# Longitudinal SOFA score trajectories and risk stratification in ICU patients with Staphylococcus aureus bloodstream infection: insights from group-based trajectory modeling

## TL;DR

This study uses machine learning to identify patterns of organ failure in ICU patients with a severe blood infection, showing how these patterns predict survival outcomes.

## Contribution

The study introduces a data-driven approach combining trajectory modeling and interpretable machine learning for risk stratification in ICU patients with Staphylococcus aureus bloodstream infection.

## Key findings

- Three reproducible SOFA trajectory groups were identified: stable, moderately worsening, and severely deteriorating.
- Severely deteriorating patients had a 4.60-fold higher risk of in-hospital mortality compared to stable patients.
- An XGBoost model accurately predicted trajectory groups with an AUC of 0.96.

## Abstract

Staphylococcus aureus bloodstream infection (SA-BSI) is a life-threatening condition in ICU patients, often leading to progressive multi-organ dysfunction. Traditional static assessments may underestimate the dynamic nature of organ failure. We aimed to identify distinct organ dysfunction trajectories and evaluate their prognostic significance using a data-driven and interpretable machine learning approach.

ICU patients with SA-BSI from two independent cohorts admitted between 2008 and 2024 were retrospectively analyzed (MIMIC-IV, n=834; the Second Affiliated Hospital of Zhejiang University School of Medicine (SAHZU), n=151). Daily Sequential Organ Failure Assessment (SOFA) scores from Day -1 to +3 were used to derive trajectory subgroups via group-based trajectory modeling. Associations with in-hospital mortality were assessed using multivariable Cox regression and Kaplan-Meier analysis. An XGBoost model was developed to predict trajectory group membership based on baseline ICU admission variables, with interpretability assessed via SHAP values.

Three reproducible SOFA trajectory groups were identified in both cohorts, representing stable, moderately worsening, and severely deteriorating clinical courses. Compared with the stable group, patients in the severely deteriorating group had a markedly increased risk of in-hospital mortality (HR 4.60, 95% CI 3.49–6.07), with consistent effects observed across both cohorts. The XGBoost model demonstrated strong predictive performance for identifying severely deteriorating trajectories (AUC 0.96), and SHAP analysis revealed biologically coherent predictors underlying each trajectory.

Early ICU data can predict dynamic organ dysfunction trajectories in SA-BSI patients. Trajectory-based phenotyping, combined with interpretable machine learning, offers a clinically valuable framework for early risk stratification and individualized ICU management.