Comparison of causal forest and regression-based approaches to evaluate treatment effect heterogeneity: an application for type 2 diabetes precision medicine.
Comparison of causal forest and regression-based approaches to evaluate treatment effect heterogeneity: an application for type 2 diabetes precision medicine.
复制标题
DOI：
10.1186/s12911-023-02207-2
复制
发表时间：
2023-06-16
影响因子：
3.5
通讯作者：
Dennis, John M.
中科院分区：
文献类型：
--
作者：
Venkatasubramaniam, Ashwini;Mateen, Bilal A.;Shields, Beverley M.;Hattersley, Andrew T.;Jones, Angus G.;Vollmer, Sebastian J.;Dennis, John M.
关键词：
精准医学需要可靠地识别不同可用治疗方法的患者水平结果的变化，通常称为治疗效果异质性。我们的目的是根据因果森林机器学习算法和惩罚回归模型预测的个体水平治疗效果来评估个体化治疗选择策略的比较效用。队列研究描述了开始 SGLT2 抑制剂或 DPP4 抑制剂治疗的 2 型糖尿病患者的个体水平降糖反应（HbA1c 降低 6 个月）。模型开发集由 SGLT2 抑制剂与 DPP4 抑制剂的 CANTATA-D 和 CANTATA-D2 随机临床试验的 1,428 名参与者组成。为了进行外部验证，在英国初级保健中的 18,741 名患者中评估了根据预测 HbA1c 获益大小定义的患者阶层中观察到的 HbA1c 与预测的差异的校准（临床实践研究数据链接）。在使用这两种方法的临床试验参与者中检测到治疗效果的异质性（预计 SGLT2 抑制剂治疗相对于 DPP4 抑制剂治疗有益处的比例：因果森林：98.6%；惩罚回归：81.7%）。在验证中，惩罚回归的校准效果很好，但因果森林的校准效果不佳。使用惩罚回归而非因果森林确定了使用 SGLT2 抑制剂可带来 HbA1c 益处 > 10 mmol/mol 的阶层（3.7% 的患者，观察到的益处为 11.0 mmol/mol [95%CI 8.0–14.0]），并确定了使用 SGLT2 抑制剂可带来 5–10 mmol HbA1c 益处的更大阶层惩罚回归（回归：20.9% 的患者，观察到的获益 7.8 mmol/mol (95%CI 6.7–8.9)；因果森林 11.6%，观察到的获益 8.7 mmol/mol (95%CI 7.4–10.1)。与临床数据结果预测的最新结果一致，在评估治疗效果异质性时，研究人员不应依赖因果森林或其他类似的机器学习算法单独，并且必须将输出与标准回归进行比较，在本次评估中，标准回归更优秀，在线版本包含可在 10.1186/s12911-023-02207-2 获取的补充材料。
Precision medicine requires reliable identification of variation in patient-level outcomes with different available treatments, often termed treatment effect heterogeneity. We aimed to evaluate the comparative utility of individualized treatment selection strategies based on predicted individual-level treatment effects from a causal forest machine learning algorithm and a penalized regression model. Cohort study characterizing individual-level glucose-lowering response (6 month reduction in HbA1c) in people with type 2 diabetes initiating SGLT2-inhibitor or DPP4-inhibitor therapy. Model development set comprised 1,428 participants in the CANTATA-D and CANTATA-D2 randomised clinical trials of SGLT2-inhibitors versus DPP4-inhibitors. For external validation, calibration of observed versus predicted differences in HbA1c in patient strata defined by size of predicted HbA1c benefit was evaluated in 18,741 patients in UK primary care (Clinical Practice Research Datalink). Heterogeneity in treatment effects was detected in clinical trial participants with both approaches (proportion predicted to have a benefit on SGLT2-inhibitor therapy over DPP4-inhibitor therapy: causal forest: 98.6%; penalized regression: 81.7%). In validation, calibration was good with penalized regression but sub-optimal with causal forest. A strata with an HbA1c benefit > 10 mmol/mol with SGLT2-inhibitors (3.7% of patients, observed benefit 11.0 mmol/mol [95%CI 8.0–14.0]) was identified using penalized regression but not causal forest, and a much larger strata with an HbA1c benefit 5–10 mmol with SGLT2-inhibitors was identified with penalized regression (regression: 20.9% of patients, observed benefit 7.8 mmol/mol (95%CI 6.7–8.9); causal forest 11.6%, observed benefit 8.7 mmol/mol (95%CI 7.4–10.1). Consistent with recent results for outcome prediction with clinical data, when evaluating treatment effect heterogeneity researchers should not rely on causal forest or other similar machine learning algorithms alone, and must compare outputs with standard regression, which in this evaluation was superior. The online version contains supplementary material available at 10.1186/s12911-023-02207-2.
登录
查看更多内容
影响因子：
8.2
作者：
Lavalle-Gonzalez, F. J.;Januszewicz, A.;Davidson, J.;Tong, C.;Qiu, R.;Canovatchel, W.;Meininger, G.
通讯作者：
Meininger, G.
DOI：
10.1002/psp4.12715
发表时间：
2021-11
期刊：
CPT: pharmacometrics & systems pharmacology
影响因子：
--
作者：
Gong X;Hu M;Basu M;Zhao L
通讯作者：
Zhao L
影响因子：
2
作者：
Efthimiou, Orestis;Hoogland, Jeroen;White, Ian R.
通讯作者：
White, Ian R.
影响因子：
7.2
作者：
Nguyen, Tri-Long;Collins, Gary S.;Le Manach, Yannick
通讯作者：
Le Manach, Yannick
影响因子：
1.8
作者：
Bleich, Justin;Kapelner, Adam;Jensen, Shane T.
通讯作者：
Jensen, Shane T.