A machine learning model for 90-day mortality prediction in hepatitis B virus-related acute-on-chronic liver failure: the pivotal role of CALLY index - Takeaways - MDSpire

A machine learning model for 90-day mortality prediction in hepatitis B virus-related acute-on-chronic liver failure: the pivotal role of CALLY index

  • By

  • Yijun Zhang

  • Chunyan Li

  • Shaohui Su

  • Jilin Huang

  • Siyu Fu

  • Yong Zhang

  • Shanhong Tang

  • July 3, 2026

  • 0 min

Share

  • 1

    The study developed a machine learning framework to predict 90-day mortality in patients with hepatitis B virus-related acute-on-chronic liver failure.

  • 2

    A total of 471 patients were included, with data split into training and validation sets to evaluate the predictive models.

  • 3

    The LightGBM model demonstrated the best performance, achieving AUCs of 0.940, 0.825, and 0.804 in training, internal, and external validation sets, respectively.

  • 4

    SHAP analysis identified the international normalized ratio as the strongest predictor of mortality, followed by the CALLY index and other clinical factors.

  • 5

    The CALLY-based model significantly improved risk stratification compared to the MELD score, facilitating earlier intervention for high-risk patients.

Original Source(s)

A machine learning model for 90-day mortality prediction in hepatitis B virus-related acute-on-chronic liver failure: the pivotal role of CALLY index

  • by Yijun Zhang, Chunyan Li, Shaohui Su, Jilin Huang, Siyu Fu, Yong Zhang, Shanhong Tang

  • July 3, 2026

Related Content

Double gallbladder malformation with duodenal ulcer stricture leading to common bile duct dilation: a case report

Editorial: National Colorectal Cancer Awareness Month 2025: Current Progress and Future Prospects on Colorectal Cancer Prevention, Diagnosis and Treatment

ESD-VesNet: uncertainty-aware vessel segmentation network for endoscopic submucosal dissection with hard negative mining