Hanxu Zhang

Introduction: Early prediction of prognosis for neurosurgical diseases remains challenging. This study aimed to develop a machine learning-based model to predict unfavorable outcomes in neurosurgical patients. Methods: We conducted a retrospective cohort study of patients with traumatic brain injury, intracerebral hemorrhage, or aneurysmal subarachnoid hemorrhage between 2018 and 2020. The primary outcome was functional status at discharge, assessed via the modified Rankin Scale. Feature selection used LASSO regression and the Boruta algorithm, with overlapping selected features retained for model development. Six machine learning algorithms were trained with 5-fold cross-validation for hyperparameter optimization via Optuna. Model performance was evaluated using area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis. Shapley additive explanations were used for interpretability. Results: The CatBoost model performed best (AUC = 0.932, accuracy = 0.879, precision = 0.872, recall = 0.810, F1 score = 0.840, Brier score = 0.116), balancing discriminative power and clinical relevance. Key predictive features included Glasgow Coma Scale (GCS) score at admission, age, and liver function markers including aspartate transaminase (AST) _mean , albumin _mean , alkaline phosphatase (ALKP) _mean , ALKP _max , albumin _min , and ALKP _first . Lower GCS score at admission and older age predicted unfavorable outcomes. Higher mean AST, mean ALKP and initial ALKP, as well as lower mean and minimum albumin, were associated with unfavorable outcomes. Discussion: The CatBoost model showed excellent performance in predicting the prognosis of neurosurgical patients by integrating neurological and liver function markers. Future studies are needed for external validation through multicenter investigations, and explore mechanistic associations between liver dysfunction and neurological deterioration.

Endothelial cells (ECs) line the inner surface of blood vessels and play a substantial role in vascular biology. Endothelial dysfunction (ED) is strongly correlated with the initiation and progression of many vascular diseases. Regulated cell death, such as ferroptosis, is one of the multiple mechanisms that lead to ED. Ferroptosis is an iron-dependent programmed cell death associated with various vascular diseases, such as cardiovascular, cerebrovascular, and pulmonary vascular diseases. This review summarized ferroptosis of ECs in vascular diseases and discussed potential therapeutic strategies for treating ferroptosis of ECs. In addition to lipid peroxidation inhibitors and iron chelators, a growing body of evidence showed that clinical drugs, natural products, and intervention of noncoding RNAs may also inhibit ferroptosis of ECs.

(1) Background: The purpose of this study was to evaluate the effect of gene polymorphisms on prothrombin time (PT) and activated partial thromboplastin time (APTT) in a healthy Chinese population. (2) Methods: A total of 403 healthy volunteers from a series of novel oral anticoagulants (NOACs) bioequivalence trials in China were included. Coagulation tests for PT and APTT were performed in the central lab at Peking University First Hospital. Whole-exome sequencing (WES) and genome-wide association analysis were performed. (3) Results: In the correlation analysis of PT, 105 SNPs from 84 genes reached the genome-wide significance threshold (p < 1 × 10⁻⁵). Zinc Finger Protein 594 (ZNF594) rs184838268 (p = 4.50 × 10⁻¹⁹) was most significantly related to PT, and Actinin Alpha 1 (ACTN1) was found to interact most with other candidate genes. Significant associations with previously reported candidate genes Aurora Kinase B (AURKB), Complement C5(C5), Clock Circadian Regulator (CLOCK), and Histone Deacetylase 9(HDAC9) were detected in our dataset (p < 1 × 10⁻⁵). PiggyBac Transposable Element Derived 2(PGBD2) rs75935520 (p = 4.49 × 10⁻⁶), Bromodomain Adjacent To Zinc Finger Domain 2A(BAZ2A) rs199970765 (p = 5.69 × 10⁻⁶) and Protogenin (PRTG) rs80064850 (p = 8.69 × 10⁻⁶) were significantly correlated with APTT (p < 1 × 10⁻⁵). The heritability values of PT and APTT were 0.83 and 0.64, respectively; (4) Conclusion: The PT and APTT of healthy populations are affected by genetic polymorphisms. ZNF594 and ACTN1 variants could be novel genetic markers of PT, while PRTG polymorphisms might be associated with APTT levels. The findings could be attributed to ethnic differences, and need further investigation.

December 2019 saw the emergence of the coronavirus disease 2019 (COVID-19), caused by severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2), which has spread across the globe. The high infectivity and ongoing mortality of SARS-CoV-2 emphasize the demand of drug discovery. Angiotensin-converting enzyme II (ACE2) is the functional receptor for SARS-CoV-2 entry into host cells. ACE2 exists as a membrane-bound protein on major viral target pulmonary epithelial cells, and its peptidase domain (PD) interacts SARS-CoV-2 spike protein with higher affinity. Therefore, targeting ACE2 is an important pharmacological intervention for a SARS-CoV-2 infection. In this review, we described the two-way switch role of ACE2 in the treatment of novel coronavirus pneumonia and underlying comorbidities, and discussed the potential effect of the ACE inhibitor and angiotensin receptor blocker on a hypertension patient with the SARS-CoV-2 infection. In addition, we analyzed the S-protein-binding site on ACE2 and suggested that blocking hot spot-31 and hot spot-353 on ACE2 could be a therapeutic strategy for preventing the spread of SARS-CoV-2. Besides, the recombinant ACE2 protein could be another potential treatment option for SARS-CoV-2 induced acute severe lung failure. This review could provide beneficial information for the development of anti-SARS-CoV-2 agents via targeting ACE2 and the clinical usage of renin-angiotensin system (RAS) drugs for novel coronavirus pneumonia treatment.