What question did this study set out to answer?

To develop and validate a prediction model for estimating in-hospital mortality in ICU patients with cirrhosis and sepsis.

February 12, 2026SHILAP Revista de lepidopterologíaOpen Access

Development and validation of a prediction model for in-hospital mortality in intensive care unit patients with cirrhosis and sepsis: a multicentre retrospective cohort study

View Full Paper

Ask AI

Bookmark

Authors

ZXZhikun Xu QYQinhua Yang DPDongting Peng

Discussion

Member takes

Overview

A multicentre retrospective cohort study develops and validates a prediction model for in-hospital mortality in ICU patients, highlighting its clinical utility.

Key Points

To develop and validate a prediction model for estimating in-hospital mortality in ICU patients with cirrhosis and sepsis.
Data sourced from MIMIC-IV, eICU-CRD, and SZPH-ICU databases.
Training cohort divided chronologically, with separate temporal validation.
Used LASSO regression for variable selection and logistic regression for model building.
Model performance evaluated using AUROC, Brier score, and calibration plots.
Developed a web-based calculator for clinical use.
In-hospital mortality rates were 24.0% in the training cohort and 35.9% in the temporal validation cohort.
External validation showed 25.9% mortality in eICU-CRD and 38.2% in SZPH-ICU.
The final model included 13 predictors related to clinical status.
Achieved AUROC values of 0.822 and 0.810 for training and temporal validation cohorts respectively.
Outperformed existing prognostic scores for predicting mortality.

Cite This Study

Xu et al. (2026) studied this question.

synapsesocial.com/papers/698d6d695be6419ac0d524d2 https://doi.org/10.3389/fmed.2026.1759988

View Full Paper

Ask AI

Bookmark

February 12, 2026SHILAP Revista de lepidopterologíaOpen Access

Development and validation of a prediction model for in-hospital mortality in intensive care unit patients with cirrhosis and sepsis: a multicentre retrospective cohort study

View Full Paper

Ask AI

Bookmark

Authors

ZXZhikun Xu QYQinhua Yang DPDongting Peng

Discussion

Member takes

Overview

A multicentre retrospective cohort study develops and validates a prediction model for in-hospital mortality in ICU patients, highlighting its clinical utility.

Key Points

To develop and validate a prediction model for estimating in-hospital mortality in ICU patients with cirrhosis and sepsis.
Data sourced from MIMIC-IV, eICU-CRD, and SZPH-ICU databases.
Training cohort divided chronologically, with separate temporal validation.
Used LASSO regression for variable selection and logistic regression for model building.
Model performance evaluated using AUROC, Brier score, and calibration plots.
Developed a web-based calculator for clinical use.
In-hospital mortality rates were 24.0% in the training cohort and 35.9% in the temporal validation cohort.
External validation showed 25.9% mortality in eICU-CRD and 38.2% in SZPH-ICU.
The final model included 13 predictors related to clinical status.
Achieved AUROC values of 0.822 and 0.810 for training and temporal validation cohorts respectively.
Outperformed existing prognostic scores for predicting mortality.

Cite This Study

Xu et al. (2026) studied this question.

synapsesocial.com/papers/698d6d695be6419ac0d524d2 https://doi.org/10.3389/fmed.2026.1759988

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark