肺癌的转移是影响存活率的重要因素。本研究旨在建立并验证一种预测肺腺癌（LUAD）转移模式下整体生存率（OS）的评分模型。基于监测、流行病学和结果统计（SEER）数据库，纳入了2010年至2015年间诊断为转移性LUAD的9727名患者，并将其随机分为训练集和验证集。同时，我中心的136名患者被纳入作为外部验证集。通过单变量和多变量分析评估OS的预后影响，并构建了一种预后评分模型。根据C-index、校准曲线、决策曲线分析（DCA）以及风险分层系统对预后评分模型进行评估。 最终，本研究纳入了6809名训练集患者和2918名验证集患者。男性性别、后期T和N分期、较大肿瘤大小、未接受手术、化疗和放疗治疗、转移部位被发现是LUAD患者OS较差的独立危险因素，并纳入了预后评分模型中。骨转移的发生率最高，单一转移部位中肝转移的预后最差。两个部位的转移比三个和四个部位的转移更常见，同时转移最终导致存活结果较差。预后评分模型在内部训练集、验证集和外部验证集的C-index值分别为0.798、0.703和0.698。校准曲线显示，预后评分模型在6个月、1年和2年的预测结果与实际观察结果具有显著一致性。DCA曲线表明，预后评分模型比AJCC TNM分期更有益。根据预后评分模型得分，将患者进一步分为低风险组和高风险组，并建立了一个生存风险分类系统。 我们的预后评分模型有望成为预测不同转移模式的LUAD患者OS的准确和个体化的临床预测工具。© 2023. 作者。

Metastasis of lung cancer is an important factor affecting survival. The present study proposed to establish and verify a nomogram for predicting overall survival (OS) in lung adenocarcinoma (LUAD) patients with different patterns of metastasis.A total of 9727 patients diagnosed with metastatic LUAD patients from 2010 to 2015 were enrolled based on surveillance, epidemiology and end results (SEER) Database and then randomly divided into training and validation cohorts, and 136 patients in our Cancer Center were enrolled as the external validation cohort. Univariate and multivariate analyses were performed to evaluate the prognostic impact on OS. A prognostic nomogram was constructed and evaluated by C-index, calibration curve, decision curve analysis (DCA), and risk stratification system.Ultimately, 6809 and 2918 patients diagnosed with metastatic LUAD in the training and validation cohorts were enrolled in the study, respectively. A male sex, a later T and N stage, a larger tumor size, treatment including no surgery, no chemotherapy and no radiotherapy, metastasis sites were found to be independent risk factors in LUAD patients for worse OS, and then incorporated into the nomogram. The frequency of bone metastasis was the highest, and in single site metastasis, the prognosis of liver metastasis was the worst. Two-site metastasis is more common than three-site and four-site metastasis, and co-metastasis eventually leads to a worse survival outcome. The C-index value of nomogram for predicting OS were 0.798, 0.703 and 0.698 in the internal training, validation and external validation cohorts, separately. The calibration curves for the 6-months, 1-year and 2-year showed significant agreement between nomogram models and actual observations. The DCA curves indicated nomogram was more beneficial than the AJCC TNM stage. Patients were further divided into low-risk and high-risk groups according to nomogram predicted scores and developed a survival risk classification system.Our prognostic nomogram is expected to be an accurate and individualized clinical predictive tool for predicting OS in LUAD patients with different patterns of metastasis.© 2023. The Author(s).