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

  • 1

    The study developed a machine learning model to identify AKI risk in hemodynamically stable sepsis patients using the MIMIC IV Database.

  • 2

    A total of 8,276 hemodynamically stable sepsis patients were analyzed, with 3,061 (37%) experiencing acute kidney injury.

  • 3

    Nine risk factors were identified for model development through univariate analysis and LASSO regression.

  • 4

    Multiple models, including XGBoost, were constructed and evaluated for their predictive performance regarding AKI risk.

  • 5

    The XGBoost model demonstrated optimal performance and was validated externally for predicting AKI in early sepsis patients.

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

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

Early Changes in Creatinine Levels Predict Outcomes in Patients with Sepsis

Complement in acute kidney injury: a convergent pathogenic pathway in multifactorial renal damage