Zhang Zexin, Wu Wenfeng, Li Xuewei, Lin Siqi, Lei Qiwei, Yu Ling, Lin Jietao, Sun Lingling, Zhang Haibo, Lin Lizhu
Guangzhou University of Chinese Medicine, Guangzhou, China.
The First Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, China.
Heliyon. 2024 Jul 21;10(15):e34585. doi: 10.1016/j.heliyon.2024.e34585. eCollection 2024 Aug 15.
Inflammation plays an important role in the transformation of pulmonary nodules (PNs) from benign to malignant. Prediction of benignancy and malignancy of PNs is still lacking efficacy methods. Although Mayo or Brock model have been widely applied in clinical practices, their application conditions are limited. This study aims to construct a diagnostic model of PNs by machine learning using inflammation-related biological markers (IRBMs).
Inflammatory related genes (IRGs) were first extracted from GSE135304 chip data. Then, differentially expressed genes (DEGs) and infiltrating immune cells were screened between malignant pulmonary nodules (MN) and benign pulmonary nodule (BN). Correlation analysis was performed on DEGs and infiltrating immune cells. Molecular modules of IRGs were identified through Consistency cluster analysis. Subsequently, IRBMs in IRGs modules were filtered through Weighted gene co-expression network analysis (WGCNA). An optimal diagnostic model was established using machine learning methods. Finally, external dataset GSE108375 was used to verify this result.
4 hub IRGs and 3 immune cells showed significantly difference between MN and BN, C1 and C2 module, namely PRTN3, ELANE, NFKB1 and CTLA4, T cells CD4 naïve, NK cells activated and Monocytes. IRBMs were screened from black module and yellowgreen module through WGCNA analysis. The Support vector machines (SVM) was identified as the optimal model with the Area Under Curve (AUC) was 0.753. A nomogram was established based on 5 hub IRBMs, namely HS.137078, KLC3, C13ORF15, STOM and KCTD13. Finally, external dataset GSE108375 verified this result, with the AUC was 0.718.
SVM model established by 5 hub IRBMs was able to effectively identify MN or BN. Accumulating inflammation and immune dysfunction were important to the transformation from BN to MN.
炎症在肺结节（PNs）从良性向恶性转变过程中起重要作用。目前仍缺乏有效的肺结节良恶性预测方法。尽管梅奥（Mayo）或布罗克（Brock）模型已在临床实践中广泛应用，但其应用条件有限。本研究旨在利用炎症相关生物标志物（IRBMs）通过机器学习构建肺结节诊断模型。
首先从GSE135304芯片数据中提取炎症相关基因（IRGs）。然后，筛选出恶性肺结节（MN）和良性肺结节（BN）之间的差异表达基因（DEGs）和浸润免疫细胞。对DEGs和浸润免疫细胞进行相关性分析。通过一致性聚类分析确定IRGs的分子模块。随后，通过加权基因共表达网络分析（WGCNA）筛选IRGs模块中的IRBMs。利用机器学习方法建立最佳诊断模型。最后，使用外部数据集GSE108375验证该结果。
4个关键IRGs和3种免疫细胞在MN和BN、C1和C2模块之间存在显著差异，即蛋白酶3（PRTN3）、弹性蛋白酶3（ELANE）、核因子κB1（NFKB1）和细胞毒性T淋巴细胞相关蛋白4（CTLA4），初始CD4 + T细胞、活化自然杀伤细胞和单核细胞。通过WGCNA分析从黑色模块和黄绿色模块中筛选出IRBMs。支持向量机（SVM）被确定为最佳模型，曲线下面积（AUC）为0.753。基于5个关键IRBMs建立了列线图，即HS.137078、动力蛋白轻链3（KLC3）、13号染色体开放阅读框15（C13ORF15）、 stomatin（STOM）和钾通道四聚体结构域蛋白13（KCTD13）。最后，外部数据集GSE108375验证了该结果，AUC为0.718。
由5个关键IRBMs建立的SVM模型能够有效识别MN或BN。炎症积累和免疫功能障碍对BN向MN的转变很重要。
