Scholarlink

Background <p>Arteriovenous fistula stenosis is a common complication in hemodialysis patients, yet effective predictive tools are lacking. This study aims to develop an interpretable machine learning model for stenosis risk prediction.</p> Methods <p>Clinical data from 974 patients (55 features) undergoing arteriovenous fistula dialysis at The Central Hospital of Wuhan (2017–2024) were analyzed retrospectively. The dataset was split into training (70%) and test (30%) sets. Seven models—Random Forest, XGBoost, Support Vector Machine, Logistic Regression, K-Nearest Neighbors, Artificial Neural Network, and Decision Tree—were trained. Performance was evaluated using F1 score, accuracy, specificity, precision, recall, and AUC-ROC. SHAP values identified key predictors in the optimal model.</p> Results <p>XGBoost achieved the highest AUC (0.829, 95% CI 0.785–0.880). SHAP analysis highlighted seven critical predictors: number of surgeries, prothrombin time activity, lymphocyte count, fistula duration, triglycerides, vitamin B12, and C-reactive protein.</p> Conclusion <p>The XGBoost model effectively predicts arteriovenous fistula stenosis risk using clinical data. SHAP explanations enhance clinical interpretability, aiding personalized care strategies.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Machine learning-based risk prediction model for arteriovenous fistula stenosis

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年3月29日

查看全文
  • Peng Shu,
  • Ling Huang,
  • Shanshan Huo,
  • Jun Qiu,
  • Haitao Bai,
  • Xia Wang,
  • Fang Xu

摘要

Background

Arteriovenous fistula stenosis is a common complication in hemodialysis patients, yet effective predictive tools are lacking. This study aims to develop an interpretable machine learning model for stenosis risk prediction.

Methods

Clinical data from 974 patients (55 features) undergoing arteriovenous fistula dialysis at The Central Hospital of Wuhan (2017–2024) were analyzed retrospectively. The dataset was split into training (70%) and test (30%) sets. Seven models—Random Forest, XGBoost, Support Vector Machine, Logistic Regression, K-Nearest Neighbors, Artificial Neural Network, and Decision Tree—were trained. Performance was evaluated using F1 score, accuracy, specificity, precision, recall, and AUC-ROC. SHAP values identified key predictors in the optimal model.

Results

XGBoost achieved the highest AUC (0.829, 95% CI 0.785–0.880). SHAP analysis highlighted seven critical predictors: number of surgeries, prothrombin time activity, lymphocyte count, fistula duration, triglycerides, vitamin B12, and C-reactive protein.

Conclusion

The XGBoost model effectively predicts arteriovenous fistula stenosis risk using clinical data. SHAP explanations enhance clinical interpretability, aiding personalized care strategies.