Our lead-risk map is built only from public housing age and poverty data. It has never seen a blood test. We held it against Iowa's real childhood blood-lead rates, county by county, pulled automatically from the CDC tracking network. Here is the prediction next to what was measured.
Hover a county to compare both numbers. Where the two maps share color, the prediction matched the measured reality.
A risk map is only worth trusting if it agrees with where children were actually poisoned. In Iowa it does, at the strength the original EPA study reported (Cohen's kappa 0.49 to 0.63). Most of this country has no public blood-lead map at all. A prediction built from data every neighborhood already has brings the same warning everywhere, including the places no one has measured.
Measured data: Iowa childhood blood-lead surveillance, CDC National Environmental Public Health Tracking Network (measure: percent at or above 3.5 µg/dL, 2022). Method anchor: Zartarian et al., Environmental Science & Technology, 2024 (DOI 10.1021/acs.est.3c07881). Predicted risk: U.S. Census ACS 2022 housing age + poverty, scored by DetectLead.
