8,Hcy,and CRP were influencing factors for poor prognosis in patients with CHD and CHF(P＜0.05).ROC curve ana-lysis showed that the AUC value of IL-8,Hey,CRP,and their combination in predicting prognosis was 0.698,0.714,0.723 and 0.899,respectively.Conclusion In the patients with CHD and CHF,serum IL-8,Hcy,and CRP levels are associated with the severity of coronary lesion and prognosis.Moreover,combining these three indicators has significant diagnostic value for predicting patient outcomes.

AIM:To investigate the effect of Huangqi-Danggui decoction(HQDG)on the brain tissue of rats with cerebral ischemia/reperfusion(I/R)injury for 7 d by regulating macroautophagy and chaperone-mediated autophagy(CMA),and to explore its mechanism.METHODS:Male SD rats were randomly divided into sham group,model group,HQDG group and Xuesaitong(XST)group.Determination of main chemical components of HQDG by liquid chro-matography-mass spectrometry.The model of middle cerebral artery occlusion/reperfusion in rats was established by the left modified thread embolism method,and the changes of cerebral blood flow were observed by laser speckle blood flow imager.Zea Longa score was used to observe the neurological deficit.HE staining was used to observe the degree of nerve cell injury.The changes of neurovascular unit and autophagosomes in brain tissue were observed by transmission electron microscopy.Immunohistochemical method was used to detect the expression of LC3,P62,lysosome-associated membrane protein-2A(LAMP-2A),heat shock protein 70(HSP70)and myocyte enhancer factor 2D(MEF2D)proteins.Western blot was used to detect the expression of autophagy-related proteins P62 and LC3-Ⅱ/LC3-I.RESULTS:Compared with the sham group,the neurological deficit score in model group was significantly higher(P<0.01).A large number of nerve cells showed necrosis and nuclear dissolution,with the cell arrangement being disordered.The number of autophagosomes increased.The protein expression levels of LC3,LAMP-2A,HSP70 and MEF2D in brain tissue increased,while the ex-pression level of P62 protein decreased(P<0.05 or P<0.01).Compared with the model group,the scores of neurological deficit in brain tissue in HQDG and XST groups were significantly lower(P<0.01).Cell damage was significantly re-duced.The number of autophagosomes further increased.The expression levels of LAMP-2A,HSP70,MEF2D and P62 proteins in brain tissue decreased,while the expression levels of LC3-Ⅱ/LC3-I protein increased(P<0.05 or P<0.01).CONCLUSION:HQDG can alleviate cerebral ischemia/reperfusion injury in rats and exert neuroprotective effects by ac-tivating macroautophagy and reducing CMA.

Patients with novel coronavirus infection still have many functional disorders during the recovery period. The timely intervention of rehabilitation treatment has important clinical significance in improving the patients’ functions and their ability of daily living. Based on the current evidence of evidence-based medicine and clinical practice, this paper summarizes the rehabilitation treatment and precautions of patients with simple novel coronavirus infection and different groups with previous dysfunction and novel coronavirus infection (such as neurological dysfunction, chronic pain, and bone and joint diseases) with a view to providing clinical reference for the rehabilitation treatment of patients with novel coronavirus infection during the recovery period.

Objective To assess the aMAP risk in prediction of hepatocellular carcinoma (HCC) risk in outpatients with chronic hepatitis B virus (HBV) infection. Methods A total of 709 patients with chronic HBV infection were recruited for calculation of the aMAP scores and then stratified for HCC risk statistically. The t -test was used for comparison of normally distributed continuous data between groups, and the Mann-Whitney U test was used for comparison of non-normally distributed continuous data between groups. Results Among these 709 patients, 22.4% had complicated with alcoholic liver disease, 11.8% with diabetes mellitus. 18.6% with fatty liver, 19.0% with liver cirrhosis, and 9.7% with liver cancer. Among all patients, 71.2% received oral antiviral medicine. Moreover, the highest aMAP score was 75.2 and the low, medium and high HCC risks were 70.0%, 23.1%, and 6.9% respectively in these patients. The proportion of patients with high HCC risk was higher among those with alcohol liver disease, diabetes mellitus, and liver cirrhosis than those without these complications (9.4% vs 6.2%; 11.9% vs 6.2%; and 19.3% vs 4.0%). The mean annual change in aMAP score was 0.93±2.05 in patients without antiviral treatment that was higher than -1.15±1.72 in patients with antiviral treatment ( t =39.36; P < 0.001). In addition, the proportion of these patients with high HCC risk three years before HCC diagnosis was 38.4%, 26.7%, and 33.3% respectively. The median of aMAP score was more than 50 three years before diagnosis liver cancer, data of which indicated that this change was earlier than that of AFP. Conclusion aMAP is a simple convenient marker for screening early HCC in outpatient with chronic HBV infection and complications, especially in those patients with alcohol liver disease, diabetes, and cirrhosis. Oral antiviral therapy could reduce aMAP in patients with chronic HBV infection.

Objective To compare the clinical efficacy between Clamshell incision and bilateral posterolateral incision in the sequential double lung transplantation for end-stage lung disease. Methods Clinical data of 120 recipients undergoing double lung transplantation were retrospectively analyzed. All recipients were divided into bilateral posterolateral incision group (n=108) and Clamshell incision group (n=12) according to different surgical methods. Intraoperative parameters were collected and statistically compared between two groups, including operation time, amount of blood loss, amount of blood transfusion, use of extracorporeal membrane oxygenation (ECMO) or not, cold ischemia time on the first side, and cold ischemia time on the second side. Postoperative parameters were also compared between two groups, including the length of hospital stay, length of intensive care unit (ICU) stay, tracheal intubation duration, ECMO duration, forced vital capacity (FVC), forced expiratory volume in one second (FEV1), incidence of anastomotic stenosis, incidence of bronchopleural fistula, perioperative fatality, and 6-minute walk test for the first time after operation. Results In the Clamshell incision group, the amount of blood loss and blood transfusion was significantly higher than those in the bilateral posterolateral incision group (both P < 0.05). The proportion of ECMO and cold ischemia time on the second side in the Clamshell incision group were significantly lower or shorter than those in the bilateral posterolateral incision group (both P < 0.05). In the Clamshell incision group, the tracheal intubation duration and ECMO duration were significantly shorter compared with those in bilateral posterolateral incision group (both P < 0.05). Conclusions Both Clamshell incision and bilateral posterolateral incision are safe and effective in sequential double lung transplantation. Bilateral posterolateral incision approach can significantly reduce the amount of blood loss and blood transfusion of the recipients without significantly prolonging the operation time. Compared with bilateral posterolateral incision approach, the cold ischemia time of lung graft, tracheal intubation duration and ECMO duration are significantly shortened via the Clamshell incision.