United StatesHealthcare and life sciences2017 – ongoingOchsner Health
Machine-learning alerts for patient deterioration
Ochsner's patient-deterioration pilot reduced cardiac and respiratory arrests by 44%, Microsoft reported
Problem
Hospital staff had to identify deteriorating patients among many people under their care. Responding only after cardiac or respiratory arrest left little time for prevention.
Approach
Ochsner trained a patient-deterioration model using Epic's machine-learning platform, supported by Microsoft Azure. Alerts prompted trained providers to assess patients before an expected emergency. Following a 90-day pilot in autumn 2017, Ochsner expanded coverage hours and deployment to more hospitals.
Results
Takeaway
Ochsner adjusted alert timing and trained staff to respond before an arrest. The reported reduction compared the pilot with the hospital's typical number of arrests.
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
- Off-the-shelf tool or platform
- Goal
- Quality and risk
- Evidence
- Vendor case study
Sources
Source summaries
Microsoft reported a 44% reduction in arrests during Ochsner's 90-day pilot. It described local model training and changes to how clinicians received and acted on alerts.
Full details are in the original sources.