中国血液净化

中国血液净化 ›› 2025, Vol. 24 ›› Issue (08): 623-628.doi: 10.3969/j.issn.1671-4091.2025.08.002

• 临床研究 • 上一篇    下一篇

维持性血液透析患者发生血管钙化的3种机器学习预测模型构建及效能比较

白伟伟    杜书同    马伟华    王雅静    王 娜   

  1. 061000 沧州，1沧州市人民医院肾病内科
  • 收稿日期:2024-12-25 修回日期:2025-03-28 出版日期:2025-08-12 发布日期:2025-08-12
  • 通讯作者: 杜书同 E-mail:553192570@qq.com
  • 基金资助:
    沧州市重点研发计划指导项目(213106068)

Developemnt and comparison of the effectiveness of three machine learning prediction models for vascular calcification in patients with maintenance hemodialysis

BAI Wei-wei1 DU Shu-tong, MA Wei-hua, WANG Ya-jing, WANG Na   

  1. Department of Nephrology, Cangzhou People's Hospital, Cangzhou 061000, China
  • Received:2024-12-25 Revised:2025-03-28 Online:2025-08-12 Published:2025-08-12
  • Contact: 061000 沧州，1沧州市人民医院肾病内科 E-mail:553192570@qq.com

摘要： 目的  构建并对比维持性血液透析患者发生血管钙化的3种机器学习预测模型。 方法  选取300例维持性血液透析患者为研究对象，按照7:3的比例随机分为训练集(210例)和验证集(90例)，根据患者是否发生血管钙化将训练集分为有钙化组(124例)和无钙化组(86例)。分别采用Logistic回归、随机森林、支持向量机构建维持性血液透析患者发生血管钙化的预测模型，并使用验证集数据评价这3种机器学习预测模型的预测能力。 结果  在训练集中，Logistic回归模型、随机森林模型、支持向量机的AUC分别为0.835、0.886、0.872；在验证集中Logistic回归模型、随机森林模型、支持向量机的AUC分别为0.823、0.879、0.866。Delong检验显示3种机器学习预测模型的AUC具有差异(Z=2.663、2.751，  P=0.003、0.001)。Logistic回归模型、随机森林模型、支持向量机模型均具有较好的一致性(χ2=4.018、4.661、3.892，P=0.642、0.887、0.739)。 结论  基于机器学习的维持性血液透析患者发生血管钙化的Logistic回归、随机森林、支持向量机模型均显示出较好的预测效果，其中随机森林模型的表现最好。

关键词: 维持性血液透析, 血管钙化, 机器学习, 预测模型

Abstract: Objective  To develop and compare three machine learning prediction models for predicting vascular calcification in patients with maintenance hemodialysis (MHD).  Methods  A total of 300 MHD patients were enrolled and randomly divided into a training set (n=210) and a validation set (n=90) in a 7:3 ratio. Based on the presence or absence of vascular calcification, the training set was further categorized into a calcification group (n=124) and a non-calcification group (n=86). Logistic Regression (LR), Random Forest (RF), and Support Vector Machine (SVM) models were developed to predict vascular calcification. The predictive performance of these models was evaluated using the validation set.  Results  In the training set, the area under curve (AUC) values for the LR, RF, and SVM models were 0.835, 0.886, and 0.872, respectively. In the validation set, the AUC values were 0.823, 0.879, and 0.866, respectively. DeLong's test showed significant differences in the AUC values among the three models (Z=2.663, 2.751; P=0.003, 0.001). All three models demonstrated good goodness-of-fit (χ²=4.018, 4.661, 3.892; P=0.642, 0.887, 0.739).  Conclusion  The LR, RF, and SVM machine learning models demonstrated good predictive performance for vascular calcification in MHD patients, with the Random Forest model showing superior performance.

Key words: Maintenance hemodialysis, Vascular calcification, Machine learning, Predictive model

中图分类号: