Development and temporal validation of a nomogram for predicting ICU 28-day mortality in middle-aged and elderly sepsis patients: An eICU database study.

<h4>Background and objective</h4>Despite advances in intensive care, sepsis remains a leading cause of mortality in intensive care unit (ICU) patients, especially middle-aged and elderly individuals. Given the limitations of conventional scoring systems and the interpretability challenge...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiao She, Xiao Zhao, Haiyan Yang, Xiaoguang Cui
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2025-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0328701
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849418743569973248
author Xiao She
Xiao Zhao
Haiyan Yang
Xiaoguang Cui
author_facet Xiao She
Xiao Zhao
Haiyan Yang
Xiaoguang Cui
author_sort Xiao She
collection DOAJ
description <h4>Background and objective</h4>Despite advances in intensive care, sepsis remains a leading cause of mortality in intensive care unit (ICU) patients, especially middle-aged and elderly individuals. Given the limitations of conventional scoring systems and the interpretability challenges of machine learning models, this study aims to develop and temporally validate a nomogram for predicting 28-day ICU mortality in middle-aged and elderly sepsis patients via the eICU database (2014--2015), providing a clinically practical prediction tool.<h4>Methods</h4>This retrospective study included 13,717 sepsis patients aged ≥45 years. The cohort was temporally divided into training (n = 6,397, 2014) and validation (n = 7,320, 2015) sets. Variable selection was performed via random forest importance ranking and LASSO regression. A nomogram was developed on the basis of multivariable logistic regression analysis.<h4>Results</h4>The 28-day ICU mortality rates were 9.08% and 9.49% in the training and validation cohorts, respectively. The final nomogram incorporated 11 independent predictors: red cell distribution width (RDW), SOFA score, lactate, pH, 24-hour urine output, platelet count, total protein, temperature, heart rate, GCS score, and white blood cell (WBC) count. The model showed good discrimination in both the training (AUC: 0.805) and validation (AUC: 0.756) cohorts. The calibration curves demonstrated good agreement between the predicted and observed probabilities.<h4>Conclusions</h4>We developed and temporally validated a nomogram with good predictive performance for 28-day ICU mortality in middle-aged and elderly sepsis patients, providing a practical tool for risk stratification and clinical decision-making.
format Article
id doaj-art-10a48cc2cc964085b82df4905d2c6336
institution Kabale University
issn 1932-6203
language English
publishDate 2025-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-10a48cc2cc964085b82df4905d2c63362025-08-20T03:32:22ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01207e032870110.1371/journal.pone.0328701Development and temporal validation of a nomogram for predicting ICU 28-day mortality in middle-aged and elderly sepsis patients: An eICU database study.Xiao SheXiao ZhaoHaiyan YangXiaoguang Cui<h4>Background and objective</h4>Despite advances in intensive care, sepsis remains a leading cause of mortality in intensive care unit (ICU) patients, especially middle-aged and elderly individuals. Given the limitations of conventional scoring systems and the interpretability challenges of machine learning models, this study aims to develop and temporally validate a nomogram for predicting 28-day ICU mortality in middle-aged and elderly sepsis patients via the eICU database (2014--2015), providing a clinically practical prediction tool.<h4>Methods</h4>This retrospective study included 13,717 sepsis patients aged ≥45 years. The cohort was temporally divided into training (n = 6,397, 2014) and validation (n = 7,320, 2015) sets. Variable selection was performed via random forest importance ranking and LASSO regression. A nomogram was developed on the basis of multivariable logistic regression analysis.<h4>Results</h4>The 28-day ICU mortality rates were 9.08% and 9.49% in the training and validation cohorts, respectively. The final nomogram incorporated 11 independent predictors: red cell distribution width (RDW), SOFA score, lactate, pH, 24-hour urine output, platelet count, total protein, temperature, heart rate, GCS score, and white blood cell (WBC) count. The model showed good discrimination in both the training (AUC: 0.805) and validation (AUC: 0.756) cohorts. The calibration curves demonstrated good agreement between the predicted and observed probabilities.<h4>Conclusions</h4>We developed and temporally validated a nomogram with good predictive performance for 28-day ICU mortality in middle-aged and elderly sepsis patients, providing a practical tool for risk stratification and clinical decision-making.https://doi.org/10.1371/journal.pone.0328701
spellingShingle Xiao She
Xiao Zhao
Haiyan Yang
Xiaoguang Cui
Development and temporal validation of a nomogram for predicting ICU 28-day mortality in middle-aged and elderly sepsis patients: An eICU database study.
PLoS ONE
title Development and temporal validation of a nomogram for predicting ICU 28-day mortality in middle-aged and elderly sepsis patients: An eICU database study.
title_full Development and temporal validation of a nomogram for predicting ICU 28-day mortality in middle-aged and elderly sepsis patients: An eICU database study.
title_fullStr Development and temporal validation of a nomogram for predicting ICU 28-day mortality in middle-aged and elderly sepsis patients: An eICU database study.
title_full_unstemmed Development and temporal validation of a nomogram for predicting ICU 28-day mortality in middle-aged and elderly sepsis patients: An eICU database study.
title_short Development and temporal validation of a nomogram for predicting ICU 28-day mortality in middle-aged and elderly sepsis patients: An eICU database study.
title_sort development and temporal validation of a nomogram for predicting icu 28 day mortality in middle aged and elderly sepsis patients an eicu database study
url https://doi.org/10.1371/journal.pone.0328701
work_keys_str_mv AT xiaoshe developmentandtemporalvalidationofanomogramforpredictingicu28daymortalityinmiddleagedandelderlysepsispatientsaneicudatabasestudy
AT xiaozhao developmentandtemporalvalidationofanomogramforpredictingicu28daymortalityinmiddleagedandelderlysepsispatientsaneicudatabasestudy
AT haiyanyang developmentandtemporalvalidationofanomogramforpredictingicu28daymortalityinmiddleagedandelderlysepsispatientsaneicudatabasestudy
AT xiaoguangcui developmentandtemporalvalidationofanomogramforpredictingicu28daymortalityinmiddleagedandelderlysepsispatientsaneicudatabasestudy