Prediction of Moderate-to-Severe Sepsis-Associated Acute Kidney Injury Using a Dual-Timepoint Machine Learning Model: Development, Multiregional Validation, and Clinical Deployment Study
Vorhersage von moderat bis schwerer sepsisassoziierter akuter Nierenschädigung mit einem Dual-Timepoint-Machine-Learning-Modell: Entwicklungs-, multiregionale Validierungs- und klinische Implementierungsstudie
Journal of Medical Internet Research · 2025-09-30 · 27 · e73840
DOI: 10.2196/73840 ↗Auf einen Blick
Ein Dual-Timepoint-LightGBM-Modell sagte moderat bis schwere SA-AKI in ICU-Daten vorher. Die AUC lag je nach Datensatz bei 0,839, 0,770/0,793 und 0,834, 0,720/0,773.
Fragestellung
Lässt sich moderat bis schwere SA-AKI mit einem dynamischen, stufenbezogenen Machine-Learning-Modell vorhersagen?
Methode
Entwicklung und Validierung mit 3 unabhängigen ICU-Datenbanken; Feature-Selection mit LightGBM und SHAP, Modellvergleich mit 8 ML-Algorithmen; interne 5-fach-Validierung und externe multiregionale Validierung.
Ergebnisse
48 h: AUC 0,839 (95 %-KI 0,824–0,854) intern, 0,770 (95 %-KI 0,762–0,779) extern, 0,793 (95 %-KI 0,726–0,856) extern. 7 d: 0,834 (95 %-KI 0,818–0,850), 0,720 (95 %-KI 0,711–0,729), 0,773 (95 %-KI 0,687–0,851).
Schlussfolgerung der Autor:innen
Die Autoren berichten, dass das System eine stufenbezogene Risikobewertung für moderat bis schwere SA-AKI liefert und als interpretierbares klinisches Entscheidungsunterstützungswerkzeug umgesetzt wurde.
Kernaussagen
- 48 h und 7 d wurden als kritische Zeitpunkte identifiziert.
- LightGBM zeigte die beste Vorhersageleistung.
- Wichtige Prädiktoren waren u. a. Urinausscheidung und mechanische Beatmung.
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
At a glance
Validierungsstudie in Journal of Medical Internet Research, published online on 2025-09-30. Written by Xinbo Ge and 9 co-authors. Institution: Department of Critical Care Medicine, The First Affiliated Hospital of Hainan Medical University, Haikou, China. Major MEDLINE topics: Acute Kidney Injury, Machine Learning, Sepsis. Cited 16 times so far (Crossref); 38 references. The full text is freely available in PubMed Central.
Abstract (original language)
Background
Sepsis-associated acute kidney injury (SA-AKI) is a frequent and life-threatening complication in patients in the intensive care unit (ICU), significantly increasing both mortality rates and the risk of chronic kidney dysfunction. However, existing prediction models have often focused on overall risk and lack severity-based stratification, which limits their clinical applicability.
Objective
This study aimed to identify critical time points in SA-AKI progression development and validate dynamic, stratified machine learning prediction models for moderate-to-severe (Kidney Disease: Improving Global Outcomes guideline stages 2-3) SA-AKI through multicenter, multiregional external validation, ultimately deploying them as publicly accessible, interpretable clinical decision support tools.
Methods
This study used three independent ICU databases: Medical Information Mart for Intensive Care-IV v3.0 (n=12,842; model development and internal validation), electronic ICU collaborative research database v2.0 (n=15,767; North American multicenter external validation), and the First Affiliated Hospital of Hainan Medical University ICU (n=210; Chinese single-center external validation). We identified 48 hours (acute phase) and 7 days (subacute phase) as critical time points. Based on clinical data from the first 24 hours of ICU admission, we used a two-stage feature selection process combining light gradient boosting machine (LightGBM) and Shapley additive explanation (SHAP) cross-validation analysis with clinical expert review, followed by modeling using 8 machine learning algorithms. The optimal model was selected based on the area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis. Internal validation used 5-fold cross-validation, while external validation and subgroup analyses assessed generalizability across different regions and populations. SHAP values and partial dependence plots were used to interpret the influence of key features on predictions.
