Background/Objectives: Gallstone disease is a prevalent digestive disorder worldwide, with incidence increasingly linked to obesity, insulin resistance, and dyslipidemia. Emerging evidence suggests that intestinal microbial communities and their bioactive compounds play a central role in pathogenesis. Here, we aimed to clarify whether diet-related microbial alterations and circulating metabolites contribute to gallstone formation. Methods: We integrated dietary inflammatory index (DII) evaluation, genetic analyses of large-scale cohorts, and a cholesterol gallstone mouse model induced by a lithogenic diet (LD). Serum and fecal samples were subjected to metabolomic and metagenomic profiling, followed by multi-omics integration to identify links between microbial taxa, metabolites, and gallstone risk. Results: Higher DII scores were associated with increased gallstone risk. Genetic evidence supported bile acid and amino acid metabolism as potential mediating pathways, with Akkermansia muciniphila linked to decreased N-acetylarginine levels and CAG-448 showing an inverse association with glycodeoxycholate (GDCA). In LD-fed mice, shotgun metagenomics revealed enrichment of lithogenic taxa such as Bacteroides stercorirosoris and Enterocloster, whereas protective taxa, including Akkermansia muciniphila and CAG-448, were markedly depleted. Untargeted metabolomics confirmed elevations of GDCA and N-acetylarginine together with broader bile acid imbalance, amino acid stress, and long-chain acylcarnitine accumulation. Correlation analyses further showed that protective taxa were inversely associated with risk metabolites, whereas gallstone-enriched microbes displayed the opposite pattern. Conclusions: This study provides evidence consistent with a contributory role of gut microbiota–metabolite dysregulation in gallstone pathogenesis. Specific taxa (A. muciniphila, CAG-448) and metabolites (GDCA, N-acetylarginine) may serve as potential biomarkers or targets for microbiota- and diet-based prevention strategies.

Background: Accurate preoperative identification of high mitotic count is important for risk stratification in gastrointestinal stromal tumors (GISTs), yet biopsy is invasive and conventional imaging alone does not directly reflect microscopic proliferative activity. We aimed to develop and externally validate an interpretable model integrating CT features and serologic indicators. Methods: This multicenter retrospective study included 802 patients from three Shanxi hospitals, randomly split into a training cohort (n = 562) and an internal validation cohort (n = 240), plus an external validation cohort from Dalian (n = 255). LASSO and multivariable logistic regression were used for feature selection and nomogram construction. Five individual machine-learning models and 31 stacking ensembles were trained, and SHAP was used to interpret model behavior. Results: Tumor size, liquefaction/necrosis, coarse vessel sign, peritumoral fat stranding, platelet-to-lymphocyte ratio, and albumin-to-fibrinogen ratio were independent predictors of high mitotic count. Among individual models, SVM achieved the highest internal-validation AUC (0.866). The best stacking model (SVM+ANN+Logit) reached an AUC of 0.867 on internal validation and 0.955 on external validation, with good calibration and favorable decision-curve performance. The gain over the best single model was small but consistent. Conclusion: An interpretable model combining CT and serologic features may provide a practical non-invasive tool for preoperative estimation of mitotic count in GISTs. Prospective validation is still needed before routine clinical implementation. The flowchart illustrates the process of patient data collection and model development for a study on gastrointestinal stromal tumors. Patients were collected from three hospitals between January 2017 and January 2025. After screening, 802 patients were included and divided into a training set of 562 patients and an internal validation set of 240 patients, with subgroups defined by mitotic index > 5/50 HPFs and ≤ 5/50 HPFs. An external test set from another hospital included 255 patients. The workflow shows variable selection using LASSO and multivariable logistic regression, followed by the development of a logistic regression-based nomogram model and several machine learning models, including XGBoost, LightGBM, Random Forest, SVM, and ANN. Model performance was compared, and a stacking ensemble model was established. SHAP analysis was also included for model interpretation.GIST study workflow: data collection, model development, performance comparison, and SHAP interpretation.

Background: Retroperitoneal paraganglioma (RPGL) is an uncommon extra-adrenal neuroendocrine tumor. When located adjacent to the pancreas, RPGL may mimic solid pseudopapillary neoplasm of the pancreas (SPN/SPTP) because both lesions may present as large cystic-solid masses with nonspecific symptoms and non-diagnostic conventional tumor markers. Percutaneous biopsy may establish the diagnosis but can be hazardous when RPGL has not been excluded. Case presentation: A 44-year-old man presented with abdominal distension. He had no history of hypertension, headache, palpitations, or profuse sweating. Laboratory tests, including routine blood tests, liver and kidney function, coagulation profile, and conventional tumor markers, showed no significant abnormalities. Ultrasound, CT, and MRI demonstrated a large multilocular cystic-solid mass in the pancreatic body-tail region, and the initial impression was SPN/SPTP or a pancreatic cystic neoplasm. Plasma or urinary catecholamines/metanephrines and functional imaging were not performed because the lesion was initially considered pancreatic in origin and the patient lacked symptoms of catecholamine excess. Ultrasound-guided 16G core biopsy yielded two tissue cores. Histology and immunohistochemistry showed synaptophysin, chromogranin A, and CD56 positivity with a Ki-67 index of approximately 1%, supporting RPGL. Surgical exploration subsequently confirmed that the tumor arose from the retroperitoneum and compressed, rather than originated from, the pancreas. Tumor manipulation caused marked hemodynamic fluctuation and pulmonary edema, requiring postoperative intensive care. Final pathology confirmed RPGL without definite evidence of metastasis or local malignant invasion. Conclusion: For large cystic-solid masses in the pancreatic tail or adjacent retroperitoneum, RPGL should remain in the differential diagnosis even when classic catecholamine-related symptoms are absent. Before biopsy, clinicians should prioritize careful assessment of tumor origin, multiphasic contrast-enhanced imaging, and biochemical testing for plasma free or urinary fractionated metanephrines. Biopsy should be selective and should follow multidisciplinary risk assessment with appropriate hemodynamic and interventional contingency planning.