Department of Endocrinology, Dalian Municipal Central Hospital, Dalian, China.
Graduate School, Dalian Medical University, Dalian, China.
Clin Cardiol. 2024 Apr;47(4):e24264. doi: 10.1002/clc.24264.
Recently, patients with type 2 diabetes mellitus (T2DM) have experienced a higher incidence and severer degree of vascular calcification (VC), which leads to an increase in the incidence and mortality of vascular complications in patients with T2DM.
To construct and validate prediction models for the risk of VC in patients with T2DM.
Twenty-three baseline demographic and clinical characteristics were extracted from the electronic medical record system. Ten clinical features were screened with least absolute shrinkage and selection operator method and were used to develop prediction models based on eight machine learning (ML) algorithms (k-nearest neighbor [k-NN], light gradient boosting machine, logistic regression [LR], multilayer perception [(MLP], Naive Bayes [NB], random forest [RF], support vector machine [SVM], XGBoost [XGB]). Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, and precision.
A total of 1407 and 352 patients were retrospectively collected in the training and test sets, respectively. Among the eight models, the AUC value in the NB model was higher than the other models (NB: 0.753, LGB: 0.719, LR: 0.749, MLP: 0.715, RF: 0.722, SVM: 0.689, XGB:0.707, p < .05 for all). The k-NN model achieved the highest sensitivity of 0.75 (95% confidence interval [CI]: 0.633-0.857), the MLP model achieved the highest accuracy of 0.81 (95% CI: 0.767-0.852) and specificity of 0.875 (95% CI: 0.836-0.912).
This study developed a predictive model of VC based on ML and clinical features in type 2 diabetic patients. The NB model is a tool with potential to facilitate clinicians in identifying VC in high-risk patients.
最近，2 型糖尿病（T2DM）患者的血管钙化（VC）发生率和严重程度更高，导致 T2DM 患者血管并发症的发生率和死亡率增加。
构建和验证 T2DM 患者 VC 风险的预测模型。
从电子病历系统中提取 23 项基线人口统计学和临床特征。采用最小绝对收缩和选择算子法筛选 10 项临床特征，基于 8 种机器学习（ML）算法（k-最近邻[k-NN]、轻梯度提升机、逻辑回归[LR]、多层感知器[(MLP]、朴素贝叶斯[NB]、随机森林[RF]、支持向量机[SVM]、XGBoost[XGB]）建立预测模型。使用受试者工作特征曲线（ROC）下面积（AUC）、准确性和精度评估模型性能。
共回顾性收集了训练集和测试集的 1407 例和 352 例患者。在 8 种模型中，NB 模型的 AUC 值高于其他模型（NB：0.753、LGB：0.719、LR：0.749、MLP：0.715、RF：0.722、SVM：0.689、XGB：0.707，均为<.05）。k-NN 模型的敏感性最高为 0.75（95%置信区间[CI]：0.633-0.857），MLP 模型的准确性最高为 0.81（95%CI：0.767-0.852），特异性最高为 0.875（95%CI：0.836-0.912）。
本研究基于 ML 和 2 型糖尿病患者的临床特征开发了 VC 预测模型。NB 模型是一种有潜力的工具，可以帮助临床医生识别高危患者的 VC。
