What type of study is this?

This is a Retrospective analysis study (also classified as: Machine Learning).

September 10, 2025

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

Key Points

Lactate-to-albumin ratio significantly improved prediction of mortality risk in septic patients.
The optimal machine learning model achieved an AUC of 0.71 for predicting 28-day mortality.
SHAP analysis confirmed that lactate-to-albumin ratio was a top predictive feature across all models.
Integrating lactate and albumin enhances risk assessment, emphasizing early intervention in sepsis.

Abstract

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 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）.

Bookmark

Cite This Study

Wang et al. (Mon,) studied this question.

synapsesocial.com/papers/68c189d29b7b07f3a06131f9 https://doi.org/https://doi.org/10.2196/preprints.82230

Bookmark