Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
April 6, 2025Nursing in Critical CareOpen Access

Development and validation of a prediction model for in‐hospital mortality in patients with sepsis

View Full Paper
Ask AI
Bookmark
Share

Authors

WSWen ShiFujian Medical UniversityMXMengqi XieDuke UniversityEMEnqiang MaoShanghai Jiao Tong University

Discussion

Loading...

Member takes

Overview

Retrospective cohort study reveals high accuracy of an 11-variable model for predicting mortality in ICU sepsis patients, highlighting valuable clinical risk stratification.

Key Points

  • To develop and validate a multivariate prognostic nomogram predicting 4-, 6-, and 8-week in-hospital mortality risks among intensive care unit patients with sepsis.
  • Analyzed a retrospective cohort of 2,389 sepsis patients, randomly splitting them 7:3 into a training set (n = 1,673) and a validation set (n = 716).
  • Selected predictive variables using LASSO regression and constructed a nomogram via a multivariate Cox proportional hazards model evaluated for discrimination and calibration.
  • Identified 11 independent prognostic factors from 35 initial variables, with minimum APACHE II score having the largest impact, followed by duration of mechanical ventilation, vasopressor use, SOFA scores, infection source, bacterial type, and malignancy.
  • Achieved 4-, 6-, and 8-week mortality AUROCs of 0.882 (95% CI, 0.855–0.909), 0.836 (95% CI, 0.798–0.874), and 0.843 (95% CI, 0.800–0.887) in the training set.
  • Demonstrated validation set AUROCs of 0.851 (95% CI, 0.804–0.899) at 4 weeks, 0.820 (95% CI, 0.761–0.878) at 6 weeks, and 0.794 (95% CI, 0.720–0.867) at 8 weeks.

Cite This Study

Shi et al. (2025) studied this question.

synapsesocial.com/papers/6a0edd7baa1655e5fb22e9eehttps://doi.org/10.1111/nicc.70015
View Full Paper
Ask AI
Bookmark
Share

Also Consider

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

  1. 1Development and validation of a prediction model for in-hospital mortality in intensive care unit patients with cirrhosis and sepsis: a multicentre retrospective cohort study2026 · 1 citations
  2. 2Prediction of 28-day mortality in patients with sepsis based on a predictive model: A retrospective cohort study2025 · 2 citations
  3. 3Development of an interpretable machine learning model for predicting in-hospital mortality in ICU patients with sepsis: a retrospective cohort study2026
  4. 4Development and Validation of a Nomogram for Mortality Prediction in Septic Patients with Prolonged or Chronic Critical Illness2026
  5. 5Development and internal validation of an ICU mortality prediction model for patients with concurrent sepsis and heart failure: a retrospective cohort study based on eICU-CRD2026