This study aimed to develop a machine learning (ML)-based tool for early and accurate prediction of in-hospital mortality risk in patients with spontaneous intracerebral hemorrhage (sICH) in the intensive care unit (ICU). We did a retrospective study in our study and identified cases of sICH from the MIMIC IV (n = 1486) and Zhejiang Hospital databases (n = 110). The model was constructed using features selected through LASSO regression. Among five well-known models, the selection of the best model was based on the area under the curve (AUC) in the validation cohort. We further analyzed calibration and decision curves to assess prediction results and visualized the impact of each variable on the model through SHapley Additive exPlanations. To facilitate accessibility, we also created a visual online calculation page for the model. The XGBoost exhibited high accuracy in both internal validation (AUC = 0.907) and external validation (AUC = 0.787) sets. Calibration curve and decision curve analyses showed that the model had no significant bias as well as being useful for supporting clinical decisions. XGBoost is an effective algorithm for predicting in-hospital mortality in patients with sICH, indicating its potential significance in the development of early warning systems.

Glioblastoma is the most common cancer in the brain, resistant to conventional therapy and prone to recurrence. Therefore, it is crucial to explore novel therapeutics strategies for the treatment and prognosis of GBM. In this study, through analyzing online datasets, we elucidated the expression and prognostic value of POLR2J and its co-expressed genes in GBM patients. Functional experiments, including assays for cell apoptosis and cell migration, were used to explore the effects of POLR2J and vorinostat on the proliferation and migration of GBM cells. The highest overexpression of POLR2J, among all cancer types, was observed in GBM. Furthermore, high expression of POLR2J or its co-expressed genes predicted a poor outcome in GBM patients. DNA replication pathways were significantly enriched in the GBM clinical samples with high POLR2J expression, and POLR2J suppression inhibited proliferation and triggered cell cycle G1/S phase arrest in GBM cells. Moreover, POLR2J silencing activated the unfolded protein response (UPR) and significantly enhanced the anti-GBM activity of vorinostat by suppressing cell proliferation and inducing apoptosis. Additionally, POLR2J could interact with STAT3 to promote the metastatic potential of GBM cells. Our study identifies POLR2J as a novel oncogene in GBM progression and provides a promising strategy for the chemotherapeutic treatment of GBM.

Golgi protein 73 (GP73), a resident protein of the Golgi apparatus, is notably elevated in hepatocellular carcinoma (HCC). While its critical role in remodeling the tumor microenvironment (TME) is recognized, the intricate mechanisms are not fully understood. This study reveals that GP73 in HCC cells interacts with prolyl hydroxylase-2 (PHD-2) in a competitive manner, thereby impeding the hydroxylation of hypoxia-induced factor-1α (HIF-1α). The effect above promotes the production and secretion of vascular endothelial growth factor A (VEGFA). Moreover, exosomal GP73 derived from HCC cells can be internalized by human umbilical vein endothelial cells (HUVECs) and competitively interact with HECTD1, an E3 ubiquitin ligase targeting growth factor receptor-bound protein 2 (GRB2). This interaction stabilizes GRB2, thereby activating the Ras–mitogen-activated protein kinase (MAPK) signaling pathway. Consequently, escalated levels of GP73 intensify VEGF production in HCC cells and potentiate mitogenic signaling in vascular endothelial cells, fostering angiogenesis in the TME. Our findings propose that GP73 might serve as a novel target for anti-angiogenic therapy in HCC.

Abstract Glioma is one of the most primary malignant brain tumors, and glioblastoma multiform (GBM) is the most common and highly aggressive glioma. Most GBM are high malignant, poor prognosis, resistant to conventional therapy, and prone to recurrence. Therefore, it is crucial to explore novel therapeutics strategies for the treatment and prognosis of GBM. In this study, we elucidated that the maximal overexpression of DNA-directed RNA polymerase II subunit J-1 (POLR2J) was observed in GBM compared with normal tissues among all cancer types, and high expression of POLR2J or its co-expressed genes predicted poor outcome of GBM patients. DNA replication were significantly enriched in the GBM clinical samples with high POLR2J expression, and POLR2J suppression inhibited the proliferation and triggered cell cycle G1/G0 phase arrest of GBM cells. HDAC inhibitors, such as vorinostat, are identified as effective agents against GBM. We showed that POLR2J silence activated UPR and significantly enhanced anti-GBM activity of vorinostat via suppressing cell proliferation and inducing apoptosis. In addition, POLR2J promoted epithelial-mesenchymal transition (EMT) and the metastatic potentials of GBM cells. Furthermore, POLR2J expression was negatively relevant to the number of B cells, neutrophil, myeloid dendritic cells, CD4 + T cells and etc. Meanwhile, the expression of POLR2J was negatively correlative to the expression of immunotherapy-related genes. Our study confirmed a novel oncogene POLR2J in GBM progression as well as provided a promising strategy for the chemotherapy and immunotherapy of GBM treatment.

Background We aimed to evaluate the predictive power of systemic inflammation response index (SIRI), a novel biomarker, to predict all-cause mortality in patients with traumatic brain injury (TBI) in the intensive care unit (ICU). Methods Clinical data were retrieved from the Medical Information Mart for Intensive Care-IV (MIMIC-IV) database. Kaplan-Meier (KM) methods and cox proportional hazard models were performed to examine the association between SIRI and all-cause mortality. The predictive power of SIRI was evaluated compared to other leukocyte-related indexes including neutrophils, lymphocytes, monocytes and white blood cells (WBC) by the Receiver Operating Characteristic (ROC)curve for 30-day mortality. In addition, propensity score matching (PSM) was conducted to reduce confounding. Results A total of 350 TBI patients were enrolled overall in our study. The optimal cutoff point of SIRI was determined at 11.24 × 109/L. After 1:1 PSM, 66 matched pairs (132 patients) were generated. During the 30-day, in-hospital and 365-day follow-up periods, patients with low SIRI level were associated with improved survival (p < 0.05) compared with patients with high SIRI level. Cox regression analysis identified that higher SIRI values was an independent risk factor for all-cause mortality and results were stable on multiple subgroup analyses. Furthermore, ROC analysis indicated that the area under the curve of SIRI [0.6658 (95% Confidence Interval, 0.5630–0.7687)] was greater than that of neutrophils, monocytes, lymphocytes and WBC. The above results were also observed in the matched cohort. Conclusion It was suggested that TBI patients with high SIRI level would suffer from a high risk of 30-day, in-hospital and 365-day mortality. SIRI is a promising inflammatory biomarker for predicting TBI patients' prognosis with relatively better predictive power than other single indicators related to peripheral differential leukocyte counts.