Scholarlink

Background <p>Sepsis-associated acute kidney injury (S-AKI) substantially increases mortality. The recent Phoenix criteria have redefined pediatric sepsis, yet AKI risk factors under this framework remain unclear. This study aimed to develop a machine learning (ML) model to identify key predictors of AKI in pediatric patients with sepsis as defined by the Phoenix criteria.</p> Methods <p>This retrospective cohort study included 2424 pediatric patients with a diagnosis of sepsis, of whom 484 developed AKI according to Kidney Disease: Improving Global Outcomes criteria. Data from the first 24&#xa0;hours of admission were analyzed. The cohort was randomly divided into a training set (70%) and a test set (30%). A least absolute shrinkage and selection operator-random forest hybrid approach selected features, and ten ML algorithms were developed and evaluated on the training set, with their performance subsequently validated on the test set. Model performance was assessed using area under the curve (AUC), accuracy, Brier score, and decision curve analysis. Shapley additive explanations (SHAP) analysis interpreted the optimal model.</p> Results <p>Feature selection identified 13 key predictors, including SpO₂/FiO₂ ratio, international normalized ratio, procalcitonin, absolute neutrophil count, and mean arterial pressure. The categorical boosting (CatBoost) model achieved the best performance, with an AUC of 0.843 [95% confidence interval (CI) = 0.818–0.867] in the training set and 0.797 (95% CI = 0.755–0.839) in the test set. SHAP analysis highlighted procalcitonin and absolute neutrophil count as the most influential features. A web-based tool was created for clinical application.</p> Conclusions <p>Based on the Phoenix criteria, we developed an interpretable CatBoost-based early prediction model and web tool for pediatric S-AKI using 13 clinical features. The model showed good predictive performance and provides a preliminary data-driven framework for S-AKI risk stratification. Future multi-center external validation is needed to confirm generalizability and explore feasibility of clinical integration.</p> Graphical Abstract <p></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

Supervised machine learning models for predicting sepsis-associated acute kidney injury in children: a real-world evaluation

  • 期刊论文

  • 发表日期：

    2026年5月18日

查看全文
  • Dan Shi,
  • Wei Gu,
  • Xue-Jing Yang,
  • Yan-Qun Sun,
  • Jiang-Wen Yin,
  • Hong-Jun Miao,
  • Xu-Hua Ge

摘要

Background

Sepsis-associated acute kidney injury (S-AKI) substantially increases mortality. The recent Phoenix criteria have redefined pediatric sepsis, yet AKI risk factors under this framework remain unclear. This study aimed to develop a machine learning (ML) model to identify key predictors of AKI in pediatric patients with sepsis as defined by the Phoenix criteria.

Methods

This retrospective cohort study included 2424 pediatric patients with a diagnosis of sepsis, of whom 484 developed AKI according to Kidney Disease: Improving Global Outcomes criteria. Data from the first 24 hours of admission were analyzed. The cohort was randomly divided into a training set (70%) and a test set (30%). A least absolute shrinkage and selection operator-random forest hybrid approach selected features, and ten ML algorithms were developed and evaluated on the training set, with their performance subsequently validated on the test set. Model performance was assessed using area under the curve (AUC), accuracy, Brier score, and decision curve analysis. Shapley additive explanations (SHAP) analysis interpreted the optimal model.

Results

Feature selection identified 13 key predictors, including SpO₂/FiO₂ ratio, international normalized ratio, procalcitonin, absolute neutrophil count, and mean arterial pressure. The categorical boosting (CatBoost) model achieved the best performance, with an AUC of 0.843 [95% confidence interval (CI) = 0.818–0.867] in the training set and 0.797 (95% CI = 0.755–0.839) in the test set. SHAP analysis highlighted procalcitonin and absolute neutrophil count as the most influential features. A web-based tool was created for clinical application.

Conclusions

Based on the Phoenix criteria, we developed an interpretable CatBoost-based early prediction model and web tool for pediatric S-AKI using 13 clinical features. The model showed good predictive performance and provides a preliminary data-driven framework for S-AKI risk stratification. Future multi-center external validation is needed to confirm generalizability and explore feasibility of clinical integration.

Graphical Abstract