Yang Lanting, Gabriel Nico, Hernandez Inmaculada, Vouri Scott M, Kimmel Stephen E, Bian Jiang, Guo Jingchuan
Department of Pharmacy and Therapeutics, University of Pittsburgh, Pittsburgh, PA, United States.
Division of Clinical Pharmacy, Skaggs School of Pharmacy and Pharmaceutical Sciences, University of California, San Diego, San Diego, CA, United States.
Front Pharmacol. 2022 Mar 11;13:834743. doi: 10.3389/fphar.2022.834743. eCollection 2022.
To predict acute kidney injury (AKI) risk in patients with type 2 diabetes (T2D) prescribed sodium-glucose cotransporter two inhibitors (SGLT2i). Using a 5% random sample of Medicare claims data, we identified 17,694 patients who filled ≥1 prescriptions for canagliflozin, dapagliflozin and empagliflozin in 2013-2016. The cohort was split randomly and equally into training and testing sets. We measured 65 predictor candidates using claims data from the year prior to SGLT2i initiation. We then applied three machine learning models, including random forests (RF), elastic net and least absolute shrinkage and selection operator (LASSO) for risk prediction. The incidence rate of AKI was 1.1% over a median 1.5 year follow up. Among three machine learning methods, RF produced the best prediction (C-statistic = 0.72), followed by LASSO and elastic net (both C-statistics = 0.69). Among individuals classified in the top 10% of the RF risk score (i.e., high risk group), the actual incidence rate of AKI was as high as 3.7%. In the logistic regression model including 14 important risk factors selected by LASSO, use of loop diuretics [adjusted odds ratio (95% confidence interval): 3.72 (2.44-5.76)] had the strongest association with AKI incidence. Our machine learning model efficiently identified patients at risk of AKI among Medicare beneficiaries with T2D undergoing SGLT2i treatment.
预测使用钠-葡萄糖协同转运蛋白2抑制剂（SGLT2i）治疗的2型糖尿病（T2D）患者发生急性肾损伤（AKI）的风险。利用医疗保险索赔数据的5%随机样本，我们确定了17694名在2013年至2016年期间开具了≥1次卡格列净、达格列净和恩格列净处方的患者。该队列被随机且平均分为训练集和测试集。我们使用SGLT2i起始前一年的索赔数据测量了65个预测指标候选变量。然后，我们应用了三种机器学习模型，包括随机森林（RF）、弹性网和最小绝对收缩和选择算子（LASSO）进行风险预测。在中位1.5年的随访中，AKI的发病率为1.1%。在三种机器学习方法中，RF的预测效果最佳（C统计量=0.72），其次是LASSO和弹性网（C统计量均为0.69）。在RF风险评分排名前10%的个体（即高风险组）中，AKI的实际发病率高达3.7%。在包含LASSO选择的14个重要风险因素的逻辑回归模型中，使用袢利尿剂[调整后的比值比（95%置信区间）：3.72（2.44-5.76）]与AKI发病率的关联最强。我们的机器学习模型有效地识别了接受SGLT2i治疗的T2D医疗保险受益人中具有AKI风险的患者。
