Islet transplantation as an effective treatment for diabetes mellitus, has increasingly attracted attention in recent years. However, it faces challenges such as a shortage of donors, loss of islets during isolation and transplantation, and the need for lifelong immunosuppression. With the rapid development of multi-omics technologies and the widespread application of machine learning algorithms, researchers have begun to explore how to use these innovative technologies to improve the success rate of islet transplantation and the quality of life for patients. Machine learning has demonstrated unique advantages in data integration, pattern recognition and predictive accuracy, thereby supporting precise prediction and personalized treatment strategies. The integration of multi-omics and machine learning holds the potential to revolutionize diabetes mellitus management and advance precision medicine by optimizing donor-recipient matching and personalized immunosuppression protocols. Therefore, this article reviews the current applications of multi-omics and machine learning in islet transplantation, explores their potential impact on diabetes mellitus treatment, and looks forward to future research directions, aiming to provide references for optimizing islet transplantation as a treatment for diabetes mellitus.

Objective:To develop CNN-Dinov2, a deep learning-based automatic classification model for Gram-stained images, enabling rapid diagnosis of three prevalent Gram-negative bacilli in bloodstream infections: Escherichia coli ( E.coli), Klebsiella pneumoniae ( K.pneumoniae), and Pseudomonas aeruginosa ( P.aeruginosa). Methods:This evaluation study analyzed 1 425 Gram-stained microscopic images from patients with bloodstream infections at Houjie Hospital, in Dongguan City, collected between January 2023 and January 2024. The images, all positive for blood culture and identified as target strains, were categorized into Escherichia coli (419 images), Klebsiella pneumoniae (411 images), Pseudomonas aeruginosa (413 images), and other Gram-negative bacilli (182 images). They were randomly split into a training set (1 141 images), a validation set (141 images), and a test set (143 images) in an 8∶1∶1 ratio. A hybrid CNN-Dinov2 model was developed by integrating ResNet′s local feature extraction with Dinov2′s global pre-trained features, followed by a fully connected layer. The model was optimized by inputting the preprocessed images and adjusting parameters through loss calculation and backpropagation. AlexNet, Dinov2, and ResNet18 served as control models. The models′ classification performance was assessed using accuracy, precision, weighted F1 score, and recall rate, derived from the confusion matrix. The PR curve and AP value further evaluated each model′s classification capability across the four image categories. Results:The CNN-Dinov2 model achieved a training accuracy of 99.74%, a validation accuracy of 98.12%, and a validation loss of 0.070 6, demonstrating robust generalization without overfitting. Validation metrics revealed superior performance with an accuracy of 98.60%, precision of 98.65%, a weighted F1 score of 98.60%, and a recall rate of 98.60%, outperforming other models. The confusion matrix confirmed its strong classification capability, with the highest sum of diagonal values for identifying four types of bacteria. The macro average precision (AP) values under the precision-recall (PR) curves were all 1, indicating excellent discrimination across all categories. Overall, the CNN-Dinov2 model exhibited the best performance among the four models evaluated.Conclusion:This study successfully developed CNN-Dinov2, an automated classification model for Gram staining images. It offers valuable support for the rapid diagnosis of bloodstream infections caused by Escherichia coli, Klebsiella pneumoniae, and Pseudomonas aeruginosa, demonstrating practical utility.

The drug resistance of the carbapenem-resistant Enterobacteriaceae(CRE)strains was mainly induced by multiple approaches such as production of carbapenemases,increase of bacterial outer membrane permeability,activation of active efflux pump system,formation of biofilm and drug modifying mechanisms.Those mecha-nisms involve deletion,mutation,insertion and posttranscriptional modification of relevant encoding genes,which may affect the susceptibility of the CRE strains to antibiotics.At present,the conventional clinical thera-pies include the use of traditional antibiotics,either the one-drug use or combined use of drugs.The development of novel antibacterial therapy is under way.The epidemiological characteristics of CRE infections,drug resist-ance mechanisms,current and prospective treatment strategies for CRE infections(covering new application of the drugs in available,the novel drugs such as ceftazidime/avibactam,meropenem/vaborbactam and imipenem/rele-bactam)were deeply reviewed in this article,so as to provide reliable reference for clinical prevention,control and treatment of CRE infections.

