United StatesHealthcare and life sciences2013 – ongoingKaiser Permanente
Advance Alert Monitor for inpatient deterioration
Kaiser's inpatient warning program operated at 21 hospitals, with researchers estimating 520 deaths prevented annually
Problem
Hospitalized patients could deteriorate before their local care teams recognized the risk. Earlier warnings could give clinicians more time to intervene.
Approach
Kaiser Permanente researchers developed a predictive algorithm that checked patient-record data hourly. Remote clinical staff monitored its alerts and contacted local care teams when intervention was needed. Advance Alert Monitor operated across Northern California hospitals.
Results
Takeaway
The evaluated program combined risk prediction with remote monitoring and local clinical intervention. The mortality estimate covered that care process rather than the algorithm alone.
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
Kaiser described its hospital warning program and the clinical teams responding to alerts. It reported an evaluation by the program's developers that estimated an average of 520 deaths prevented annually.
Full details are in the original sources.