Lin Duanyu, Wu Wenxi, Huang Zongwei, Xu Siqi, Li Ying, Chen Zihan, Li Yi, Lai Jinghua, Lu Jun, Qiu Sufang
Clinical Oncology School of Fujian Medical University, Fujian Cancer Hospital（Fujian Branch of Fudan University Shanghai Cancer Center）, 420 Fuma Rd, Jin'an District, Fuzhou, Fujian, China.
Clin Transl Oncol. 2025 Apr;27(4):1748-1759. doi: 10.1007/s12094-024-03709-9. Epub 2024 Sep 20.
The objective of this study is to assess the prognostic efficacy of F-fluorodeoxyglucose (F-FDG) positron emission tomography/computed tomography (PET-CT) parameters in nasopharyngeal carcinoma (NPC) and identify the best machine learning (ML) prognostic model for NPC patients based on these F-FDG PET/CT parameters and clinical variables.
A cohort of 678 patients diagnosed with NPC between 2016 and 2020 was analyzed in this study. The model was constructed using four advanced ML algorithms, namely Random Forest (RF), Extreme Gradient Boosting (XGBoost), Least Absolute Shrinkage and Selection Operator (LASSO), and multifactor COX step-up regression. Statistical significance of the models was assessed using Kaplan-Meier (K-M) curves, with a significance level established at P < 0.05. The prognostic efficacy of the models was evaluated through the analysis of receiver operating characteristic (ROC) curves, with the area under the ROC curve (AUC) serving as a criterion for model selection. The decision curve analysis (DCA) and concordance index (C-index) were employed to assess the precision of the optimal model.
Multivariate analysis revealed age, T stage, and metabolic tumor volume (MTV) for the primary nasopharyngeal tumor (MTVT) as significant independent prognostic factors for overall survival (OS) in NPC patients. Additionally, the LASSO model identified six key variables, including peak standardized uptake value (SUV-peak) for the primary nasopharyngeal tumor (SUV-peak(T)), MTVT, heterogeneity index for neck lymph nodes (HIN), age, pathological type, and T stage. Remarkably, the LASSO model demonstrated superior performance with a 5-year AUC of 0.849 compared to other models. Further assessment using the C-index and DCA confirmed the accuracy of the LASSO model. Subgroup analysis revealed notable risk factors, such as a high heterogeneity index (HI) for the primary nasopharyngeal tumor (HIT), MTV values for neck lymph nodes (MTVN), and HIN.
We developed a novel prognostic machine learning model that integrates F-FDG PET-CT parameters and clinical characteristics, significantly enhancing prognosis prediction in NPC.
本研究旨在评估氟脱氧葡萄糖（F-FDG）正电子发射断层扫描/计算机断层扫描（PET-CT）参数在鼻咽癌（NPC）中的预后效能，并基于这些F-FDG PET/CT参数和临床变量确定针对NPC患者的最佳机器学习（ML）预后模型。
本研究分析了2016年至2020年间确诊为NPC的678例患者队列。使用四种先进的ML算法构建模型，即随机森林（RF）、极端梯度提升（XGBoost）、最小绝对收缩和选择算子（LASSO）以及多因素COX逐步回归。使用Kaplan-Meier（K-M）曲线评估模型的统计学显著性，显著性水平设定为P < 0.05。通过分析受试者工作特征（ROC）曲线评估模型的预后效能，以ROC曲线下面积（AUC）作为模型选择的标准。采用决策曲线分析（DCA）和一致性指数（C-index）评估最佳模型的精度。
多变量分析显示，年龄、T分期以及鼻咽原发肿瘤的代谢肿瘤体积（MTV）（MTVT）是NPC患者总生存期（OS）的显著独立预后因素。此外，LASSO模型确定了六个关键变量，包括鼻咽原发肿瘤的峰值标准化摄取值（SUV-peak）（SUV-peak(T)）、MTVT、颈部淋巴结异质性指数（HIN）、年龄、病理类型和T分期。值得注意的是，与其他模型相比，LASSO模型表现更优，5年AUC为0.849。使用C-index和DCA进行的进一步评估证实了LASSO模型的准确性。亚组分析揭示了显著的危险因素，如鼻咽原发肿瘤的高异质性指数（HI）（HIT）、颈部淋巴结的MTV值（MTVN）和HIN。
我们开发了一种整合F-FDG PET-CT参数和临床特征的新型预后机器学习模型，显著提高了NPC的预后预测能力。
