Clinical and biological clusters of sepsis patients using hierarchical clustering

Abstract

Background: Heterogeneity in sepsis expression is multidimensional, including highly disparate data such as the underlying disorders, infection source, causative micro-organismsand organ failures. The aim of the study is to identify clusters of patients based on clinical and biological characteristic available at patients' admission.

Methods: All patients included in a national prospective multicenter ICU cohort OUTCOMEREA and admitted for sepsis or septic shock (Sepsis 3.0 definition) were retrospectively analyzed. A hierarchical clustering was performed in a training set of patients to build clusters based on a comprehensive set of clinical and biological characteristics available at ICU admission. Clusters were described, and the 28-day, 90-day, and one-year mortality were compared with log-rank rates. Risks of mortality were also compared after adjustment on SOFA score and year of ICU admission.

Results: Of the 6,046 patients with sepsis in the cohort, 4,050 (67%) were randomly allocated to the training set. Six distinct clusters were identified: young patients without any comorbidities, admitted in ICU for community-acquired pneumonia (n = 1,603 (40%)); young patients without any comorbidities, admitted in ICU for meningitis or encephalitis (n = 149 (4%)); elderly patients with COPD, admitted in ICU for bronchial infection with few organ failures (n = 243 (6%)); elderly patients, with several comorbidities and organ failures (n = 1,094 (27%)); patients admitted after surgery, with a nosocomial infection (n = 623 (15%)); young patients with immunosuppressive conditions (e.g., AIDS, chronic steroid therapy or hematological malignancy) (n = 338 (8%)). Clusters differed significantly in early or late mortality (p < .001), even after adjustment on severity of organ dysfunctions (SOFA) and year of ICU admission.

Conclusions: Clinical and biological features commonly available at ICU admission of patients with sepsis or septic shock enabled to set up six clusters of patients, with very distinct outcomes. Considering these clusters may improve the care management and the homogeneity of patients in future studies.

Fig 1. Schematic of study.

Definition of abbreviations: MCA = multiple correspondence analysis; HC = hierarchical clustering Sensitivity analyses: Cluster analysis in the training set after excluding COPD exacerbation and cluster analysis in the training set after excluding the data before 2008.

Fig 2. Mortality estimated by Kaplan-Meier according to the cluster assignment with log rank tests (performed in training set).

Definition of abbreviations: Each curve was compared one by one using a log rank test; Results of these tests are presented in a double entry matrix; each cluster can be identified by its color; Analysis was performed including all patients in sepsis or septic shock. Cluster 1 = young patients without any comorbidities, admitted in ICU for community-acquired pneumonia; Cluster 2 = young patients without any comorbidities, admitted in ICU for meningitis or encephalitis; Cluster 3 = elderly patients with COPD, admitted in ICU for bronchial infection with few organ failures; Cluster 4 = elderly patients with several comorbidities and organ failures; Cluster 5 = patients admitted after surgery with a nosocomial infection; Cluster 6 = young patients with immunosuppressive disease or therapy, such as AIDS, chronic steroid therapy or hematological malignancy.

Fig 3. Description of the clusters and their risks of early, intermediate and late mortality, with and without adjustment (performed in training set).

Definition of abbreviations: HR: Hazard ratio; The analysis was performed after exclusion of patients without septic shock. A Cox model was used to determine the hazard ratio; Data are reported as HR ± 95% confidence intervals, presented from lowest to highest;presented from lowest to highest; Cluster 3 was used as reference; Adjusted mortality were adjusted using SOFA score at admission and year of ICU admission. Cluster 1 = young patients without any comorbidities, admitted in ICU for community-acquired pneumonia; Cluster 2 = young patients without any comorbidities, admitted in ICU for meningitis or encephalitis; Cluster 3 = elderly patients with COPD, admitted in ICU for bronchial infection with few organ failures; Cluster 4 = elderly patients with several comorbidities and organ failures; Cluster 5 = patients admitted after surgery with a nosocomial infection; Cluster 6 = young patients with immunosuppressive disease or therapy such as AIDS, chronic steroid therapy or hematological malignancy.