Product type · Not yet

Predictive models quality.

Risk scores that drift without warning. Predictive models score risk: sepsis, readmission, deterioration.

Not offered yet: we are being honest about what we do not do today.

Not yetwhere it sits for Precision
8parameters we can measure
3agents that help
3common failures to test first
What goes wrong

Where predictive models breaks.

Predictive models score risk: sepsis, readmission, deterioration. They're often built once and left running while the patient population and the hospital change.

Drift

Performance falls as patients, coding or workflows change.

Alert fatigue

A low positive predictive value means most alerts are false.

Miscalibrated risk

A 20% score doesn't mean 20% of those patients have the event.

How we test it

Three steps, in the open.

Local validation and drift (Epic's free seismometer already covers tabular models).

  1. 01

    Validate locally

    Check discrimination and calibration on your own patients.

  2. 02

    Measure alert burden

    Positive predictive value and alerts per day.

  3. 03

    Watch over time

    Track subgroup results and drift.

As a service

Local validation and drift checks.

As a product

Drift monitor.

Why it matters now

Who builds it, who buys it.

Epic Sepsis Model and risk models, Bayesian Health

The stakes

Free tools already serve much of this need, so it isn't our wedge.

Measure predictive models on your own data

Questions

Common questions.

Do you evaluate predictive models?

Not as a focus. We include drift and local validation in other services when they apply.

What is calibration?

How well predicted risk matches what actually happens.

Why does local validation matter?

Joint Commission and CHAI guidance expects it before go-live, because performance elsewhere may not hold in your hospital.

Know your healthcare AI is safe to trust
before it reaches a patient.

Book a 30-minute call. We'll look at your product and tell you what we would measure first.