竞争风险下高维变量选择与预测:在SEER-Medicare关联数据中的应用
该研究针对竞争风险数据,在cause-specific和subdistribution两种风险模型下,通过模拟实验评估现有机器学习方法的高维预测与变量选择准确性,并比较不同惩罚参数选择策略;随后将最优方法应用于SEER-Medicare前列腺癌数据,预测癌症与非癌症死亡。
要点
- 竞争风险高维预测需区分cause-specific与subdistribution模型。
- 惩罚参数选择策略影响机器学习方法的预测与变量选择性能。
- 最优方法可用于SEER-Medicare前列腺癌死亡原因预测。
核心结论
- 在竞争风险高维场景下,现有机器学习方法的预测与变量选择准确性因模型和惩罚参数选择而异,需通过模拟评估确定最优策略。
研究设计与样本
- 研究通过广泛模拟实验评估机器学习方法在cause-specific和subdistribution风险模型下的表现,并应用于SEER-Medicare关联数据。
主要发现
- 模拟实验比较了不同惩罚参数选择方法下各机器学习方法的预测与变量选择准确性,并据此选出最优方法。
- 最优方法被应用于SEER-Medicare数据,用于预测前列腺癌患者的癌症与非癌症死亡。
临床怎么用
- 在前列腺癌竞争风险预测中,可参考该研究筛选的最优机器学习方法与惩罚参数策略进行高维变量选择与风险预测。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
Competing risk analysis considers event times due to multiple causes or of more than one event types. Commonly used regression models for such data include (1) cause-specific hazards model, which focuses on modeling one type of event while acknowledging other event types simultaneously, and (2) subdistribution hazards model, which links the covariate effects directly to the cumulative incidence function. Their use in the presence of high-dimensional predictors are largely unexplored. Motivated by an analysis using the linked SEER-Medicare database for the purposes of predicting cancer versus noncancer mortality for patients with prostate cancer, we study the accuracy of prediction and variable selection of existing machine learning methods under both models using extensive simulation experiments, including different approaches to choosing penalty parameters in each method. We then apply the optimal approaches to the analysis of the SEER-Medicare data.
引用
- Hou J, Paravati A, Hou J, et al. High-dimensional variable selection and prediction under competing risks with application to SEER-Medicare linked data. Stat Med. 2018. PMID: 29845637. doi:10.1002/sim.7822
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。