Department of Cardiology, the Second Affiliated Hospital of Chongqing Medical University, Chongqing, China.
Medical Data Science Academy, Chongqing Medical University, Chongqing, China.
Front Endocrinol (Lausanne). 2023 Jul 4;14:1184190. doi: 10.3389/fendo.2023.1184190. eCollection 2023.
Diabetic kidney disease (DKD) has been reported as a main microvascular complication of diabetes mellitus. Although renal biopsy is capable of distinguishing DKD from Non Diabetic kidney disease(NDKD), no gold standard has been validated to assess the development of DKD.This study aimed to build an auxiliary diagnosis model for type 2 Diabetic kidney disease (T2DKD) based on machine learning algorithms.
Clinical data on 3624 individuals with type 2 diabetes (T2DM) was gathered from January 1, 2019 to December 31, 2019 using a multi-center retrospective database. The data fell into a training set and a validation set at random at a ratio of 8:2. To identify critical clinical variables, the absolute shrinkage and selection operator with the lowest number was employed. Fifteen machine learning models were built to support the diagnosis of T2DKD, and the optimal model was selected in accordance with the area under the receiver operating characteristic curve (AUC) and accuracy. The model was improved with the use of Bayesian Optimization methods. The Shapley Additive explanations (SHAP) approach was used to illustrate prediction findings.
DKD was diagnosed in 1856 (51.2 percent) of the 3624 individuals within the final cohort. As revealed by the SHAP findings, the Categorical Boosting (CatBoost) model achieved the optimal performance 1in the prediction of the risk of T2DKD, with an AUC of 0.86 based on the top 38 characteristics. The SHAP findings suggested that a simplified CatBoost model with an AUC of 0.84 was built in accordance with the top 12 characteristics. The more basic model features consisted of systolic blood pressure (SBP), creatinine (CREA), length of stay (LOS), thrombin time (TT), Age, prothrombin time (PT), platelet large cell ratio (P-LCR), albumin (ALB), glucose (GLU), fibrinogen (FIB-C), red blood cell distribution width-standard deviation (RDW-SD), as well as hemoglobin A1C(HbA1C).
A machine learning-based model for the prediction of the risk of developing T2DKD was built, and its effectiveness was verified. The CatBoost model can contribute to the diagnosis of T2DKD. Clinicians could gain more insights into the outcomes if the ML model is made interpretable.
糖尿病肾病（DKD）已被报道为糖尿病的主要微血管并发症。虽然肾活检能够将 DKD 与非糖尿病肾病（NDKD）区分开来，但尚未验证评估 DKD 发展的金标准。本研究旨在基于机器学习算法为 2 型糖尿病肾病（T2DKD）建立辅助诊断模型。
使用多中心回顾性数据库，于 2019 年 1 月 1 日至 12 月 31 日期间收集了 3624 名 2 型糖尿病（T2DM）患者的临床数据。数据随机分为训练集和验证集，比例为 8:2。为了确定关键的临床变量，使用了具有最小数量的绝对收缩和选择算子。建立了 15 个机器学习模型来支持 T2DKD 的诊断，并根据接收者操作特征曲线（AUC）和准确性选择最佳模型。使用贝叶斯优化方法改进了模型。使用 Shapley Additive explanations（SHAP）方法来解释预测结果。
在最终队列中，3624 名患者中有 1856 名（51.2%）被诊断为 DKD。根据 SHAP 结果，在预测 T2DKD 风险方面，Categorical Boosting（CatBoost）模型表现最佳，基于前 38 个特征的 AUC 为 0.86。SHAP 结果表明，根据前 12 个特征构建了一个简化的 AUC 为 0.84 的简化 CatBoost 模型。更基本的模型特征包括收缩压（SBP）、肌酐（CREA）、住院时间（LOS）、凝血酶时间（TT）、年龄、凝血酶原时间（PT）、血小板大型细胞比率（P-LCR）、白蛋白（ALB）、血糖（GLU）、纤维蛋白原（FIB-C）、红细胞分布宽度标准差（RDW-SD）以及血红蛋白 A1C（HbA1C）。
建立了一种基于机器学习的预测 T2DKD 风险的模型，并验证了其有效性。CatBoost 模型可用于诊断 T2DKD。如果可以使 ML 模型具有可解释性，临床医生可以更好地了解结果。
