Association between clinical characteristics within 6 h of ICU admission and 30-day mortality risk in immunocompromised sepsis patients: development and validation of a machine learning model based on the MIMIC-IV database - Takeaways - MDSpire

Association between clinical characteristics within 6 h of ICU admission and 30-day mortality risk in immunocompromised sepsis patients: development and validation of a machine learning model based on the MIMIC-IV database

  • By

  • Zhipeng Cheng

  • Xiuqing Ma

  • Weiying Duan

  • Zeyu Mou

  • Zhixin Liang

  • July 13, 2026

Share

  • 1

    A machine learning model was developed to predict 30-day mortality in immunocompromised sepsis patients using data from the MIMIC-IV and eICU databases.

  • 2

    The study included 2,494 immunosuppressed sepsis patients, with a 30-day mortality rate of 33.4%.

  • 3

    The final prediction model utilized 10 clinical indicators, including age, SOFA score, and prothrombin time, collected within 6 hours of ICU admission.

  • 4

    The Support Vector Machine (SVM) model showed the best predictive performance with an AUC of 0.794 in the validation set.

  • 5

    External validation on the eICU dataset confirmed the model's stability and generalizability, achieving an AUC of 0.847.

Original Source(s)

Association between clinical characteristics within 6 h of ICU admission and 30-day mortality risk in immunocompromised sepsis patients: development and validation of a machine learning model based on the MIMIC-IV database

  • by Zhipeng Cheng, Xiuqing Ma, Weiying Duan, Zeyu Mou, Zhixin Liang

  • July 13, 2026

Related Content

Predicting SIRS after PCNL using machine learning: the joint impact of sarcopenia and staghorn stones

Interpretable gradient boosting machine model for predicting in-hospital mortality in sepsis-induced myocardial injury: a multicenter development, validation, and web-based clinical implementation

Development and external validation of a 90-day mortality prediction model for comatose sepsis patients: impact of cerebrovascular disease and dementia