Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 1, 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 (Preprint)

View Full Paper
Ask AI
Bookmark
Share

Authors

XGX. GeWCWeiwei ChenJSJianshan Shi

Discussion

Loading...

Member takes

Overview

This study demonstrates a machine learning model for predicting sepsis-associated acute kidney injury, suggesting improved clinical decision support.

Key Points

  • The dual-timepoint LightGBM model achieved an AUC of 0.839 for the 48-hour prediction task in internal testing.
  • External validation demonstrated AUCs of 0.770 and 0.793, highlighting robust predictive performance across cohorts.
  • Using clinical data, two-stage feature selection combined LightGBM and SHAP methods to enhance prediction accuracy.
  • This interpretable prediction system supports precision management of sepsis-associated acute kidney injury in various patient subgroups.

Cite This Study

Ge et al. (2025) studied this question.

synapsesocial.com/papers/68dd91d5fe798ba2fc498e0ehttps://doi.org/10.2196/preprints.73840
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Prediction of Moderate-to-Severe Sepsis-Associated Acute Kidney Injury Using a Dual-Timepoint Machine Learning Model: Development, Multiregional Validation, and Clinical Deployment Study2025
  2. 2Interpretable Machine Learning for Early Prediction of Acute Kidney Disease (AKD) in Sepsis-Associated Acute Kidney Injury (SA-AKI): A Multicenter Cohort Study with External Validation 2025
  3. 3Risk stratification for in-hospital mortality in sepsis-associated acute kidney injury patients receiving continuous renal replacement therapy: an interpretable, externally validated machine learning study2026
  4. 4Machine learning-based mortality risk prediction models in patients with sepsis-associated acute kidney injury: a systematic review2025 · 7 citations
  5. 5Machine Learning Models for Predicting 28-Day Mortality in Gastrointestinal Bleeding with Acute Kidney Injury: A MIMIC-IV-Based Study2025