TrialsgrambetaRCTs are beautiful

Deterioration & sepsis alerts

Machine-learning and electronic early-warning systems on hospital wards: CONCERN, SCREEN, the Kaiser Advance Alert Monitor and TREWS.

  • 2025CONCERN Core⁠General deteriorationIn 60,893 hospital encounters on 74 clinical units, a machine-learning early warning system reading nursing documentation reduced in-hospital mortality and length of stay compared with usual care.HR 0.6495% CI 0.53-0.78Read →
  • 2025SCREEN⁠Sepsis alertsIn 60,055 patients admitted to hospital wards, an electronic qSOFA-based sepsis alert reduced 90-day in-hospital mortality compared with no screening (alert in silent mode).RR 0.8595% CI 0.77-0.93Read →
  • 2022TREWS⁠Sepsis alertsIn 6,877 patients with sepsis flagged before antibiotics, provider confirmation of the machine-learning sepsis alert within 3 h reduced in-hospital mortality compared with alerts not confirmed by a provider within 3 h.Read →
  • 2020Escobar Advance Alert Monitor⁠General deteriorationIn 43,949 non-ICU hospitalisations reaching the alert threshold, automated deterioration alerts reviewed by remote nurses and escalated reduced 30-day mortality after an alert compared with usual care where the system was not yet deployed.RR 0.8495% CI 0.78-0.90Read →