United StatesHealthcare and life sciences2016 – ongoingDuke University
Sepsis Watch early warning and treatment workflow
Duke reported doubled sepsis-treatment compliance after deploying Sepsis Watch
Problem
Duke sought earlier recognition of sepsis and more timely completion of recommended treatment.
Approach
Sepsis Watch began with a proposal in 2016 and went live in November 2018. Duke combined a machine-learning model with a web application for tracking patients and treatment. Clinical workflows were tailored to its emergency departments.
Results
Takeaway
The reported improvement concerned treatment-bundle compliance. Duke was still evaluating clinical outcomes when it published these results.
Categories
- Size
- Large enterprise
- Industry
- Healthcare and life sciences
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Built in-house
- Goal
- Quality and risk
- Evidence
- Company's own claim
Sources
Source summaries
Duke described Sepsis Watch's deployment and subsequent expansion into inpatient care. It reported doubled treatment-bundle compliance across three emergency departments while evaluation of clinical outcomes continued.
Full details are in the original sources.