J

Johns Hopkins TREWS identifies 82% of sepsis cases early, cuts time to antibiotics by 1.85 hours

“Johns Hopkins TREWS identifies 82% of sepsis cases early, cuts time to antibiotics by 1.85 hours” documents a Clinical Decision Support deployment in Hospital & Health System at Johns Hopkins Medicine. www.mayoclinicplatform.org reports sepsis detection rate: 82%; this directory has not independently verified that result.

Maintained by Peter Korpak, Founder & Chief AnalystHow evidence is checked

Evidence at a glance

Evidence status:
Automated evidence gate passed
Deployment timeframe:
Not reported by source
Reported outcome metrics:
2 cited below
Directory entry published:
Source link checked:

The source-link check confirms reachability, not independent re-verification of every claim.

82%Sepsis Detection Rate
1.85 hoursTime to Antibiotic Reduction

Source-reported figures — cited source: www.mayoclinicplatform.org

The Challenge

Sepsis affects nearly 49 million patients annually with ~11 million deaths worldwide. Existing detection protocols including Epic's sepsis algorithm have well-documented shortcomings, often failing to identify patients early enough for timely intervention.

The Solution

Johns Hopkins investigators developed TREWS (Targeted Real-Time Early Warning System), a machine learning model deployed across five hospitals over two years. The system monitors patients in real time and alerts providers, who can confirm or dismiss the alert within a 3-hour window before antibiotic orders are placed.

Results

Across 9,800+ retrospectively confirmed sepsis cases, TREWS identified 82% of patients early. A prospective multi-site study of 6,800+ patients showed that timely provider confirmation (within 3 hours) reduced median time to first antibiotic order by 1.85 hours and was associated with reduced in-hospital mortality.

Key Takeaways

  • Provider confirmation speed is a critical mediating variable — alert value depends on clinician engagement within a narrow window.
  • Both retrospective and prospective validation are needed; retrospective alone may miss confounders.
  • Deploying across five hospitals in a real-world setting demonstrates generalizability beyond a single site.

Share:

Details

Company Size
Enterprise
Evidence status
Automated evidence gate passed
Deployment timeframe
Not reported by source
Directory entry published
Source link checked

Have a similar implementation?

Share your customer's AI results and link it to your vendor profile.

Submit a case study →