Machine Learning Model for Predicting the Risk of AKI in Early Hemodynamically Stable Sepsis Patients: A Study Based on the MIMIC IV Database - Summary - MDSpire

Machine Learning Model for Predicting the Risk of AKI in Early Hemodynamically Stable Sepsis Patients: A Study Based on the MIMIC IV Database

  • By

  • He, Miao

  • Li, Xinran

  • Wu, Jiajing

  • Huang, Luyao

  • Wang, Nan

  • Chen, Limin

  • Jiang, Mingxin

  • Chen, Zhe

  • Wei, Lin

  • Zhang, Hong

  • May 18, 2026

  • 0 min

Share

Objective:

To develop a machine learning model to identify patients at high risk of acute kidney injury (AKI) among hemodynamically stable sepsis patients.

Key Findings:
  • A total of 8,276 hemodynamically stable sepsis patients were included.
  • 3,061 patients (37%) experienced AKI.
  • Nine risk factors were identified for model development.
  • The XGBoost model demonstrated optimal performance in predicting AKI risk.
Interpretation:

Limitations:
Conclusion:

Original Source(s)

Machine Learning Model for Predicting the Risk of AKI in Early Hemodynamically Stable Sepsis Patients: A Study Based on the MIMIC IV Database

  • by He, Miao , Li, Xinran , Wu, Jiajing , Huang, Luyao , Wang, Nan , Chen, Limin , Jiang, Mingxin , Chen, Zhe , Wei, Lin , Zhang, Hong

  • May 18, 2026

Related Content

Early Changes in Creatinine Levels Predict Outcomes in Patients with Sepsis

Correlation of Shock-Lactate Index with 28-Day Mortality in Patients Experiencing Sepsis-Related AKI: An Analysis Using the MIMIC-IV Database

Serum HDAC3 as an Early Indicator for Predicting and Staging Acute Kidney Injury Associated with Sepsis: A Prospective Cohort Analysis