Sodium: sign, signifier, or signified, of sepsis?

O’Sullivan, Mai; McCarthy, Kevin F.

doi:10.1016/j.ejim.2020.12.002

Cited by 2 publications

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[21,22] In contrast, the study by O'Sullivan, et al only revealed a relationship between hyponatremia but not hypernatremia and mortality in sepsis patients. [23] Interestingly, despite previous studies showing opposite trends, they were both included in our findings because previous studies were either confined to small sample sizes or had algorithmic restrictions, and hence did not detect nonlinear correlations. Because sodium is an important inorganic salt component of the body, extreme levels of distribution (too low or too high) can cause alterations in the body's physiological balance, therefore the U-shaped association we discovered makes sense.…”

Section: Discussionmentioning

confidence: 99%

Association between serum sodium and 28‐day mortality in sepsis patients: A secondary data analysis from three large critical illness cohorts

Li,

Yuan

et al. 2023

Ther Apher Dial

View full text Add to dashboard Cite

ObjectiveThe present study was designed to explore the association between serum sodium and mortality in patients with sepsis by using a large sample, multicenter MIMIC‐IV database.MethodsWe extracted the data of 34 925 sepsis patients from the retrospective cohort mimicIV database. After adjusting the confounders, we explored the independent effects of serum sodium on 28‐day mortality.ResultsA nonlinear relationship existed between serum sodium and 28‐day mortality, of which a negative association was found between serum sodium and 28‐day mortality (odds ratio: 0.95, 95% CI: 0.94, 0.96, p = 0.0001) when serum sodium was in 102 mmol/L to 138 mmol/L, but a positive correlation appeared when sodium climbed to the range of 140–179 mmol/L (odds ratio: 1.04, 95% CI: 1.03–1.06, p = 0.0001).ConclusionsBoth lower and higher serum sodium levels are associated with an increased risk of death in sepsis patients.

show abstract

Section: Discussionmentioning

confidence: 99%

Association between serum sodium and 28‐day mortality in sepsis patients: A secondary data analysis from three large critical illness cohorts

Li,

Yuan

et al. 2023

Ther Apher Dial

View full text Add to dashboard Cite

show abstract

Machine learning-based prediction of in-hospital mortality for critically ill patients with sepsis-associated acute kidney injury

Gao,

Nong,

Luo

et al. 2024

Renal Failure

View full text Add to dashboard Cite

Objectives This study aims to develop and validate a prediction model in-hospital mortality in critically ill patients with sepsis-associated acute kidney injury (SA-AKI) based on machine learning algorithms. Methods Patients who met the criteria for inclusion were identified in the Medical Information Mart for Intensive Care-IV (MIMIC-IV) database and divided according to the validation ( n = 2440) and development ( n = 9756, 80%) queues. Ensemble stepwise feature selection method was used to screen for effective features. The prediction models of short-term mortality were developed by seven machine learning algorithms. Ten-fold cross-validation was used to verify the performance of the algorithm in the development queue. The area under the receiver operating characteristic curve (ROC-AUC) was used to evaluate the differentiation accuracy and performance of the prediction model in the validation queue. The best-performing model was interpreted by Shapley additive explanations (SHAP). Results A total of 12,196 patients were enrolled in this study. Eleven variables were finally chosen to develop the prediction model. The AUC of the random forest (RF) model was the highest value both in the Ten-fold cross-validation and evaluation (AUC: 0.798, 95% CI: 0.774–0.821). According to the SHAP plots, old age, low Glasgow Coma Scale (GCS) score, high AKI stage, reduced urine output, high Simplified Acute Physiology Score (SAPS II), high respiratory rate, low temperature, low absolute lymphocyte count, high creatinine level, dysnatremia, and low body mass index (BMI) increased the risk of poor prognosis. Conclusions The RF model developed in this study is a good predictor of in-hospital mortality for patients with SA-AKI in the intensive care unit (ICU), which may have potential applications in mortality prediction.

show abstract

Sodium: sign, signifier, or signified, of sepsis?

Cited by 2 publications

References 9 publications

Association between serum sodium and 28‐day mortality in sepsis patients: A secondary data analysis from three large critical illness cohorts

Association between serum sodium and 28‐day mortality in sepsis patients: A secondary data analysis from three large critical illness cohorts

Machine learning-based prediction of in-hospital mortality for critically ill patients with sepsis-associated acute kidney injury

Contact Info

Product

Resources

About