目的:本研究旨在开发和验证基于机器学习的诊断和预后模型,以预测肝细胞癌(HCC)患者远处淋巴结转移(DLNM)的风险,并评估该队列的预后。
方法:利用回顾性设计,这项调查利用了从监控中提取的数据,流行病学,和最终结果(SEER)数据库,特别是2024年1月的子集,进行分析。
方法:研究队列包括SEER数据库中确定的15,775例诊断为HCC的患者,从2016年到2020年。
方法:在构建诊断模型时,递归特征消除(RFE)用于变量选择,纳入五个关键预测因素:年龄,肿瘤大小,放射治疗,T-stage,和血清甲胎蛋白(AFP)水平。这些变量是堆叠集成模型的基础,通过Shapley加法解释(SHAP)进一步阐明了这一点。相反,预后模型是利用逐步向后回归选择相关变量来构建的,包括化疗,放射治疗,肿瘤大小,和年龄。该模型最终形成了预后列线图,以Cox比例风险模型为基础。
方法:诊断模型的结果是患者发生DLNM。预后模型的结果由生存时间和生存状态决定。
结果:基于堆叠开发的集成模型显示出良好的预测性能以及高度的解释变异性和差异化。训练集中的曲线下面积(AUC)为0.767,而验证集中的AUC为0.768。列线图,使用Cox模型构建,还表现出一致和强大的预测能力。同时,我们认识到对DLNM和预后有重大影响的因素,并广泛讨论了它们在模型和临床实践中的意义.
结论:我们的研究确定了DLNM的关键预测因素,并阐明了患有DLNM的HCC患者的重要预后指标。这些发现为临床医生提供了有价值的工具,可以准确识别DLNM的高危个体,并对该患者亚组进行更精确的风险分层。有可能改善管理策略和患者预后。
OBJECTIVE: This study aims to develop and validate machine learning-based diagnostic and prognostic models to predict the risk of distant lymph node metastases (DLNM) in patients with hepatocellular carcinoma (HCC) and to evaluate the prognosis for this cohort.
METHODS: Utilizing a retrospective design, this investigation leverages data extracted from the Surveillance, Epidemiology, and End Results (SEER) database, specifically the January 2024 subset, to conduct the analysis.
METHODS: The study cohort consists of 15,775 patients diagnosed with HCC as identified within the SEER database, spanning 2016 to 2020.
METHODS: In the construction of the diagnostic model, recursive feature elimination (RFE) is employed for variable selection, incorporating five critical predictors: age, tumor size, radiation therapy, T-stage, and serum alpha-fetoprotein (AFP) levels. These variables are the foundation for a stacking ensemble model, which is further elucidated through Shapley Additive Explanations (SHAP). Conversely, the prognostic model is crafted utilizing stepwise backward regression to select pertinent variables, including chemotherapy, radiation therapy, tumor size, and age. This model culminates in the development of a prognostic nomogram, underpinned by the Cox proportional hazards model.
METHODS: The outcome of the diagnostic model is the occurrence of DLNM in patients. The outcome of the prognosis model is determined by survival time and survival status.
RESULTS: The integrated model developed based on stacking demonstrates good predictive performance and high interpretative variability and differentiation. The area under the curve (AUC) in the training set is 0.767, while the AUC in the validation set is 0.768. The nomogram, constructed using the Cox model, also demonstrates consistent and strong predictive capabilities. At the same time, we recognized elements that have a substantial impact on DLNM and the prognosis and extensively discussed their significance in the model and clinical practice.
CONCLUSIONS: Our study identified key predictive factors for DLNM and elucidated significant prognostic indicators for HCC patients with DLNM. These findings provide clinicians with valuable tools to accurately identify high-risk individuals for DLNM and conduct more precise risk stratification for this patient subgroup, potentially improving management strategies and patient outcomes.