Machine learning-based identification of a neutrophil extracellular traps-derived signature for improving outcomes and therapy responses in patients with glioma

Neutrophils, a cellular component in glioma, contribute to its heterogeneous microenvironment and clinical outcomes. This study aimed to develop a neutrophil extracellular traps (NETs)-related signature for prognostic stratification and prediction of immunotherapy efficacy in glioma. Expression data and clinical information from public databases were utilized to establish a prognostic risk model using LASSO and machine learning algorithms. The NETs-based signature demonstrated superior accuracy compared to published signatures and served as an independent prognostic factor. High-risk patients exhibited elevated immune and stromal infiltration. NETs-related gene expression correlated with drug sensitivity, and MMP9 was identified as a hub gene associated with the prognostic model. Immunohistochemistry confirmed MMP9's unfavorable prognosis association. These findings suggest that the NETs-based signature can aid in precise patient stratification and guide immunotherapy and chemotherapy decisions in glioma.中性粒细胞（Neutrophils）作为胶质瘤中的细胞组分，参与构成其异质性微环境并影响临床结局。本研究旨在构建一种与中性粒细胞胞外陷阱（Neutrophil extracellular traps, NETs）相关的特征模型，用于胶质瘤的预后分层及免疫治疗疗效预测。研究利用公共数据库中的表达数据与临床信息，通过LASSO与机器学习算法构建预后风险模型。相较于已发表的特征模型，基于NETs的特征模型展现出更优的预测精度，且可作为独立的预后因素。高风险患者的免疫与基质浸润水平显著升高。NETs相关基因的表达与药物敏感性存在关联，基质金属蛋白酶9（Matrix Metalloproteinase 9, MMP9）被鉴定为该预后模型的枢纽基因。免疫组化实验证实了MMP9与不良预后的相关性。上述研究结果表明，基于NETs的特征模型可辅助实现胶质瘤患者的精准分层，并为其免疫治疗与化疗方案的决策提供指导。