Association between the (neutrophil + monocyte)/albumin ratio and all-cause mortality in sepsis patients: a retrospective cohort study and predictive model establishment according to machine learning

Abstract

Introduction: Sepsis is a life-threatening condition characterized by widespread inflammatory response syndrome in the body resulting from infection. Previous studies have demonstrated that some inflammatory factors or nutritional elements contributed to deaths in patients diagnosed with sepsis. Nevertheless, the correlation between the (neutrophil + monocyte)/albumin (NMa) ratio and all-cause mortality of patients diagnosed with sepsis remains unclear. This study aims to investigate the association between the NMa ratio and all-cause mortality in sepsis patients and to develop a predictive model using machine learning techniques.

Methods: The clinical data were harvested from 13,851 patients with sepsis from the MIMIC-IV (3.1) database. We divided the subjects into four groups based on quartiles of the NMa ratio. The main endpoint was 30-day all-cause mortality, and the secondary endpoint was 90-day all-cause mortality. The relationship between the NMa ratio and adverse prognosis was investigated employing Cox proportional hazard regression, restricted cubic splines, and Kaplan‒Meier curves. Moreover, we employed Boruta algorithm to evaluate the predictive potential of the NMa ratio and established the prediction models utilizing machine learning algorithms.

Results: After adjusting for confounders, each unit increase in the NMa ratio was associated with a 1.8% and 1.6% higher risk of 30-day and 90-day all-cause mortality, respectively (P < 0.001), indicating a linear relationship, and when treated as a categorical variable, the Quartile 4 group demonstrated a significantly higher mortality risk. Boruta feature selection also displayed that the NMa ratio possessed a higher Z score, and the models established utilizing the Cox and Random Forest algorithm identified excellent predictive performance (area under the curve (AUC) = 0.72, AUC = 0.74, respectively).

Conclusion: The NMa ratio is strongly and linearly associated with 30-day and 90-day all-cause mortality, with higher levels significantly increasing mortality risk, even after adjusting for potential confounders. Predictive models using Cox regression and Random Forest algorithms showed strong performance, indicating that the NMa ratio could function as a predictor of negative prognosis in patients with sepsis.

Keywords: (neutrophil + monocyte)/albumin ratio; Boruta algorithm; Machine learning; Sepsis.

Fig. 1

Flow chart of study participants. ICU: Intensive Care Unit, NMa: (neutrophil + monocyte) to albumin

Fig. 2

Feature selection according to 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. NMa: (neutrophil + monocyte) to albumin, wbc: white blood cell count, rdw: red cell volume distribution width, LAC: lactate, bun: blood urea nitrogen, ptt: partial prothrombin time, sofa: Sequential Organ Failure Assessment, DM: diabetes, crrt: continuous renal replacement therapy

Fig. 3

Kaplan-Meier survival curves based on the quartiles of the NMa ratio. NMa: (neutrophil + monocyte) to albumin, Q1: Quartile 1, Q2: Quartile 2, Q3: Quartile 3, Q4: Quartile 4

Fig. 4

Restricted cubic spline (RCS) analysis of 30-day and 90-day all-cause mortality. Solid lines express hazard ratios, and dashed lines demonstrate 95% confidence intervals. The bar chart reveals the distribution of the NMa ratio in the population. NMa: (neutrophil + monocyte) to albumin

Fig. 5

Receiver operating characteristic (ROC) curves of the machine learning algorithms. Cox: Cox Proportional Hazards Survival Learner algorithm, Decision Tree: Rpart Survival Trees Survival Learner algorithm, Random Forest: Survival Random Forest SRC Learner, XGBoost: Extreme Gradient Boosting Survival Learner algorithm