Development and external validation of prediction models for a trial-informed operational composite after stage 3 acute kidney injury
- 1Department of Critical Care Medicine, Beijing Chao-yang Hospital, Capital Medical University
- 2Institute of Cardiovascular Sciences, University College London
Abstract
Renal replacement therapy (RRT) is considered when severe acute kidney injury (AKI) is complicated by severe electrolyte disturbance, acid-base derangement, fluid overload with respiratory compromise, or azotaemia. However, actual RRT initiation is influenced by clinician and centre practice. We developed and externally validated machine-learning models to predict subsequent fulfilment of a trial-informed operational composite within 24–72 h after creatinine- or urine-output-defined stage 3 AKI. The prediction time was 24 h after stage 3 AKI onset. At this landmark, eligible patients remained alive in the ICU and had not received RRT or met any composite criterion. Predictors were routinely collected during the first 24 h. The composite comprised potassium > 6.0 mmol/L; pH ≤ 7.20 with bicarbonate ≤ 12 mmol/L within ± 2 h; fluid balance > 10% of cleaned body weight with PaO₂/FiO₂ ≤200; or blood urea nitrogen > 112 mg/dL. MIMIC-IV included 2,457 patients (238 events, 9.7%) and eICU-CRD 3,228 (145 events, 4.5%). Gradient Boosting achieved internal/external AUROCs of 0.778/0.721, AUPRCs of 0.279/0.131, and Brier scores of 0.079/0.053. External mean predicted risk was 11.8% versus an observed 4.5%; L2-penalized logistic regression and ExtraTrees performed similarly. The models provided moderate discrimination but substantial external overprediction and should not guide RRT initiation.
Related
- Admission-time prediction of 7-day mortality in clinician-attributed hypertensive intracerebral hemorrhage: development and external validation against the ICH score
- Development and external validation of a prediction model for suboptimal orthokeratology control in adolescents
- Integrated transcriptomic and clinical prediction model for malignant pulmonary nodules : Model development, external dataset evaluation, and single-center expression validation
- MRI-Based Radiomics Model for Pretreatment Prediction of Pathological Lymph Node Metastasis in Neuroendocrine Carcinoma of the Cervix: Dual-Center Development and External Validation.
- Development and external validation of a risk prediction tool for recurrent wheeze attacks in preschool children in England.
BibTeX
@article{chen2026development,
title = {{Development and external validation of prediction models for a trial-informed operational composite after stage 3 acute kidney injury}},
author = {Chao-Dong Chen and Peng-Chao Tian and Xin Chen and Fang-Xing Guo and Wen-Xiong Li},
journal = {Scientific Reports},
year = {2026},
month = sep,
doi = {10.1038/s41598-026-72758-7},
url = {https://doi.org/10.1038/s41598-026-72758-7},
note = {CC BY},
}
RIS
TY - JOUR
TI - Development and external validation of prediction models for a trial-informed operational composite after stage 3 acute kidney injury
AU - Chao-Dong Chen
AU - Peng-Chao Tian
AU - Xin Chen
AU - Fang-Xing Guo
AU - Wen-Xiong Li
PY - 2026
DA - 2026/09/01
JO - Scientific Reports
DO - 10.1038/s41598-026-72758-7
UR - https://doi.org/10.1038/s41598-026-72758-7
AB - Renal replacement therapy (RRT) is considered when severe acute kidney injury (AKI) is complicated by severe electrolyte disturbance, acid-base derangement, fluid overload with respiratory compromise, or azotaemia. However, actual RRT initiation is influenced by clinician and centre practice. We developed and externally validated machine-learning models to predict subsequent fulfilment of a trial-informed operational composite within 24–72 h after creatinine- or urine-output-defined stage 3 AKI. The prediction time was 24 h after stage 3 AKI onset. At this landmark, eligible patients remained alive in the ICU and had not received RRT or met any composite criterion. Predictors were routinely collected during the first 24 h. The composite comprised potassium > 6.0 mmol/L; pH ≤ 7.20 with bicarbonate ≤ 12 mmol/L within ± 2 h; fluid balance > 10% of cleaned body weight with PaO₂/FiO₂ ≤200; or blood urea nitrogen > 112 mg/dL. MIMIC-IV included 2,457 patients (238 events, 9.7%) and eICU-CRD 3,228 (145 events, 4.5%). Gradient Boosting achieved internal/external AUROCs of 0.778/0.721, AUPRCs of 0.279/0.131, and Brier scores of 0.079/0.053. External mean predicted risk was 11.8% versus an observed 4.5%; L2-penalized logistic regression and ExtraTrees performed similarly. The models provided moderate discrimination but substantial external overprediction and should not guide RRT initiation.
SN - 2045-2322
ER -