Nicolò Chiara, Périer Cynthia, Prague Melanie, Bellera Carine, MacGrogan Gaëtan, Saut Olivier, Benzekry Sébastien
Mathematical Modeling for Oncology Team, Inria Bordeaux Sud-Ouest, Talence, France.
Institut de Mathématiques de Bordeaux, UMR 5251, CNRS, Bordeaux, France.
JCO Clin Cancer Inform. 2020 Mar;4:259-274. doi: 10.1200/CCI.19.00133.
For patients with early-stage breast cancer, predicting the risk of metastatic relapse is of crucial importance. Existing predictive models rely on agnostic survival analysis statistical tools (eg, Cox regression). Here we define and evaluate the predictive ability of a mechanistic model for time to distant metastatic relapse.
The data we used for our model consisted of 642 patients with 21 clinicopathologic variables. A mechanistic model was developed on the basis of two intrinsic mechanisms of metastatic progression: growth (parameter α) and dissemination (parameter μ). Population statistical distributions of the parameters were inferred using mixed-effects modeling. A random survival forest analysis was used to select a minimal set of five covariates with the best predictive power. These were further considered to individually predict the model parameters by using a backward selection approach. Predictive performances were compared with classic Cox regression and machine learning algorithms.
The mechanistic model was able to accurately fit the data. Covariate analysis revealed statistically significant association of expression with α ( = .001) and expression with μ ( = .009). The model achieved a c-index of 0.65 (95% CI, 0.60 to 0.71) in cross-validation and had predictive performance similar to that of random survival forest (95% CI, 0.66 to 0.69) and Cox regression (95% CI, 0.62 to 0.67) as well as machine learning classification algorithms.
By providing informative estimates of the invisible metastatic burden at the time of diagnosis and forward simulations of metastatic growth, the proposed model could be used as a personalized prediction tool for routine management of patients with breast cancer.
对于早期乳腺癌患者，预测远处转移复发风险至关重要。现有的预测模型依赖于不可知的生存分析统计工具（如Cox回归）。在此，我们定义并评估一个关于远处转移复发时间的机制模型的预测能力。
我们用于模型的数据包括642例患者及21个临床病理变量。基于转移进展的两种内在机制（生长，参数α；播散，参数μ）建立了一个机制模型。使用混合效应模型推断参数的总体统计分布。采用随机生存森林分析选择具有最佳预测能力的最少的五个协变量集。通过向后选择方法进一步单独考虑这些协变量来预测模型参数。将预测性能与经典Cox回归和机器学习算法进行比较。
该机制模型能够准确拟合数据。协变量分析显示，[具体变量1]表达与α具有统计学显著关联（P = 0.001），[具体变量2]表达与μ具有统计学显著关联（P = 0.009）。该模型在交叉验证中的c指数为0.65（95%CI，0.60至0.71），其预测性能与随机生存森林（95%CI，0.66至0.69）、Cox回归（95%CI，0.62至0.67）以及机器学习分类算法相似。
通过在诊断时提供关于不可见转移负担的信息性估计以及转移生长的前瞻性模拟，所提出的模型可作为乳腺癌患者常规管理的个性化预测工具。
