Machine learning-based prediction of a high-risk kidney function trajectory class after acute kidney injury

Clinical Snapshot

Key Findings

• P Value: Not reported in abstract

• Effect Size: AUROC 0.974 for 10-variable XGBoost model

• Primary Outcome: Prediction of membership in high-risk eGFR trajectory class (Steady Low)

• Nnt Or Sensitivity: Sensitivity 0.913, Specificity 0.919

• Confidence Interval: Not reported in abstract

Clinical Application

High feasibility using routinely collected clinical data within 3 months post-discharge Relevant to Australian nephrology practice for post-AKI monitoring, aligns with ANZDATA registry outcomes tracking, could inform PBS-subsidised nephrology referrals Adults with acute kidney injury requiring hospitalisation with available post-discharge eGFR monitoring

Abstract

OBJECTIVES: Monitoring kidney function after acute kidney injury (AKI) hospitalisation is essential for identifying patients at risk of rapid progression. This study developed a machine learning (ML) model to predict membership in a high-risk longitudinal estimated glomerular filtration rate (eGFR) trajectory associated with subsequent kidney replacement therapy (KRT) initiation. METHODS: We conducted a cohort study of 88 632 adults with ≥2 post-discharge eGFR measurements between 2010 and 2017. Joint latent class mixed models were used to identify dynamic eGFR trajectories from 665 499 measurements. Patient-level data splitting (80/20) was strictly enforced. Extreme gradient boosting (XGBoost) and random forest models were trained using clinical features within 3 months after discharge to predict membership in the highest-risk eGFR trajectory class. RESULTS: Three eGFR trajectories were identified: Steady Low (high-risk phenotype), Slow Decline and Recovery. The Steady Low group showed the strongest association with KRT. The 10-variable XGBoost model demonstrated excellent discrimination (AUROC 0.974, sensitivity 0.913, specificity 0.919). The eGFR slope from discharge to 3 months was the most influential predictor of high-risk progression. DISCUSSION: Although the study was limited to a single healthcare system, this ML framework identified patients at risk of rapid kidney function decline using routinely available clinical data. The model supports early risk stratification after AKI and may enable more timely kidney-protective interventions. External validation, calibration assessment and benchmarking against simpler eGFR-based rules remain important next steps. CONCLUSION: A 10-variable XGBoost model accurately identifies patients with deteriorative eGFR trajectories (Steady Low) early after discharge, providing a practical framework for personalised post-AKI kidney care.

References

1. 1.Liu, C. L., Tain, Y. L., Lin, C. C., Peng, Y. L., & Hsu, C. N. (2026). Machine learning-based prediction of a high-risk kidney function trajectory class after acute kidney injury. BMJ Health & Care Informatics. https://doi.org/10.1136/bmjhci-2025-101578