Development and internal validation of a prediction model for early identification of sepsis-associated acute kidney injury based on admission serum biomarkers: a retrospective cohort study - Report - MDSpire

Development and internal validation of a prediction model for early identification of sepsis-associated acute kidney injury based on admission serum biomarkers: a retrospective cohort study

  • By

  • Chi Wang

  • Rui Ye

  • Xingxin Gong

  • Meng Tang

  • Fei Ding

  • Yi Xie

  • Yanxi Sheng

  • Xin Nie

  • Yong He

  • June 22, 2026

  • 0 min

Share

Clinical Report: Predictive Model for Early Detection of SA-AKI

Overview

This study developed and validated a predictive model for sepsis-associated acute kidney injury (SA-AKI) using first serum laboratory indicators.

Background

Sepsis-associated acute kidney injury (SA-AKI) is a significant complication that increases mortality in critically ill patients. Early detection is crucial for timely interventions, yet traditional diagnostic methods often fail to identify kidney injury promptly.

Data Highlights

IndicatorRisk Factor
Myoglobin (MYO)Yes
Alanine aminotransferase (ALT)Yes
Phosphorus (PO4)Yes
Sodium (Na)Yes
Potassium (K)Yes
Carbon dioxide combining power (CO2-CP)Yes
Platelet (PLT)Yes
Neutrophil (NEUT)Yes

Key Findings

  • The model identified 8 independent risk factors for SA-AKI from first serum indicators.
  • Training cohort AUC was 0.839, and validation cohort AUC was 0.832.
  • Subgroup analyses showed stable performance across age and sex strata (all AUCs > 0.81).
  • A nomogram was developed for individualized risk estimation.
  • The model demonstrated significant clinical utility across a wide threshold probability range.

Clinical Implications

The predictive model can assist healthcare professionals in early risk stratification of sepsis patients for SA-AKI.

Conclusion

The study presents a validated predictive model for SA-AKI risk estimation using initial serum biomarkers, emphasizing the need for further external validation.

Related Resources & Content

  1. Author(s)/Org, Source, Year -- Title
  2. Author(s)/Org, Source, Year -- Title
  3. Author(s)/Org, Source, Year -- Title
  4. Author(s)/Org, Source, Year -- Title
  5. Author(s)/Org, Source, Year -- Title
  6. Author(s)/Org, Source, Year -- Title
  7. Author(s)/Org, Source, Year -- Title
  8. Sepsis-associated acute kidney injury: consensus report of the 28th Acute Disease Quality Initiative workgroup | Nature Reviews Nephrology
  9. Topic
  10. Complementary role of transcriptomic endotyping and protein-based biomarkers for risk stratification in sepsis-associated acute kidney injury | Critical Care | Springer Nature Link

Original Source(s)

Development and internal validation of a prediction model for early identification of sepsis-associated acute kidney injury based on admission serum biomarkers: a retrospective cohort study

  • by Chi Wang, Rui Ye, Xingxin Gong, Meng Tang, Fei Ding, Yi Xie, Yanxi Sheng, Xin Nie, Yong He

  • June 22, 2026

Related Content

Endothelial cell, but not neutrophil, programmed cell death receptor-ligand 1 loss has a morbid impact on experimental murine shock/sepsis-induced lung injury

When Bad Data Enters the Drug Pipeline

Federal prosecutors allege that a Florida physician and research staff fabricated clinical trial records that were submitted into database systems used to evaluate investigational drugs.

Remote Monitoring Approaches to Reduce Readmissions After Infection and Sepsis: A Randomized Clinical Trial