Results
Our dual-timepoint LightGBM model demonstrated robust predictive performance. For the 48-hour prediction task, the model achieved an AUC of 0.839 (95% CI 0.824-0.854) in the internal test set, with AUCs of 0.770 (95% CI 0.762-0.779) and 0.793 (95% CI 0.726-0.856) in the external validation cohorts, respectively. For the 7-day prediction task, the corresponding AUCs across the three cohorts were 0.834 (95% CI 0.818-0.850), 0.720 (95% CI 0.711-0.729), and 0.773 (95% CI 0.687-0.851), respectively. Subgroup analyses confirmed robust model performance across different age, gender, and comorbidity subgroups. SHAP analysis identified urine output, mechanical ventilation, Sequential Organ Failure Assessment score, creatinine, Glasgow Coma Scale score, and nephrotoxic drug use as core predictive features. Decision curve analysis confirmed that LightGBM provided consistent clinical benefit across different threshold ranges. The optimal LightGBM model was deployed as a publicly accessible web-based prediction app with integrated SHAP interpretability.
Conclusions
This study developed and validated a dynamic, stratified prediction system that provides stage-specific risk assessment for moderate-to-severe SA-AKI. The system underwent rigorous multiregional, multicenter validation and was translated into an interpretable clinical decision support tool, providing a scientific foundation for precision management.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Department of Critical Care Medicine, The First Affiliated Hospital of Hainan Medical University, Haikou, China.
- Emergency and Trauma College, Hainan Medical University, Haikou, China.
- School of Intelligent Medicine and Technology, Hainan Engineering Research Center for Health Big Data, Hainan Medical University, Haikou, China.
- Department of Interventional Vascular Surgery, The First Affiliated Hospital of Hainan Medical University, Haikou, China.
- Department of Radiology, Wanning Hospital, The First Affiliated Hospital of Hainan Medical University, Wanning, China.
- Department of Emergency Medicine, Wanning Hospital, The First Affiliated Hospital of Hainan Medical University, Wanning, China.
ORCID profiles: Xinbo Ge, Weiwei Chen, Jianshan Shi, Jiaqiang Zhang, Hao Tai, Ying Zhang, Biao Wang, Wei Liu, Song Chen, Huirui Han
Cite
APA
Ge, X., Chen, W., Shi, J., Zhang, J., Tai, H., Zhang, Y., Wang, B., Liu, W., Chen, S., & Han, H. (2025). Prediction of Moderate-to-Severe Sepsis-Associated Acute Kidney Injury Using a Dual-Timepoint Machine Learning Model: Development, Multiregional Validation, and Clinical Deployment Study. Journal of Medical Internet Research, 27, e73840. https://doi.org/10.2196/73840
Vancouver
Ge X, Chen W, Shi J, Zhang J, Tai H, Zhang Y, et al. Prediction of Moderate-to-Severe Sepsis-Associated Acute Kidney Injury Using a Dual-Timepoint Machine Learning Model: Development, Multiregional Validation, and Clinical Deployment Study. Journal of Medical Internet Research. 2025;27:e73840. doi:10.2196/73840
BibTeX
@article{Ge2025,
author = {Ge, Xinbo and Chen, Weiwei and Shi, Jianshan and Zhang, Jiaqiang and Tai, Hao and Zhang, Ying and Wang, Biao and Liu, Wei and Chen, Song and Han, Huirui},
title = {Prediction of Moderate-to-Severe Sepsis-Associated Acute Kidney Injury Using a Dual-Timepoint Machine Learning Model: Development, Multiregional Validation, and Clinical Deployment Study},
journal = {Journal of Medical Internet Research},
year = {2025},
volume = {27},
pages = {e73840},
doi = {10.2196/73840}
}
EUVIMED