Association between the stress hyperglycemia ratio and 28-day all-cause mortality in critically ill patients with sepsis: a retrospective cohort study and predictive model establishment based on machine learning

Abstract

Background: Sepsis is a severe form of systemic inflammatory response syndrome that is caused by infection. Sepsis is characterized by a marked state of stress, which manifests as nonspecific physiological and metabolic changes in response to the disease. Previous studies have indicated that the stress hyperglycemia ratio (SHR) can serve as a reliable predictor of adverse outcomes in various cardiovascular and cerebrovascular diseases. However, there is limited research on the relationship between the SHR and adverse outcomes in patients with infectious diseases, particularly in critically ill patients with sepsis. Therefore, this study aimed to explore the association between the SHR and adverse outcomes in critically ill patients with sepsis.

Methods: Clinical data from 2312 critically ill patients with sepsis were extracted from the MIMIC-IV (2.2) database. Based on the quartiles of the SHR, the study population was divided into four groups. The primary outcome was 28-day all-cause mortality, and the secondary outcome was in-hospital mortality. The relationship between the SHR and adverse outcomes was explored using restricted cubic splines, Cox proportional hazard regression, and Kaplan‒Meier curves. The predictive ability of the SHR was assessed using the Boruta algorithm, and a prediction model was established using machine learning algorithms.

Results: Data from 2312 patients who were diagnosed with sepsis were analyzed. Restricted cubic splines demonstrated a "U-shaped" association between the SHR and survival rate, indicating that an increase in the SHR is related to an increased risk of adverse events. A higher SHR was significantly associated with an increased risk of 28-day mortality and in-hospital mortality in patients with sepsis (HR > 1, P < 0.05) compared to a lower SHR. Boruta feature selection showed that SHR had a higher Z score, and the model built using the rsf algorithm showed the best performance (AUC = 0.8322).

Conclusion: The SHR exhibited a U-shaped relationship with 28-day all-cause mortality and in-hospital mortality in critically ill patients with sepsis. A high SHR is significantly correlated with an increased risk of adverse events, thus indicating that is a potential predictor of adverse outcomes in patients with sepsis.

Keywords: Boruta algorithm; Critical illness; Machine learning; Sepsis; Stress hyperglycemia ratio.

Fig. 1

Selection of the study population from the MIMIC-IV database

Fig. 2

28-day KM survival curve. KM curves showing the survival rates at 28 days for each quartile. SHR: Quartile 1 (0.21–0.915), Quartile 2 (0.915–1.14), Quartile 3 (1.14–1.45), and Quartile 4 (1.45–7.41)

Fig. 3

RCS analysis of 28-day all-cause mortality. Curves represent estimated adjusted hazard ratios, and shaded ribbons represent 95% confidence intervals. The vertical dotted line represents the lowest point of the curve (SHR = 0.85), which represents the lowest hazard ratio. The horizontal dashed line represents a hazard ratio of 1.0. HR hazard ratio, CI confidence interval

Fig. 4

RCS results for in-hospital mortality. Curves represent estimated adjusted hazard ratios, and shaded ribbons represent 95% confidence intervals. The vertical dotted line represents the lowest point of the curve, which represents the lowest hazard ratio. The horizontal dashed line represents a hazard ratio of 1.0. HR hazard ratio; CI, confidence interval

Fig. 5

Subgroup forest plot for 28-day all-cause mortality. Adjusted for age, weight, sex, heart rate, respiratory rate, systolic blood pressure, SOFA scores, and use of steroids (glucocorticoids). SHR: Quartile 1 (0.21–0.915), Quartile 2 (0.915–1.14), Quartile 3 (1.14–1.45), and Quartile 4 (1.45–7.41). Diabetes I type 1 diabetes, Diabetes II type 2 diabetes, HR hazard ratio, CI confidence interval

Fig. 6

Feature selection based on the Boruta algorithm. The horizontal axis is the name of each variable, and the vertical axis is the Z value of each variable. The box plot shows the Z value of each variable during model calculation. The green boxes represent important variables, and the red boxes represent unimportant variables

Fig. 7

ROC curves of the machine learning algorithms. coxph Cox proportional hazards survival learner, dt Rpart Survival Trees Survival Learner, deepsurv Survival DeepSurv Learner, rsf Survival Random Forest SRC Learner, xgboost extreme gradient boosting survival learner, T days, AUC area under the curve

Fig. 8

Performance of the SHR and laboratory data. WBC white blood cell count, RBC red blood cell count, INR prothrombin time international normalized ratio, AST aspartate aminotransferase, HbA1c glycosylated hemoglobin, SHR stress hyperglycemia ratio, AUC area under the curve