EUVIMEDEUVIMED entdecken
Open Access

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

Vorhersage der Krankenhaussterblichkeit bei ICU-Patient:innen mit Causal SurvivalNet unter Einbezug von Serumchlorid und weiteren kausalen Faktoren: länderübergreifende Studie

Jing Wang iD, Qixiu Li iD, Can Xie iD, Xiaofei Li iD, Huikao Wang iD, Wei Xu iD, Ruyan Lv iD, Xiaobing Zhai iD, Ping Xu iD, Kefeng Li iD, Xi-Cheng Song iD

Journal of Medical Internet Research · 24.07.2025 · 27 · e70118

DOI: 10.2196/70118 ↗

Auf einen Blick

Bei 189.462 ICU-Patient:innen war das Serumchlorid bei Aufnahme mit der 28-Tage-Mortalität assoziiert. Ein Modell sagte individuelle Überlebenskurven mit guten Brier-Scores voraus.

Fragestellung

Welcher Zusammenhang besteht zwischen Serumchlorid bei ICU-Aufnahme und Krankenhaussterblichkeit, und lässt sich damit ein personalisiertes Überlebensmodell erstellen?

Methode

Länderübergreifende, multikohortige Studie mit 189.462 ICU-Patient:innen aus 4 Kohorten. Kausale Graphanalyse, restricted cubic splines, Cox-Modelle; Validierung mit Cox-Frailty, Kaplan-Meier, Sensitivitätsanalysen.

Ergebnisse

Das Risiko war außerhalb von 103-115 mEq/L höher. HR für ≤103 mEq/L: 1,36 (95 %-KI 1,29-1,43); für >115 mEq/L: 1,27 (95 %-KI 1,14-1,41). Causal SurvivalNet erreichte Brier-Scores von 0,09, 0,12 und 0,15.

Schlussfolgerung der Autor:innen

Die Autoren schlussfolgern, dass initiale Serumchloridwerte die Prognosegenauigkeit verbessern und eine individualisierte Behandlung von ICU-Patient:innen unterstützen können.

Kernaussagen

  • Serumchlorid bei Aufnahme war mit der 28-Tage-Mortalität assoziiert
  • Erhöhtes Risiko außerhalb des Bereichs 103-115 mEq/L
  • Causal SurvivalNet sagte Überlebenskurven individuell voraus

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Medical Internet Research, online erschienen am 24.07.2025. Verfasst von Jing Wang und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Critical Care Medicine, Yantai Yuhuangding Hospital, Qingdao University, Yantai, China. Hauptthemen laut MEDLINE: Hospital Mortality, Intensive Care Units, Chlorides. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

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

Objective

Quantitative analysis of the relationship between serum chloride levels at intensive care unit (ICU) admission and in-hospital mortality, and the establishment of a personalized survival curve prediction deep learning model to enhance risk stratification and clinical decision-making.

Methods

A large-scale, cross-country, multicohort study of 189,462 ICU patients from four cohorts was conducted: 70,370 from Medical Information Mart for Intensive Care IV (MIMIC-IV), 112,457 from eICU Collaborative Research Database (eICU-CRD; 2 US cohorts), 4653 from Yantai Yuhuangding Hospital, and 1982 patients from Zigong Fourth People’s Hospital (2 Chinese cohorts). We collected demographics, underlying diseases, ICU complications, electrolyte levels, biochemical parameters, and vital signs at ICU admission, along with length of stay and in-hospital survival outcomes. Causal graph analysis pinpointed clinical variables linked to mortality. Nonlinear associations between chloride levels and mortality were evaluated using restricted cubic splines and Cox proportional hazards models, validated with the Cox frailty model, Kaplan-Meier curves, and sensitivity analyses. 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. The median serum chloride level at ICU admission was 104 (IQR 100-108) mEq/L. In analyzing all 42 variables, restricted cubic splines identified thresholds at 103 mEq/L and 115 mEq/L, categorizing patients into three groups: ≤103 mEq/L, 103-115 mEq/L, and >115 mEq/L. Cox proportional hazards models revealed higher death risks for patients outside this range, with hazard ratios (HRs) of 1.36 (95% CI 1.29-1.43) for ≤103 mEq/L and 1.27 (95% CI 1.14-1.41) for >115 mEq/L. Four cross-cohort validations confirmed these critical ranges. For the eICU-CRD dataset, the HRs for the key intervals are 1.30 (95% CI 1.24-1.36) and 0.97 (95% CI 0.89-1.06). In the Yantai Yuhuangding Hospital affiliated with Qingdao University (YHD-HOSP) dataset, the HRs for the key intervals are 1.23 (95% CI 1.09-1.38) and 1.58 (95% CI 1.27-1.96). In the Sichuan Zigong Fourth People’s Hospital (SCZG-HOSP) dataset, the HR for the key interval is 2.20 (95% CI 1.43-3.39). 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. Results from cohort analyses in both China and the United States consistently and closely correlate the critical range of chloride with the prognosis of ICU patients.

Conclusions

Using initial serum chloride levels enhances prognostic accuracy and facilitates tailored treatment plans for ICU patients in critical care settings.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Hospital MortalityIntensive Care UnitsChloridesHumansFemaleMaleMiddle AgedAgedPrognosisChinaCohort StudiesDeep Learning

Stichwörter der Autor:innen

Causal SurvivalNetICUdeep learningelectrolyte imbalanceintensive care unitprognosisthreshold

Substanzen

Chlorides

Autor:innen und Institutionen

  • Department of Critical Care Medicine, Yantai Yuhuangding Hospital, Qingdao University, Yantai, China.
  • Faculty of Applied Science, Macao Polytechnic University, Macao, Macao.
  • Emergency Department, Zigong Fourth People's Hospital, Zigong, China.
  • Department of Otolaryngology Head and Neck Surgery, Yantai Yuhuangding Hospital, Qingdao University, Yantai, China.

ORCID-Profile: Jing Wang, Qixiu Li, Can Xie, Xiaofei Li, Huikao Wang, Wei Xu, Ruyan Lv, Xiaobing Zhai, Ping Xu, Kefeng Li, Xi-Cheng Song

Zitieren

APA

Wang, J., Li, Q., Xie, C., Li, X., Wang, H., Xu, W., Lv, R., Zhai, X., Xu, P., Li, K., & Song, X. C. (2025). Predicting In-Hospital Mortality in Intensive Care Unit Patients Using Causal SurvivalNet With Serum Chloride and Other Causal Factors: Cross-Country Study. Journal of Medical Internet Research, 27, e70118. https://doi.org/10.2196/70118

Vancouver

Wang J, Li Q, Xie C, Li X, Wang H, Xu W, et al. Predicting In-Hospital Mortality in Intensive Care Unit Patients Using Causal SurvivalNet With Serum Chloride and Other Causal Factors: Cross-Country Study. Journal of Medical Internet Research. 2025;27:e70118. doi:10.2196/70118

BibTeX
@article{Wang2025,
  author = {Wang, Jing and Li, Qixiu and Xie, Can and Li, Xiaofei and Wang, Huikao and Xu, Wei and Lv, Ruyan and Zhai, Xiaobing and Xu, Ping and Li, Kefeng and Song, Xi-Cheng},
  title = {Predicting In-Hospital Mortality in Intensive Care Unit Patients Using Causal SurvivalNet With Serum Chloride and Other Causal Factors: Cross-Country Study},
  journal = {Journal of Medical Internet Research},
  year = {2025},
  volume = {27},
  pages = {e70118},
  doi = {10.2196/70118}
}
Kostenlos starten →