Artificial intelligence for predicting paediatric acute kidney injury: a systematic review and meta-analysis

Acute kidney injury (AKI) in hospitalised children is a major complication associated with significant morbidity and mortality. The integration of artificial intelligence (AI)/machine learning (ML) models may enable early detection and risk stratification. This systematic review evaluates the performance of AI/ML models for predicting paediatric AKI across clinical settings.

We systematically searched PubMed, Embase, and Web of Science for studies applying AI/ML models to predict AKI in paediatric populations. Studies reporting performance metrics such as the area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, and F1 score were included.

Among 470 records identified, 11 studies met the inclusion criteria, with 14 AI/ML models used. The overall sample size included 33 949 paediatric patients with an AKI proportion of 12.5%. Meta-analyses of the AUC were conducted on neural network, gradient boosting, and logistic regression. Gradient boosting had the highest pooled AUC of 0.873 (95% confidence interval 0.836-0.909). Random forest demonstrated the highest median sensitivity (0.821), specificity (0.942), PPV (0.860), NPV (0.935), and accuracy (0.821); however, these metrics could not be pooled due to inconsistent reporting and limited validation.

Gradient boosting, random forest, and logistic regression demonstrated reasonable predictive performance for paediatric AKI prediction within specific clinical contexts. However, small sample size, heterogeneity, lack of testing/validation cohorts, insufficient data, and inconsistent patient populations and AKI diagnostic criteria restrict generalisability.