Machine Learning-Augmented Traditional Analysis: Lactate versus Lactate-to-Albumin Ratio in Predicting Mortality Risk among Septic Patients — A Large-scale Retrospective Study (Preprint)

BACKGROUND Effective risk stratification in sepsis remains a clinical challenge. While lactate is a cornerstone biomarker, its predictive limitations are well-known. The lactate-to-albumin ratio (LAR) has emerged as a promising alternative, but its superiority, particularly in patients without severe hyperlactatemia, has not been rigorously validated in a large cohort using advanced, transparent methodologies. OBJECTIVE To determine whether the lactate-to-albumin ratio (LAR) provides superior and more robust prediction of 28-day mortality than lactate alone in adult sepsis patients, through comprehensive analysis using threshold effects, restricted cubic splines, and interpretable machine learning models in a large multicenter cohort. METHODS We conducted a retrospective analysis of 3637 adult sepsis patients from the multicenter eICU database. The primary outcome was 28-day mortality. We employed a dual approach: 1. Traditional statistical analyses, including threshold and restricted cubic spline modeling, to compare the predictive behavior of lactate and LAR. 2. Development of nine machine learning models to assess their predictive performance. We used SHapley Additive exPlanations (SHAP) to provide full model interpretability and to quantify the precise predictive contribution of each biomarker. RESULTS LAR consistently demonstrated a stronger and more stable association with mortality than lactate, especially in patients with lactate levels <4 mmol/L. In machine learning analyses, the top-performing Extreme Gradient Boosting (XGBoost) model achieved an AUC of 0.71 for 28-day in-hospital mortality. Critically, SHAP analysis revealed that LAR was consistently ranked as one of the top three most important predictive features across all models, with a contribution quantitatively greater than that of lactate alone. CONCLUSIONS The LAR is a superior and more robust biomarker than lactate for sepsis mortality prediction. By integrating a measure of acute metabolic distress (lactate) with a marker of systemic inflammation and capillary leak (albumin), LAR provides a more comprehensive risk assessment, particularly in the crucial early stages of sepsis. Interpretable machine learning models powered by LAR offer a promising pathway toward more precise and reliable clinical decision support. CLINICALTRIAL .Database access complied with the PhysioNet review board's data use agreement and HIPAA Safe Harbor provisions. This study received an exemption from the Massachusetts Institute of Technology Institutional Review Board, and the researcher completed the required data access training certification（Xu Yi, Certificate No.66014966）.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.