Sepsis is a leading cause of morbidity and mortality in hospitalized patients. While most sepsis research has focused on community-onset sepsis (COS), hospital-onset sepsis (HOS) is increasingly recognized as a distinct clinical entity with worse outcomes. However, a few studies have systematically compared the characteristics and outcomes of COS and HOS. Understand the differences between COS and HOS from a clinical perspective and study hospital outcomes in sepsis patients using a machine learning driven approach. We conducted a retrospective analysis of sepsis events at a major academic medical center in the Pacific Northwest using our institutional and Vizient databases. Adults (≥ 18 years) hospitalized with sepsis between January 2019 and August 2023 were included. We compared demographics, clinical characteristics, comorbidities, and outcomes between COS and HOS. We analyzed the association between the timing of sepsis onset and hospital outcomes. Random Forest models were used to evaluate the variable importance to hospital outcomes. Among 2,589 hospitalizations of patients with sepsis in the combined dataset, HOS was associated with significantly higher in-hospital mortality (38.2% vs. 28.5%, P < 0.001), longer median hospital (24 vs. 11 days, P < 0.001), and Intensive Care Unit (7 vs. 2 days, P < 0.001) length of stay (LOS) compared to COS. Patients with HOS also had a higher comorbidity burden and were less likely to receive early antibiotic therapy. In a random forest model, the timing of sepsis onset (HOS vs. COS) emerged as one of the key predictors of both mortality and hospital LOS. HOS sepsis is associated with significantly higher mortality, longer hospital and ICU stays, and delayed antibiotic initiation compared to COS. These findings underscore the importance of early recognition and targeted management strategies for HOS. Our insights could also help refine predictive models for better sepsis detection, treatment and prognostication.
Verma et al. (Sat,) studied this question.