clinicians.build · interactive · august 31, 2026

Who Is Asking?

At Epic's CIO Forum, MyChart's AI told a patient it was fine to play golf. The room's first thought was lawyers. Here is the question nobody asked: who is on the other end? Every US county — 3,144 dots, 260.8 million adults — on ten CDC health measures.

Data: CDC PLACES, Local Data for Better Health — County Data, 2024 release
Crude prevalence, adults 18+, modelled from BRFSS 2022 · all 3,144 counties

A patient asks the assistant whether it is okay to play golf. Based on the record, the assistant says yes. A CIO who is also a practising clinician raises his hand: you do realise that's medical advice. On This Week Health's Newsday, the word the panel reaches for is lawyers.

All of that is downstream of a question nobody asked: was the answer correct? And correctness here is not a property of the model. It is a property of the person typing. Eighteen holes is four to five miles of walking. For most adults that is exercise. For an adult with coronary heart disease, or COPD, or a recent stroke, it is a clinical question whose answer depends on things a chart may or may not contain.

An escalation threshold is not a policy. It is a number applied to a population. So look at the population.

Every county in the United States, on two axes you choose

Each dot is one county. Dot area is the adult population — from Loving County, Texas (37 adults) to Los Angeles County (7.7 million). Colour is the uncertainty index: the average width of the 95% confidence interval across all ten measures for that county. Navy dots are tightly estimated. Red dots are not.

Horizontal axis
Vertical axis
any size
≤ 6.44 pts
tight estimate wide estimate · dot area = adults 18+ · dashed lines = US value
Counties shown
3,144
of 3,144 counties
Adults covered
260.8M
100.0% of US adults
Spread on X
lowest to highest county
Correlation r
X vs Y, unweighted
Pick two measures. The gap between the lowest and the highest county is the range of people a single answer has to be correct for.

What the assistant cannot see from inside the chart

Leave the horizontal axis on coronary heart disease. The national figure is 6.8% of adults. The county range runs from 3.4% in Madison County, Idaho to 14.9% in La Paz County, Arizona — a 4.4× spread. Four hundred and ninety-four counties, holding 9.3 million adults, sit at 10% or above.

None of that is visible to a patient-facing assistant reading one record. It is not supposed to be. But it is exactly the thing an escalation threshold gets calibrated against, and a threshold tuned on the population that produced the pilot data is a threshold tuned on somebody else's county.

The critical lens: the correlation that will not move

Drag min adults all the way right and watch the correlation. Nine hundred and seventeen counties — 29% of all counties, holding 1.8% of US adults — have fewer than 10,000 adults. In most county datasets, dropping them collapses whatever pattern the tiny denominators invented.

Here it barely budges. Coronary heart disease against fair-or-poor general health is r = 0.66 across all 3,144 counties and r = 0.59 among counties with 50,000+ adults. That stability is not evidence the finding is robust. It is evidence of what these numbers are.

PLACES county estimates are not measurements. They are model-based small-area estimates — multilevel regression on BRFSS responses, poststratified onto census demographics. In a county with a handful of respondents, the estimate is mostly the model talking. The same covariates drive every county, so some of the correlation between measures is built in. Filtering by size does not remove the model. It removes the counties where the model did the most work.

Read this the right way round. The county-level ranking is credible — PLACES is validated for exactly that. The county-level precision is not: the average 95% interval across these ten measures spans 4.7 percentage points, and in the widest county it spans 6.4. Use this to ask who is asking. Do not use it to set a threshold to one decimal place.

The uncertainty ceiling is the honest version of the small-n filter. Slide it down and the dots that vanish first are not the wrong counties — they are the counties where CDC is telling you, in the width of the interval, that it does not really know.

What this does not show