Department of Gastrointestinal Surgery, Harbin Medical University Cancer Hospital, Harbin 150081, Heilongjiang Province, China.
Department of Gastroenterological Surgery, Harbin Medical University Cancer Hospital, Harbin 150081, Heilongjiang Province, China.
World J Gastroenterol. 2024 Oct 28;30(40):4354-4366. doi: 10.3748/wjg.v30.i40.4354.
Although immune checkpoint inhibitors (ICIs) have demonstrated significant survival benefits in some patients diagnosed with gastric cancer (GC), existing prognostic markers are not universally applicable to all patients with advanced GC.
To investigate biomarkers that predict prognosis in GC patients treated with ICIs and develop accurate predictive models.
Data from 273 patients diagnosed with GC and distant metastasis, who un-derwent ≥ 1 cycle(s) of ICIs therapy were included in this study. Patients were randomly divided into training and test sets at a ratio of 7:3. Training set data were used to develop the machine learning models, and the test set was used to validate their predictive ability. Shapley additive explanations were used to provide insights into the best model.
Among the 273 patients with GC treated with ICIs in this study, 112 died within 1 year, and 129 progressed within the same timeframe. Five features related to overall survival and 4 related to progression-free survival were identified and used to construct eXtreme Gradient Boosting (XGBoost), logistic regression, and decision tree. After comprehensive evaluation, XGBoost demonstrated good accuracy in predicting overall survival and progression-free survival.
The XGBoost model aided in identifying patients with GC who were more likely to benefit from ICIs therapy. Patient nutritional status may, to some extent, reflect prognosis.
尽管免疫检查点抑制剂（ICIs）在一些诊断为胃癌（GC）的患者中显示出显著的生存获益，但现有的预后标志物并非普遍适用于所有晚期 GC 患者。
探究预测接受 ICI 治疗的 GC 患者预后的生物标志物，并开发准确的预测模型。
本研究纳入了 273 例经诊断患有 GC 且发生远处转移、接受了≥1 个周期 ICI 治疗的患者。患者按 7:3 的比例随机分为训练集和测试集。训练集数据用于开发机器学习模型，测试集用于验证其预测能力。Shapley 加性解释用于深入了解最佳模型。
在本研究中，273 例接受 ICI 治疗的 GC 患者中，112 例在 1 年内死亡，129 例在同一时间段内进展。确定了 5 个与总生存期相关的特征和 4 个与无进展生存期相关的特征，并用于构建极端梯度提升（XGBoost）、逻辑回归和决策树。经过综合评估，XGBoost 在预测总生存期和无进展生存期方面表现出良好的准确性。
XGBoost 模型有助于识别更有可能从 ICI 治疗中获益的 GC 患者。患者的营养状况在一定程度上可能反映预后。
