Abstract
BACKGROUND AND OBJECTIVES: Delays in septic shock diagnosis cause preventable mortality in children. Evidence is limited around early recognition strategies. The hypothesis was that clinical decision support (CDS) based on machine-learning predictive models would increase the proportion of children receiving septic shock treatment prior to shock onset. METHODS: CDS was implemented in a prospective, stepped-wedge, cluster randomized trial in 4 pediatric emergency departments (EDs) over five 10-week periods. The CDS used models identifying children who did not yet have shock but were predicted to be at high risk based on electronic health record data at arrival and after 2 hours. Providers received CDS; effectiveness was evaluated in patients 60 days to 18 years with concern for sepsis. The primary outcome was antibiotic and bolus within 1 hour of sepsis suspicion. Secondary outcomes were time-to-antibiotic, hypotensive septic shock. Implementation outcomes were evaluated in qualitative interviews. RESULTS: Of 200 354 ED encounters from March 16, 2022, to March 1, 2023, 1331 encounters met inclusion criteria (979 intervention, 352 control arms). Antibiotic and bolus within 1 hour occurred in 39.0% of patients in the intervention arm versus 38.9% of patients in the control arm (adjusted odds ratio [aOR]: 1.07 [0.61-1.88]). There was no difference in outcomes of shock (aOR: 1.12 [0.53-2.46]) or antibiotic timeliness (aHR: 0.85 [0.63-1.16]). Providers reported the CDS felt valuable and unobtrusive (adoption); 6 months after the trial, EDs continued to use the CDS (maintenance). CONCLUSIONS: Implementing predictive CDS that infrequently alerted was feasible and acceptable. It did not change the proportion of patients with suspected sepsis who progressed to hypotensive shock.