Clinical Pharmacology, Roche/Genentech, South San Francisco, California, USA.
Formerly of Department of Statistics, The Ohio State University, Columbus, Ohio, USA.
CPT Pharmacometrics Syst Pharmacol. 2021 Jan;10(1):59-66. doi: 10.1002/psp4.12576. Epub 2020 Dec 13.
Machine learning (ML) was used to leverage tumor growth inhibition (TGI) metrics to characterize the relationship with overall survival (OS) as a novel approach and to compare with traditional TGI-OS modeling methods. Historical dataset from a phase III non-small cell lung cancer study (OAK, atezolizumab vs. docetaxel, N = 668) was used. ML methods support the validity of TGI metrics in predicting OS. With lasso, the best model with TGI metrics outperforms the best model without TGI metrics. Boosting was the best linear ML method for this dataset with reduced estimation bias and lowest Brier score, suggesting better prediction accuracy. Random forest did not outperform linear ML methods despite hyperparameter optimization. Kernel machine was marginally the best nonlinear ML method for this dataset and uncovered nonlinear and interaction effects. Nonlinear ML may improve prediction by capturing nonlinear effects and covariate interactions, but its predictive performance and value need further evaluation with larger datasets.
机器学习 (ML) 被用于利用肿瘤生长抑制 (TGI) 指标来描述与总生存期 (OS) 的关系，这是一种新的方法，并与传统的 TGI-OS 建模方法进行比较。使用了来自 III 期非小细胞肺癌研究 (OAK，atezolizumab 对比 docetaxel，N=668) 的历史数据集。ML 方法支持 TGI 指标在预测 OS 中的有效性。使用lasso，具有 TGI 指标的最佳模型优于没有 TGI 指标的最佳模型。对于该数据集，boosting 是最好的线性 ML 方法，具有较低的估计偏差和最低的 Brier 得分，表明具有更好的预测准确性。尽管进行了超参数优化，但随机森林并未优于线性 ML 方法。核机器对于该数据集是略微最好的非线性 ML 方法，揭示了非线性和交互作用。虽然非线性 ML 可以通过捕捉非线性效应和协变量交互作用来提高预测能力，但它的预测性能和价值需要通过更大的数据集进行进一步评估。
