Cardoso Pedro, Young Katie G, Hopkins Rhian, Mateen Bilal A, Pearson Ewan R, Hattersley Andrew T, McKinley Trevelyan J, Shields Beverley M, Dennis John M
Clinical and Biomedical Sciences, University of Exeter Medical School, Exeter, UK.
Institute of Health Informatics, University College London, London, UK.
Diabetes Obes Metab. 2025 Aug;27(8):4320-4329. doi: 10.1111/dom.16470. Epub 2025 May 16.
A precision medicine approach in type 2 diabetes (T2D) needs to consider potential treatment risks alongside established benefits for glycaemic and cardiometabolic outcomes. Considering five major T2D drug classes, we aimed to describe variation in short-term discontinuation (a proxy of overall tolerability) by drug and patient routine clinical features and determine whether combining features in a model to predict drug class-specific tolerability has clinical utility.
UK routine clinical data (Clinical Practice Research Datalink, 2014-2020) of people with T2D initiating glucagon-like peptide-1 receptor agonists (GLP-1RA), dipeptidyl peptidase-4 inhibitors (DPP4i), sodium-glucose co-transporter-2 inhibitors (SGLT2i), thiazolidinediones (TZD) and sulfonylureas (SU) in primary care were studied. We first described the proportions of short-term (3-month) discontinuation by drug class across subgroups stratified by routine clinical features. We then assessed the performance of combining features to predict discontinuation by drug class using a flexible machine learning algorithm (a Bayesian Additive Regression Tree).
Amongst 182 194 treatment initiations, discontinuation varied modestly by clinical features. Higher discontinuation on SGLT2i and GLP-1RA was seen for older patients and those with longer diabetes duration. For most other features, discontinuation differences were similar by drug class, with higher discontinuation for patients who had previously discontinued metformin, females and people of South-Asian and Black ethnicities. Lower discontinuation was seen for patients currently taking statins and blood pressure medication. The model combining all sociodemographic and clinical features had a low ability to predict discontinuation (AUC = 0.61).
A model-based approach to predict drug-specific discontinuation for individual patients with T2D has low clinical utility. Instead of likely tolerability, prescribing decisions in T2D should focus on drug-specific side-effect risks and differences in the glycaemic and cardiometabolic benefits of available medication classes.
2型糖尿病（T2D）的精准医疗方法需要在考虑已确定的血糖和心脏代谢结局获益的同时，兼顾潜在治疗风险。考虑到五大类T2D药物，我们旨在描述药物及患者常规临床特征导致的短期停药（总体耐受性的一个指标）差异，并确定在模型中合并特征以预测特定药物类别的耐受性是否具有临床实用性。
研究了英国初级医疗中开始使用胰高血糖素样肽-1受体激动剂（GLP-1RA）、二肽基肽酶-4抑制剂（DPP4i）、钠-葡萄糖协同转运蛋白-2抑制剂（SGLT2i）、噻唑烷二酮类（TZD）和磺脲类（SU）的T2D患者的常规临床数据（临床实践研究数据链，2014 - 2020年）。我们首先描述了按常规临床特征分层的各亚组中不同药物类别短期（3个月）停药的比例。然后，我们使用灵活的机器学习算法（贝叶斯加法回归树）评估合并特征以预测特定药物类别停药情况的性能。
在182194次治疗起始中，停药情况因临床特征而有适度差异。老年患者以及糖尿病病程较长的患者使用SGLT2i和GLP-1RA时停药率较高。对于大多数其他特征，不同药物类别之间的停药差异相似，曾停用二甲双胍的患者、女性以及南亚和黑人种族人群的停药率较高。目前正在服用他汀类药物和血压药物的患者停药率较低。合并所有社会人口统计学和临床特征的模型预测停药的能力较低（AUC = 0.61）。
基于模型的方法预测个体T2D患者特定药物的停药情况临床实用性较低。T2D的处方决策不应侧重于可能的耐受性，而应关注特定药物的副作用风险以及现有药物类别在血糖和心脏代谢方面的获益差异。
