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 - Takeaways - 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

  • 1

    The study developed a predictive model for sepsis-associated acute kidney injury (SA-AKI) using first serum biomarkers from 1,573 patients.

  • 2

    Eight independent risk factors for SA-AKI were identified, including myoglobin, alanine aminotransferase, and phosphorus.

  • 3

    The model demonstrated favorable discrimination with AUC values of 0.839 in the training cohort and 0.832 in the validation cohort.

  • 4

    A nomogram was created to facilitate individualized risk estimation for SA-AKI in sepsis patients.

  • 5

    Subgroup analyses indicated stable model performance across different age and sex strata, with all AUCs exceeding 0.81.

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

Cytokine-induced chromatin accessibility in whole blood neutrophils links to sepsis transcriptional states

Teleology of immune system response to sepsis – failure due to dysregulation or adaptive response that sometimes fails?

A machine learning integrated multi-omics framework for risk prediction and target discovery in insomnia aggravated sepsis induced acute lung injury