The prevalence of early-stage lung adenocarcinoma (LUAD) has increased alongside increased implementation of lung cancer screenings. Robust discrimination criteria are urgently needed to identify those patients who might benefit from additional systemic therapy. Here, to develop a reliable, individualized immune gene-set-based signature to predict recurrence in early-stage LUAD, a novel recurrence-associated immune signature was identified using a least absolute shrinkage and selection operator model, and a stepwise Cox proportional hazards regression model with a training set comprised of 338 early-stage LUAD samples form TCGA, which was subsequently validated in 226 cases from GSE31210 and an independent set of 68 frozen tumor samples with qRT-PCR data. This new classification system remained strongly predictive of prognoses across clinical subgroups and mutation status. Further analysis revealed that samples from high-risk cases were characterized by active interferon signal transduction, distinctive immune cell proportions and immune checkpoint profiles. Moreover, the signature was identified as an independent prognostic factor. In conclusion, the signature is highly predictive of recurrence in patients with early-stage LUAD, which may serve as a powerful prognostic tool to further optimize immunotherapies for cancer.

早期肺腺癌（LUAD）的患病率随着肺癌筛查实施的增加而增加。迫切需要鲁棒的判别标准来识别可能从其他全身治疗中受益的患者。在这里，为了建立可靠的，基于个性化免疫基因集的签名来预测早期LUAD的复发，使用最小绝对收缩和选择算子模型，以及逐步的Cox比例风险回归，确定了一种新的与复发相关的免疫签名。该模型的训练集包含来自TCGA的338个早期LUAD样本，随后在226例来自GSE31210的病例中进行了验证，并通过qRT-PCR数据独立验证了68个冷冻肿瘤样本。这个新的分类系统仍然可以强烈预测整个临床亚组和突变状态的预后。进一步的分析表明，来自高危病例的样品的特征在于活性干扰素信号转导，独特的免疫细胞比例和免疫检查点特征。此外，签名被鉴定为独立的预后因素。综上所述，该签名可高度预测早期LUAD患者的复发，这可能是进一步优化癌症免疫疗法的有力预后工具。签名被确定为独立的预后因素。综上所述，该签名可高度预测早期LUAD患者的复发，这可能是进一步优化癌症免疫疗法的有力预后工具。签名被确定为独立的预后因素。综上所述，该签名可高度预测早期LUAD患者的复发，这可能是进一步优化癌症免疫疗法的有力预后工具。