Advance Alert Monitor (Kaiser Permanente)

By Kaiser Permanente (Division of Research)
· USA
In-house early warning model that scores ward patients every hour from the electronic health record, so a remote nurse team can trigger rapid-response review before deterioration.
Predictive
Critical Care
Multi-Hospital
Regulatory status
Deployment
Multi-Hospital
Clinical role
Adjunct (decision support)
Headquarters
USA
AI type
Predictive

Precise indication

Adult medical-surgical ward patients. An automated score predicts the risk of deterioration (unplanned ICU transfer or death) within the next 12 hours. Alerts are reviewed by specially trained remote nurses, who contact the bedside rapid-response team; scores are not shown directly to bedside staff.

Regulatory status

Developed and used internally by Kaiser Permanente Northern California. No FDA clearance or CE marking reported in the sources reviewed (November 2026).

Clinical evidence

Vendor-supported

Developer-led evaluation: Escobar GJ et al., NEJM 2020;383:1951-60. Staggered deployment across 21 hospitals (2013-2019), observational design. 30-day mortality after an alert 15.8% vs 20.4% in comparison patients; adjusted relative risk 0.84 (95% CI 0.78-0.90). ICU admission 17.7% vs 20.9%.

Independent

Real-world deployment

In routine use in Kaiser Permanente Northern California hospitals: pilot in 2 hospitals from 2013, then staggered rollout to 19 further hospitals between August 2016 and February 2019.

Interoperability

European status

Editorial verdict

Limits and uncertainties

– Evaluated by the team that built it; no independent external validation identified.
– Observational, staggered rollout rather than a randomised trial: residual confounding is possible.
– The benefit depends on the organisational model (dedicated remote nurse team, rapid-response escalation), not on the score alone.
– Built and calibrated on one integrated health system; performance elsewhere would need local validation.

Sources

Study, Escobar GJ et al., Automated Identification of Adults at Risk for In-Hospital Clinical Deterioration, NEJM, 2020: https://pmc.ncbi.nlm.nih.gov/articles/PMC7787261 News, Kaiser Permanente, Real-time alerts associated with lower mortality, November 2020: https://about.kaiserpermanente.org/news/press-release-archive/real-time-alerts-associated-with-lower-mortality

This profile is not medical advice or an endorsement. Hospitals should perform their own due diligence (regulatory compliance, GDPR, cybersecurity, integration, local clinical validation). How we evaluate

At a glance
Vendor
Kaiser Permanente (Division of Research)
Headquarters
USA
AI type
Predictive
Specialty
Clinical role
Adjunct (decision support)
CE marking
Notified body
EU AI Act
Data hosting
Last verified
Reviewed by
How we evaluate

Every profile documents the precise indication, regulatory status, vendor-supported and independent evidence, real-world deployment, limits and dated sources.

A independent systematic review or prospective multicentre study · B at least one independent peer-reviewed study · C peer-reviewed, vendor-supported · D vendor claims only.

Read the methodology →

Spotted an error?

Vendors, authors and clinicians can request a correction. Corrections are dated on the profile.