The drug resistance of the carbapenem-resistant Enterobacteriaceae(CRE)strains was mainly induced by multiple approaches such as production of carbapenemases,increase of bacterial outer membrane permeability,activation of active efflux pump system,formation of biofilm and drug modifying mechanisms.Those mecha-nisms involve deletion,mutation,insertion and posttranscriptional modification of relevant encoding genes,which may affect the susceptibility of the CRE strains to antibiotics.At present,the conventional clinical thera-pies include the use of traditional antibiotics,either the one-drug use or combined use of drugs.The development of novel antibacterial therapy is under way.The epidemiological characteristics of CRE infections,drug resist-ance mechanisms,current and prospective treatment strategies for CRE infections(covering new application of the drugs in available,the novel drugs such as ceftazidime/avibactam,meropenem/vaborbactam and imipenem/rele-bactam)were deeply reviewed in this article,so as to provide reliable reference for clinical prevention,control and treatment of CRE infections.

Objective:To develop CNN-Dinov2, a deep learning-based automatic classification model for Gram-stained images, enabling rapid diagnosis of three prevalent Gram-negative bacilli in bloodstream infections: Escherichia coli ( E.coli), Klebsiella pneumoniae ( K.pneumoniae), and Pseudomonas aeruginosa ( P.aeruginosa). Methods:This evaluation study analyzed 1 425 Gram-stained microscopic images from patients with bloodstream infections at Houjie Hospital, in Dongguan City, collected between January 2023 and January 2024. The images, all positive for blood culture and identified as target strains, were categorized into Escherichia coli (419 images), Klebsiella pneumoniae (411 images), Pseudomonas aeruginosa (413 images), and other Gram-negative bacilli (182 images). They were randomly split into a training set (1 141 images), a validation set (141 images), and a test set (143 images) in an 8∶1∶1 ratio. A hybrid CNN-Dinov2 model was developed by integrating ResNet′s local feature extraction with Dinov2′s global pre-trained features, followed by a fully connected layer. The model was optimized by inputting the preprocessed images and adjusting parameters through loss calculation and backpropagation. AlexNet, Dinov2, and ResNet18 served as control models. The models′ classification performance was assessed using accuracy, precision, weighted F1 score, and recall rate, derived from the confusion matrix. The PR curve and AP value further evaluated each model′s classification capability across the four image categories. Results:The CNN-Dinov2 model achieved a training accuracy of 99.74%, a validation accuracy of 98.12%, and a validation loss of 0.070 6, demonstrating robust generalization without overfitting. Validation metrics revealed superior performance with an accuracy of 98.60%, precision of 98.65%, a weighted F1 score of 98.60%, and a recall rate of 98.60%, outperforming other models. The confusion matrix confirmed its strong classification capability, with the highest sum of diagonal values for identifying four types of bacteria. The macro average precision (AP) values under the precision-recall (PR) curves were all 1, indicating excellent discrimination across all categories. Overall, the CNN-Dinov2 model exhibited the best performance among the four models evaluated.Conclusion:This study successfully developed CNN-Dinov2, an automated classification model for Gram staining images. It offers valuable support for the rapid diagnosis of bloodstream infections caused by Escherichia coli, Klebsiella pneumoniae, and Pseudomonas aeruginosa, demonstrating practical utility.

To investigate the genomic features and perform cluster analysis of Carbapenem-resistant Klebsiella pneumoniae (CRKP) to provide an experimental basis for guiding the prevention and treatment of CRKP infections.A retrospective case-cohort study was conducted on 19 non-redundant CRKP strains isolated from the Tenth Affiliated Hospital of Southern Medical University between January and June 2023. Whole genome sequencing (WGS) and multilocus sequence typing (MLST) were performed to compare genomic features and analyze the resistance genes and homology of the strains.The results showed that the 19 CRKP strains were isolated from 8 different clinical departments, mainly from respiratory specimens. The whole genome sequencing revealed that the genomic lengths of CRKP ranged from 4.90 to 5.85 Mbp, with contigs N50 values>20 kb for each genome. The median overall GC content was 57.0% (50.4%-57.1%). Comparative genomic analysis identified three regions with high genomic variability. WGS detected 32 resistance genes across 11 categories. All 19 strains carried carbapenem resistance genes ( blaKPC-2 and blaOXA-48), blaTEM-1B extended-spectrum β-lactamase resistance genes, qnrS1 quinolone resistance gene, and fosA fosfomycin resistance gene, with each strain carrying only one carbapenemase gene. The detection rate of blaKPC-2 was 94.7% (18/19). MLST identified three sequence types: ST11, ST437 and ST147, with ST11 being predominant (89.5%, 17/19). Clustering analysis based on acquired resistance genes revealed three clonal transmission patterns among strains 72 and 90, and strains 88, 84, 66 and 79.In conclusion, CRKP strains carry multiple resistance genes, and clustering analysis indicating that nosocomial clonal transmission is closely related to acquired resistance genes. The ST11- blaKPC-2 type strain is the predominant clone. Strengthened surveillance and effective control strategies are necessary to reduce nosocomial transmission of CRKP.

