clinicians.build · interactive · september 3, 2026

Two Denominators

A Medicare add-on payment attaches to cases where the technology was used. A positive predictive value describes the alerts it got right. Same product, two denominators — and only one of them appears on the claim. Here are a thousand dots, colored both ways.

Primary source: “Artificial intelligence tools in sepsis prediction: a systematic review and meta-analysis,”
npj Digital Medicine, August 31, 2026 — 53 studies, >7 million admissions, pooled PPV 34.2%
Payment figures: Bayesian Health NTAP approval (PR Newswire, Sep 2, 2026) · CMS FY2027 IPPS final rule

Starting October 1, hospitals can bill up to $61.84 per case for a continuous AI sepsis monitor, across an estimated 739 MS-DRGs. It is the first line in the Medicare inpatient payment system drawn for continuous monitoring software.

The obvious objection is that 82% sensitivity is not good enough to pay for. That is the wrong number to be angry about. Watch what happens when the same thousand dots get counted two different ways.

denominator 1 — the claim
Every case where the monitor was used
denominator 2 — the alert
Every case the alert said was sepsis
$0
billable
billable / true positive not counted / false positive 1 dot = 1 case
move the assumptions
34.2%
$61.84
paid on 1,000 cases
regardless of correctness
alerts that were right
at the pooled PPV
per correct catch
payment ÷ true positives
paid on wrong alerts
the alarm-fatigue tab

$61.84 against the bar it sits on

The other reflex is that $61.84 is a rounding error. It is. Drawn to scale against the average Medicare payment for DRG 871 — septicemia or severe sepsis with MCC, $15,105 — the add-on is the red edge below. That is 0.41%.

■ $61.84 add-on — 0.41%DRG 871 average Medicare payment — $15,105

But DRG 871 is the single largest MS-DRG in Medicare fee-for-service inpatient — 561,795 discharges across 2,678 hospitals. A sliver of the biggest denominator in the building is $34.7M a year at perfect capture, and it is the first line in the system with continuous monitoring software's name on it.

Where this argument is thin

The argument worth having is not whether the model is good enough. It is that Medicare just built a payment whose denominator is usage, for a class of product whose failure mode is over-firing. Those two facts point the same direction, and nobody has to be dishonest for it to go badly.