Pituitary adenomas (PAs) are the second most common primary brain tumor and may develop from any of the cell lineages responsible for producing the different pituitary hormones. DNA methylation is one of the essential epigenetic mechanisms in cancers, including PAs. In this study, we measured the expression profile and promoter methylation status of carbohydrate sulfotransferase 7 (CHST7) in patients with PA; then, we investigated the effect of the CHST7 methylation status on the proliferation and differentiation of PAs. The volcano map and Metascape results showed that the levels of CHST7 were related to the lineages’ differentiation and the cell adhesion of PAs, and patients with low CHST7 had greater chances of having an SF-1 lineage (p = 0.002) and optic chiasm compression (p = 0.007). Reactome pathway analysis revealed that most of the DEGs involved in the regulation of TP53 regulated the transcription of cell cycle genes (HSA-6791312 and HSA6804116) in patients with high CHST7. Correlation analysis showed that CHST7 was significantly correlated with the eIF2/ATF4 pathway and mitochondrion-related genes. The AUC of ROC showed that CHST7 (0.288; 95% CI: 0.187–0.388) was superior to SF-1 (0.555; 95% CI: 0.440–0.671) and inferior to FSHB (0.804; 95% CI: 0.704–0.903) in forecasting the SF-1 lineage (p < 0.001). The SF-1 lineage showed a higher methylation frequency for CHST7 than the Pit-1 and TBX19 lineages (p = 0.009). Furthermore, as the key molecule of the hypothalamic–pituitary–gonadal axis, inhibin βE (INHBE) was positively correlated with the levels of CHST7 (r = 0.685, p < 0.001). In summary, CHST7 is a novel pituitary gland specific protein in SF-1 lineage adenomas with a potential role in gonadotroph cell proliferation and lineage differentiation in PAs.

Objective: Critically ill patients with digestive system tumors are at high risk of acute kidney injury (AKI), a complication strongly associated with increased mortality and adverse outcomes. However, early AKI risk identification in the intensive care unit (ICU) remains challenging. This study aimed to develop and externally validate an interpretable model for early AKI risk prediction in critically ill patients with digestive system tumors. Methods: We retrospectively analyzed 3,821 patients with digestive system tumors from the MIMIC-IV 3.0 database. Routine clinical variables from the first 24 hours after ICU admission were extracted. Least absolute shrinkage and selection operator (LASSO) regression and multivariable logistic regression were used for feature selection, followed by the development and comparison of six machine learning models. Model performance was evaluated using the AUC, calibration analysis, and decision curve analysis. The optimal model was interpreted using Shapley Additive Explanations (SHAP), and an online interactive prediction tool was developed to facilitate clinical translation. External validation was conducted in three independent cohorts from the United States and China, including the eICU Collaborative Research Database (eICU), the Tangshan tumor-related AKI cohort (TS-TAKI), and the Beijing Acute Kidney Injury cohort (BAKIT). Result: The incidence of AKI was 75.8%. Among all models, extreme gradient boosting (XGBoost) showed the best overall performance, with an AUC of 0.765 (95% CI 0.745–0.786) in the training set and 0.742 (95% CI 0.710–0.773) in the validation set, low Brier score, good calibration, and meaningful clinical net benefit. SHAP analysis identified the SOFA score, mechanical ventilation, WBC count, age, serum potassium level, sepsis, and vasoactive drug use as key predictors, with consistent interpretability at both the population and individual levels. In external validation, the model demonstrated stable discrimination across multicenter populations (AUCs of 0.719 in eICU, 0.769 in TS-TAKI, and 0.616 in BAKIT); however, calibration performance was notably affected by population heterogeneity, suggesting the need for recalibration using local data in real-world application. Conclusion: This interpretable XGBoost-based model, based on routine ICU data, enables early AKI risk stratification in critically ill patients with digestive system tumors. The model achieves a balance between predictive performance, transparency, and clinical feasibility. It exhibited stable discriminative performance across multicenter and cross-population cohorts, while calibration was clearly affected by population heterogeneity, highlighting the need for local validation and recalibration in real-world application. An online prediction tool further supports its potential for clinical translation.

Pituitary neuroendocrine tumors (PitNETs) are commonly managed with endoscopic endonasal transsphenoidal surgery (EETS), but early postoperative hypopituitarism remains a clinically important complication. This retrospective cohort study analyzed early postoperative risk factors for hypopituitarism in 124 patients with PitNETs who underwent EETS at a single center between January 2022 and December 2024. Endocrine status was assessed preoperatively, during the immediate postoperative period before discharge (postoperative days 3–7), and at scheduled outpatient reassessments at 1 and 3 months after surgery; the mean interval from surgery to endpoint endocrine assessment was 3.2 ± 0.6 months. Patients were categorized into a hypopituitarism group (n = 38) and a non-hypopituitarism group (n = 86) based on postoperative endocrine evaluation across the hypothalamic–pituitary–adrenal, thyroid, gonadal, and growth hormone axes. Demographic, radiologic, perioperative, and endocrine data were collected, and univariate and multivariate logistic regression analyses were performed. Patients who developed hypopituitarism were older and had larger tumors, higher Knosp grades, more frequent suprasellar extension, longer operation times, greater intraoperative blood loss, more intraoperative cerebrospinal fluid leakage, and lower rates of gross total resection. In the multivariate model, maximum tumor diameter (adjusted odds ratio [aOR] per 10-mm increase = 2.02, 95% confidence interval [CI]: 1.09–3.74) and Knosp grade 3–4 (aOR = 2.37, 95% CI: 1.03–5.46) were identified as independent risk factors for early postoperative hypopituitarism, whereas gross total resection was independently associated with a reduced risk (aOR = 0.39, 95% CI: 0.16–0.96). These findings indicate that tumor anatomy and extent of resection are key determinants of early endocrine outcomes after EETS and should be incorporated into preoperative risk stratification and postoperative endocrine surveillance; however, they should not be extrapolated to long-term pituitary functional recovery or deterioration without further follow-up.