Unsupervised Machine Learning in Identification of Septic Shock Phenotypes and Their In-Hospital Outcomes: A Multicenter Cohort Study.

Background

Septic shock is a heterogeneous syndrome with diverse clinical presentations and pathophysiology, yet current management guidelines largely treat it as a homogenous entity. Early risk stratification relies on lactate and different predictive scoring systems, which may not capture the underlying heterogeneity in host responses. Aim: To identify discrete subphenotypes of septic shock using admission demographics and laboratory parameters, and to evaluate their relationship with in-hospital outcomes.

Methods

We conducted a retrospective multicenter cohort study of 10,462 adult patients with ICD-10-defined septic shock admitted to intensive care units between 2014 and 2015. We used Two-Step Cluster Analysis using log-likelihood distance and the Bayesian Information Criterion to identify two distinct phenotypes. We compared clusters on baseline characteristics, in-hospital outcomes including mortality, days on mechanical ventilation, vasopressor use, acute kidney injury (AKI), AKI requiring renal replacement therapy (RRT), and ICU and hospital lengths of stay.

Results

We identified two clusters (Cluster 1, n = 5355 and Cluster 2, n = 5107) in our study. Cluster 1 showed greater biochemical severity at presentation, including higher median lactate (2.40 vs. 2.20 mmol L-1; p < 0.001), serum creatinine (1.39 vs. 1.20 mg dL-1; p < 0.001), blood urea nitrogen (28 vs. 25 mg dL-1; p < 0.001), and neutrophil-to-lymphocyte ratio (11.12 vs. 10.38; p < 0.001), and a higher mean SOFA score (7.05 ± 3.85 vs. 6.76 ± 3.87; p < 0.001). Despite this, Cluster 1 required mechanical ventilation more frequently (46.1% vs. 42.2%; p < 0.001) and had a higher incidence of AKI (58.1% vs. 55.6%; p = 0.009), including more stage 3 AKI (17.2% vs. 15.2%; p < 0.001) and dialysis (6.6% vs. 5.2%; p = 0.005), yet experienced similar in-hospital mortality (15.4% vs. 15.8%; p = 0.615) and comparable ICU (2.18 vs. 2.26 days; p = 0.254) and hospital lengths of stay (6.63 vs. 6.80 days; p = 0.251).

Conclusions

Two septic shock phenotypes were identified, one with marked early organ dysfunction (Cluster 1) and another with milder initial derangements (Cluster 2), yet both showed convergent short-term mortality and lengths of stay despite divergent support needs. These results challenge reliance on single-parameter severity markers and underscore the need for phenotype-guided risk stratification and personalized management strategies in septic shock.