To investigate the genomic features and perform cluster analysis of Carbapenem-resistant Klebsiella pneumoniae (CRKP) to provide an experimental basis for guiding the prevention and treatment of CRKP infections.A retrospective case-cohort study was conducted on 19 non-redundant CRKP strains isolated from the Tenth Affiliated Hospital of Southern Medical University between January and June 2023. Whole genome sequencing (WGS) and multilocus sequence typing (MLST) were performed to compare genomic features and analyze the resistance genes and homology of the strains.The results showed that the 19 CRKP strains were isolated from 8 different clinical departments, mainly from respiratory specimens. The whole genome sequencing revealed that the genomic lengths of CRKP ranged from 4.90 to 5.85 Mbp, with contigs N50 values>20 kb for each genome. The median overall GC content was 57.0% (50.4%-57.1%). Comparative genomic analysis identified three regions with high genomic variability. WGS detected 32 resistance genes across 11 categories. All 19 strains carried carbapenem resistance genes ( blaKPC-2 and blaOXA-48), blaTEM-1B extended-spectrum β-lactamase resistance genes, qnrS1 quinolone resistance gene, and fosA fosfomycin resistance gene, with each strain carrying only one carbapenemase gene. The detection rate of blaKPC-2 was 94.7% (18/19). MLST identified three sequence types: ST11, ST437 and ST147, with ST11 being predominant (89.5%, 17/19). Clustering analysis based on acquired resistance genes revealed three clonal transmission patterns among strains 72 and 90, and strains 88, 84, 66 and 79.In conclusion, CRKP strains carry multiple resistance genes, and clustering analysis indicating that nosocomial clonal transmission is closely related to acquired resistance genes. The ST11- blaKPC-2 type strain is the predominant clone. Strengthened surveillance and effective control strategies are necessary to reduce nosocomial transmission of CRKP.

Objective:Based on the principle that the aggregation-induced emission (AIE) fluorescent probe 6PD-DPAN could bind and aggregate with bacteria, and the fluorescence intensity could reflect the quantity of bacteria, a new method for rapid, convenient, and accurate bacterial drug sensitivity testing was established, which provided a basis for rapid and accurate clinical drug use.Methods:This was a methodological evaluation study. A total of 107 clinical isolates were collected from Houjie Hospital of Dongguan City from January to December 2022, among which 46 isolates were used for the establishment of the new method, and 61 isolates were used for methodological validation. The minimum inhibitory concentration (MIC) determined by broth microdilution method was used as the gold standard, and three antibacterial drugs, gentamicin, levofloxacin, and cefotaxime, were used as experimental drugs. The AIE plate was incubated for 4 hours, and the fluorescence intensity was measured every half an hour to draw a fluorescence change curve. The MIC results were compared with the CLSI breakpoints to determine the bacteria as sensitive, intermediate, or resistant. To simplify the detection process, the ratio of fluorescence intensity at 4 hours(R) was calculated, and the ROC curve was used to analyze the efficacy of R in determining bacterial growth and establish its cutoff value. The new method was used to determine the MIC of 61 clinical isolates, with broth microdilution method as the gold standard. The basic consistency, categorical consistency, very major errors, and major errors of the new method were analyzed, and the consistency between the two methods was determined by the Kappa test.Results:ROC curve analysis of the R after 4 hours of culture: The cut-off value was 3.0, with both sensitivity and specificity for determining bacterial growth being 100%. The median (interquartile) R for bacterial growth inhibition was 11.1 (8.6, 14.4); the median R-value for bacterial growth was 1.1 (1.0, 1.2). Compared to the gold standard, the newly established method showed 100% (61/61) essential agreement in detecting MICs of 61 clinical isolates, with a categorical agreement of 96.7% (59/61). There were no very major or major errors, and the Kappa value was 0.94, indicating good consistency between the newly established method and the microbroth dilution method.Conclusions:This study successfully established a new method for bacterial drug sensitivity testing based on AIE technology, which could obtain satisfactory results within 5 hours, providing a basis for early precision drug treatment in clinical practice.

