Akimoto Hayato, Nagashima Takuya, Minagawa Kimino, Hayakawa Takashi, Takahashi Yasuo, Asai Satoshi
Division of Pharmacology, Department of Biomedical Sciences, Nihon University School of Medicine; Oyaguchi-Kamicho 30-1, Itabashi-ku, Tokyo, Japan.
Division of Genomic Epidemiology and Clinical Trials, Clinical Trials Research Center, Nihon University School of Medicine, Itabashi-ku, Tokyo, Japan.
Pharmacol Res Perspect. 2025 Feb;13(1):e70055. doi: 10.1002/prp2.70055.
The dose-response relationship between metformin and change in hemoglobin A1c (HbA1c) shows a maximum at 1500-2000 mg/day in patients with type 2 diabetes (T2D) in the U.S. In Japan, there is little evidence on the HbA1c-lowering effect of high-dose metformin because the maintenance and maximum doses of metformin were raised in 2010. The aim of this study was to investigate whether there is saturation of the dose-response relationship for metformin in Japanese T2D patients. Longitudinal clinical information of T2D patients was extracted from electronic medical records. Supervised machine learning models with random effect were constructed to predict change in HbA1c: generalized linear mixed-effects models (GLMM) with/without a feature selection and combining tree-boosting with Gaussian process and mixed-effects models (GPBoost). GPBoost was interpreted by SHapley Additive exPlanations (SHAP) and partial dependence. GPBoost had better predictive performance than GLMM with/without feature selection: root mean square error was 0.602 (95%CI 0.523-0.684), 0.698 (0.629-0.774) and 0.678 (0.609-0.753), respectively. Interpretation of GPBoost by SHAP and partial dependence suggested that the relationship between the daily dose of metformin and change in HbA1c is non-linear rather than linear, and the HbA1c-lowering effect of metformin reaches a maximum at 1500 mg/day. Interpretation of GPBoost, a non-linear supervised machine-learning algorithm, suggests that there is saturation of the dose-response relationship of metformin in Japanese patients with T2D. This finding may be useful for decision-making in pharmacotherapy for T2D.
在美国，2型糖尿病（T2D）患者中，二甲双胍与糖化血红蛋白（HbA1c）变化之间的剂量反应关系在每日1500 - 2000毫克时显示出最大值。在日本，由于二甲双胍的维持剂量和最大剂量于2010年提高，关于高剂量二甲双胍降低HbA1c效果的证据很少。本研究的目的是调查日本T2D患者中二甲双胍的剂量反应关系是否存在饱和现象。从电子病历中提取T2D患者的纵向临床信息。构建具有随机效应的监督机器学习模型来预测HbA1c的变化：有/无特征选择的广义线性混合效应模型（GLMM）以及将树增强与高斯过程相结合的混合效应模型（GPBoost）。通过SHapley Additive exPlanations（SHAP）和部分依赖对GPBoost进行解释。GPBoost比有/无特征选择的GLMM具有更好的预测性能：均方根误差分别为0.602（95%CI 0.523 - 0.684）、0.698（0.629 - 0.774）和0.678（0.609 - 0.753）。通过SHAP和部分依赖对GPBoost的解释表明，二甲双胍日剂量与HbA1c变化之间的关系是非线性而非线性的，并且二甲双胍降低HbA1c的效果在每日1500毫克时达到最大值。对非线性监督机器学习算法GPBoost的解释表明，日本T2D患者中二甲双胍的剂量反应关系存在饱和现象。这一发现可能有助于T2D药物治疗的决策。
