Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: Journal of Medical Internet Research

Date Submitted: Dec 16, 2024
Date Accepted: May 20, 2025

The final, peer-reviewed published version of this preprint can be found here:

Predicting In-Hospital Mortality in Intensive Care Unit Patients Using Causal SurvivalNet With Serum Chloride and Other Causal Factors: Cross-Country Study

Wang J, Li Q, Xie C, Li X, Wang H, Xu W, Lv R, Zhai X, Xu P, Li K, Song X

Predicting In-Hospital Mortality in Intensive Care Unit Patients Using Causal SurvivalNet With Serum Chloride and Other Causal Factors: Cross-Country Study

J Med Internet Res 2025;27:e70118

DOI: 10.2196/70118

PMID: 40706028

PMCID: 12332460

Predicting In-hospital Mortality in ICU Patients Using Causal Survival Net with Serum Chloride and Other Causal Factors: A Cross-Country Study

  • Jing Wang; 
  • Qixiu Li; 
  • Can Xie; 
  • Xiaofei Li; 
  • Huikao Wang; 
  • Wei Xu; 
  • Ruyan Lv; 
  • Xiaobing Zhai; 
  • Ping Xu; 
  • Kefeng Li; 
  • Xicheng Song

ABSTRACT

Background:

Incorporating initial serum chloride levels as a prognostic indicator in the intensive care environment stands to refine risk stratification and tailor treatment strategies, leading to more efficient use of clinical resources and improved patient prognoses.

Objective:

Quantitative analysis of the relationship between serum chloride levels at ICU admission and in-hospital mortality, and the establishment of a personalized survival curve prediction deep learning model.

Methods:

A study of 189,462 ICU patients from four cohorts was conducted. We collected demographics, underlying diseases, ICU complications, electrolyte levels, biochemical parameters, and vital signs at ICU admission, along with length of stay and survival outcomes. Causal graph analysis pinpointed variables linked to mortality. Nonlinear associations between chloride levels and mortality were evaluated using restricted cubic splines (RCS) and Cox Proportional Hazards (CPH) models, validated with Kaplan-Meier curves. A deep learning model was created for individualized survival predictions.

Results:

Causal inference revealed a significant association between admission serum chloride levels and 28-day mortality. RCS identified thresholds at 103 mEq/L and 115 mEq/L, categorizing patients into three groups. CPH models revealed higher death risks for patients outside this range, with HRs of 1.36 (95% CI 1.29-1.43) and 1.27 (95% CI 1.14-1.41). Cross-cohort validation confirmed these critical ranges. The Causal SurvivalNet accurately predicted individual survival curves using admission chloride levels and other factors, achieving Brier scores of 0.09, 0.12, and 0.15.

Conclusions:

Utilizing initial serum chloride levels enhances prognostic accuracy and facilitates tailored treatment plans for ICU patients in critical care settings. Clinical Trial: This study was conducted in accordance with the ethical principles outlined in the Declaration of Helsinki and was approved by the Institutional Review Board (IRB) or Ethics Committee of Yantai Yuhuangding Hospital (File No: 2024-018).


 Citation

Please cite as:

Wang J, Li Q, Xie C, Li X, Wang H, Xu W, Lv R, Zhai X, Xu P, Li K, Song X

Predicting In-Hospital Mortality in Intensive Care Unit Patients Using Causal SurvivalNet With Serum Chloride and Other Causal Factors: Cross-Country Study

J Med Internet Res 2025;27:e70118

DOI: 10.2196/70118

PMID: 40706028

PMCID: 12332460

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.