clinicians.build · interactive · september 1, 2026

Two Out of Three

A network meta-analysis of 53 studies and 7 million admissions puts the best sepsis-prediction models at an AUROC of 0.88. Then the number nobody puts on a slide: pooled positive predictive value 34.2%. Here is what that means at your denominator — and what 3,106 US hospitals look like when you plot them against theirs.

Primary source: Nature npj Digital Medicine, published online August 31, 2026
Hospital data via MIMI Labs: CMS Care Compare, Timely and Effective Care — Hospital
Sepsis Care measures, reporting period 2024-07-01 to 2025-06-30, 3,106 hospitals, 489,935 cases

Discrimination is not the same as a workable alert. An AUROC of 0.88 says the model ranks septic patients above non-septic ones most of the time. A positive predictive value of 34.2% says that when it fires, it is wrong about twice for every once it is right. The paper names the consequence itself: a substantial risk for alarm fatigue.

The gap between those two numbers is not a modelling problem. It is arithmetic, and the variable that drives it is the one your vendor's slide never contains: how common sepsis actually is in the population you are screening.

the ppv engine — bayes, not a benchmark
4.0%
80%
85.0%
120
▶ Land on the pooled 34.2%
positive predictive value
false alerts
per 100 that fire
alerts per shift
number needed to alert
alerts per true sepsis

If you can't state false alerts per nurse per shift, you don't have a deployment plan. You have a benchmark.

Now the other denominator: 3,106 hospitals

The meta-analysis reports heterogeneity above 95% and a 95% prediction interval from −0.06 to 0.30 — a polite way of saying the pooled estimate may not describe your hospital at all. So here is every US hospital that reported CMS sepsis bundle compliance, plotted against the thing that decides how much to believe it.

Each dot is one hospital. Horizontal is the denominator — how many severe sepsis and septic shock cases the measure was computed on, from 11 to 2,313, on a log scale. Vertical is the score. Drag the denominator floor and watch the shape of the cloud change.

the critical lens — a denominator floor
no floor
hospitals shown
spread (SD)
percentage points
range
cases covered

What this can't tell you