Mortality and antibiotic timing in deep learning-derived surviving sepsis campaign risk groups: a multicenter study
Authors' conclusion
Our data suggest that patients who are at low risk of developing shock and possible sepsis had similar rates of mortality in the 1-hour vs. > 1-hour and 3-hour vs. > 3-hour time to antibiotic administration groups.
Study context
- Population
- Adults with potential sepsis at the time of clinical suspicion, two large health systems, 2016–2024adults with potential sepsis
- Participants
- 34,087 adults
- Exposure
- Deep learning (DL)-derived Surviving Sepsis Campaign (SSC) risk groups; antibiotic timing within groups
- Outcome
- Short-term mortality (composite of in-hospital mortality and transition to hospice care) across each risk group
Methodological detailsmulticentre, two health systems, deep learning risk stratification, development and validation sites, prospectively applied patient data, encounters 2016–2024
- Multicentre
- Two health systems
- Deep learning risk stratification
- Development and validation sites
- Prospectively applied patient data, encounters 2016–2024
Main finding
As reported in the abstract
Short-term mortality by risk group
Observational data: associations, not effects.
Further findings
Time to antibiotics by risk group · development site
Mortality by antibiotic timing, possible sepsis unlikely to develop shock (subgroup)
- Mortality similar regardless of antibiotics within 1, 3 or more hours from triage
Mortality by antibiotic timing, probable sepsis regardless of shock risk (subgroup)
- Mortality significantly lower if antibiotics within the first hour from triage
- Development site
Original publication
Mortality and antibiotic timing in deep learning-derived surviving sepsis campaign risk groups: a multicenter study. Crit Care. Published 14 July 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →