Başkent University Faculty of Medicine, Department of Internal Medicine, Division of General Internal Medicine.
Hacettepe University Faculty of Medicine, Department of Internal Medicine, Division of General Internal Medicine.
Eur J Intern Med. 2023 Aug;114:74-83. doi: 10.1016/j.ejim.2023.05.021. Epub 2023 May 20.
Renin-angiotensin-aldosterone system inhibitors (RAASi) are commonly used medications. Renal adverse events associated with RAASi are hyperkalemia and acute kidney injury. We aimed to evaluate the performance of machine learning (ML) algorithms in order to define event associated features and predict RAASi associated renal adverse events.
Data of patients recruited from five internal medicine and cardiology outpatient clinics were evaluated retrospectively. Clinical, laboratory, and medication data were acquired via electronic medical records. Dataset balancing and feature selection for machine learning algorithms were performed. Random forest (RF), k-nearest neighbor (kNN), naïve Bayes (NB), extreme gradient boosting (xGB), support vector machine (SVM), neural network (NN), and logistic regression (LR) were used to create a prediction model.
409 patients were included, and 50 renal adverse events occurred. The most important features predicting the renal adverse events were the index K and glucose levels, as well as having uncontrolled diabetes mellitus. Thiazides reduced RAASi associated hyperkalemia. kNN, RF, xGB and NN algorithms have the highest and similar AUC (≥ 98%), recall (≥ 94%), specifity (≥ 97%), precision (≥ 92%), accuracy (≥ 96%) and F1 statistics (≥ 94%) performance metrics for prediction.
RAASi associated renal adverse events can be predicted prior to medication initiation by machine learning algorithms. Further prospective studies with large patient numbers are needed to create scoring systems as well as for their validation.
肾素-血管紧张素-醛固酮系统抑制剂（RAASi）是常用的药物。与 RAASi 相关的肾脏不良事件包括高钾血症和急性肾损伤。我们旨在评估机器学习（ML）算法的性能，以便定义与事件相关的特征并预测 RAASi 相关的肾脏不良事件。
回顾性评估了从五个内科和心脏病学门诊招募的患者的数据。通过电子病历获取临床、实验室和药物数据。对机器学习算法进行数据集平衡和特征选择。使用随机森林（RF）、k-最近邻（kNN）、朴素贝叶斯（NB）、极端梯度提升（xGB）、支持向量机（SVM）、神经网络（NN）和逻辑回归（LR）创建预测模型。
共纳入 409 例患者，发生 50 例肾脏不良事件。预测肾脏不良事件的最重要特征是指数 K 和血糖水平，以及患有未控制的糖尿病。噻嗪类药物可降低 RAASi 相关的高钾血症。kNN、RF、xGB 和 NN 算法在预测方面具有最高和相似的 AUC（≥98%）、召回率（≥94%）、特异性（≥97%）、精度（≥92%）、准确性（≥96%）和 F1 统计数据（≥94%）性能指标。
通过机器学习算法，可以在开始用药之前预测 RAASi 相关的肾脏不良事件。需要进一步进行前瞻性研究，纳入大量患者，以创建评分系统并对其进行验证。