Objective: Corydalis bungeana (CB) is a well-used medicinal herb in Mongolian folk medicine and has been traditionally applied as an antiobesity agent. However, the evidence-based pharmacological effects of CB and its specific metabolic alterations in the obese model are not entirely understood. This study aimed to utilize untargeted metabolomic techniques to identify biomarkers and gain mechanistic insight into the serum metabolite alterations associated with weight loss and lipid metabolism in obese rats. Methods: A high-fat high-sugar (HFHS) diet was used to induce obese models in rats. CB extract was orally gavaged at 0.18, 0.9 and 1.8 g/kg doses for six weeks, and feed intake, body weight, fat pad weight, and blood indexes were measured. Blood serum metabolites were evaluated by gas chromatography/quadrupole time-of-flight tandem mass spectrometry (GC-TOF/MS). Results: The results showed that compared with the obese group, the administration of CB extract caused significant decreases in body weight (P < 0.05), feed intake, Lee's index, and perirenal, mesenteric, epididymal fat weight. CB extract also reduced blood triglyceride and total cholesterol levels (P < 0.05) of obese rats. Metabolomic findings showed that nine differential metabolites, including pyruvic acid, D-glucuronic acid, malic acid, dimethylglycine, oxoglutaric acid, pantothenic acid, sorbitol acid, fumaric acid and glucose 6-phosphate were identified under CB treatment and altered metabolic pathways such as TCA cycle, pantothenate and CoA biosynthesis, and glycolysis/gluconeogenesis. Conclusion: This study demonstrated weight loss and lipid lowering effects of CB on HFHS diet-induced obese rats and identified nine metabolites as potential biomarkers for evaluating the favorable therapeutic mechanism of CB via regulation of lipid and glucose metabolism.

Objective To investigate the expression level of serum miR-486-5p in patients with pancreatic cancer and the value of serum miR-486-5p combined with carbohydrate antigen 19-9 (CA19-9) in predicting the resectability of pancreatic cancer. Methods A total of 60 patients who were diagnosed with pancreatic cancer in Qingdao Municipal Hospital from September 2018 to December 2020 were enrolled, among whom 32 patients had resectable or borderline resectable pancreatic cancer (operable group) and 28 had unresectable pancreatic cancer (non-operable group), and a benign pancreatic disease group with 30 patients and a healthy control group with 44 individuals were also established. Quantitative real-time PCR was used to measure the serum level of miR-486-5p in each group, and the relative expression level of miR-486-5p was calculated to analyze its association with the clinical features of pancreatic cancer, including age, sex, tumor location, tumor size, TNM stage, lymphatic metastasis, and distant metastasis. The Mann-Whitney U test was used for comparison of non-normally distributed continuous variables between two groups, and the chi-square test was used for comparison of categorical variables. The receiver operating characteristic (ROC) curve was plotted, and a binary logistic regression analysis was used to calculate the combined predictive value and then investigate the value of serum miR-486-5p combined with CA19-9 in predicting the resectability of pancreatic cancer. Results The relative expression level of serum miR-486-5p in the operable group [2.16 (1.38~3.30)] and the non-operable group [4.65 (2.80~9.90)] was significantly higher than that in the benign pancreatic disease group [1.01 (0.52~1.53)] and the healthy control group [0.99 (0.24~1.01)] (all P < 0.001). There were significant differences in the number of patients with low or high expression of miR-486-5p between the patients with different TNM stages, presence or absence of lymphatic metastasis, and presence or absence of distant metastasis ( χ 2 =13.765, 5.157, and 6.638, all P < 0.05). Compared with CA19-9 alone, miR-486-5p+CA19-9 had a significantly better value in distinguishing the operable group from the benign pancreatic disease group (area under the ROC curve [AUC]=0.87, 95% confidence interval [ CI ]: 0.760-0.942; with a sensitivity of 81.3% and a specificity of 83.3%), distinguishing the operable group from the healthy control group (AUC=0.92, 95% CI : 0.836-0.970; with a sensitivity of 90.6% and a specificity of 86.4%), and distinguishing the operable group from the non-operable group (AUC=0.94, 95% CI : 0.884-0.998; with a sensitivity of 85.7% and a specificity of 93.7%) ( Z =2.841, 2.510, and 2.387, all P < 0.05), and the optimal cut-off values were 3.12, 3.21, and 6.63, respectively. Conclusion MiR-486-5p can be used as a serum biomarker for the diagnosis of pancreatic cancer, and miR-486-5p combined with CA19-9 has a better clinical value than CA19-9 alone in predicting the resectability of pancreatic cancer in the patients with benign pancreatic diseases and the healthy population.