OBJECTIVE To analyze the development history， current status， and major challenges of central （cloud） pharmacies within China’s close-knit county-level medical communities， and to provide references for improving the overall effectiveness of the primary-level pharmaceutical supply and support system.METHODS Policy documents and practical case data related to central （cloud） pharmacies in county-level medical communities from 31 provinces （autonomous regions and municipalities） in China were collected. A qualitative approach combining policy text analysis and comparative case analysis was employed to longitudinally trace and cross-sectionally compare the development history and current status of central （cloud） pharmacies， identify existing problems， and propose targeted recommendations. RESULTS &CONCLUSIONS The development of central （cloud） pharmacies in China has undergone three stages： initial exploration， pilot expansion and mechanism deepening， and high-level promotion with local responses. While adhering to national policy directives， various regions have conducted diverse explorations in organizational and legal forms， management models， and institutional frameworks. However， several challenges remain， including insufficient policy guidance， an imperfect mechanism for drug coordination and supply security， weaknesses in hardware infrastructure and information technology development， and the need to strengthen statistical monitoring and outcome evaluation systems. It is recommended that the construction of central （cloud） pharmacies should be oriented toward achieving their fundamental functions， improve the institutional framework， adopt differentiated construction models tailored to local conditions， enhance the coordinated drug supply and support system， strengthen information technology infrastructure and professional capacity building， unify evaluation standards， and improve performance assessment mechanisms， so as to elevate the overall effectiveness of the primary-level pharmaceutical supply and support system.

Objective:To develop and validate the models based on mixed enhanced computed tomography (CT) radiomics and deep learning features, and evaluate the efficacy for differentiating pancreatic adenosquamous carcinoma (PASC) from pancreatic ductal adenocarcinoma (PDAC) before surgery.Methods:The clinical data of 201 patients with surgically resected and histopathologically confirmed PASC (PASC group) and 332 patients with surgically resected histopathologically confirmed PDAC (PDAC group) who underwent enhanced CT within 1 month before surgery in the First Affiliated Hospital of Naval Medical University from January 2011 to December 2020 were retrospectively collected. The patients were chronologically divided into a training set (treated between January 2011 and January 2018, 156 patients with PASC and 241 patients with PDAC) and a validation set (treated between February 2018 and December 2020, 45 patients with PASC and 91 patients with PDAC) according to the international consensus on the predictive model. The nnU-Net model was used for pancreatic tumor automatic segmentation, the clinical and CT images were evaluated, and radiomics features and deep learning features during portal vein phase were extracted; then the features were dimensionally reduced and screened. Binary logistic analysis was performed to develop the clinical, radiomics and deep learning models in the training set. The models' performances were determined by area under the ROC curve (AUC), sensitivity, specificity, accuracy, and decision curve analysis (DCA).Results:Significant differences were observed in tumor size, ring-enhancement, upstream pancreatic parenchymal atrophy and cystic degeneration of tumor both in PASC and PDAC group in the training and validation set (all P value <0.05). The multivariable logistic regression analysis showed the tumor size, ring-enhancement, dilation of the common bile duct and upstream pancreatic parenchymal atrophy were associated with PASC significantly in the clinical model. The ring-enhancement, dilation of the common bile duct, upstream pancreatic parenchymal atrophy and radiomics score were associated with PASC significantly in the radiomics model. The ring-enhancement, upstream pancreatic parenchymal atrophy and deep learning score were associated with PASC significantly in the deep learning model. The diagnostic efficacy of the deep learning model was highest, and the AUC, sensitivity, specificity, and accuracy of the deep learning model was 0.86 (95% CI 0.82-0.90), 75.00%, 84.23%, and 80.60% and those of clinical and radiomics models were 0.81 (95% CI 0.76-0.85), 62.18%, 85.89%, 76.57% and 0.84 (95% CI 0.80-0.88), 73.08%, 82.16%, 78.59% in the training set. In the validation set, the area AUC, sensitivity, specificity, and accuracy of deep learning model were 0.78 (95% CI 0.67-0.84), 68.89%, 78.02% and 75.00%, those of clinical and radiomics were 0.72 (95% CI 0.63-0.81), 77.78%, 59.34%, 65.44% and 0.75 (95% CI 0.66-0.84), 86.67%, 56.04%, 66.18%. The DCA in the training and validation sets showed that if the threshold probabilities were >0.05 and >0.1, respectively, using the deep learning model to distinguish PASC from PDAC was more beneficial for the patients than the treat-all-patients as having PDAC scheme or the treat-all-patients as having PASC scheme. Conclusions:The deep learning model based on CT automatic image segmentation of pancreatic neoplasm could effectively differentiate PASC from PDAC, and provide a new non-invasive method for confirming PASC before surgery.

Objective To establish a MRI grading diagnostic model for chronic pancreatitis (CP) to acquire better combination for CP diagnosis and improve the diagnostic ability of CP grading.Methods To collecte the data of 68 CP patients who were clinically diagnosed and 23 health volunteers from Dec 2012 to Oct 2014.There were 23 mild CP, 14 moderate CP and 31 severe CP according to Cambridge classification.3.0 T MRI data were analyzed, and 14 features were extracted to compare the MRI features among groups.The single ordinal regression analysis was conducted on the variables with significant difference between groups, and the collinearity was diagnosed.The factor analysis was used for multicollinearity.The multiple ordinal logistic regression was finally conducted to establish the regression model.Results There was no significant difference between control groups and CP groups on pancreas divisum (X14), but significant differences were found in other 13 features (P<0.05).Single ordinal regression analysis of 13 features showed that all features except pancreatic parenchymal bubble (X12) were significantly correlated with CP grading diagnosis(P<0.05).The effect of multicollinearity was validated among 9 continuous variables.Three common factors were identified, including F1(X3、X4、X5、X9、X8), F2(X7、X6) and F3 (X1、X2) which represented the exocrine function, the features of main pancreatic ducts and pancreatic parenchyma, respectively.Six features were implemented into the multi Logistic regression model, which included F1, F2, F3, X10 (the visualizations of branch pancreatic duct after secretin stimulation), X11 (pancreatic shape) and X13 (the filling defects of main pancreatic duct).Finally, the most appropriate regression model was gotten, which was the scale model of the probit link function.The model′s diagnostic accuracy for normal, mild CP, moderate CP, severe CP and total CP was 96.65%,100%, 71.42%,100% and 94.50%, respectively.Conclusions The ordinal logistic regression model proposed in this study may accurately predict the CP grades and can offer valuable references for clinic diagnosis and therapy of CP.