Analysis
Original findings, recomputed and cross-checked.
Each analysis assembles something no single study or press release contains — a cross-study table, a recomputed rate — from the primary sources. To guard against a coding error rather than a typo, every finding is built independently by two different AI models and reconciled against the source, with the disagreements published. The data lives in the page for you to check and reuse.
-
The scoreboard that can’t be drawn: what seven “AI-beats-clinician” health studies actually measured
Seven headline studies say AI matches or beats clinicians in global health. Placed on one honest table, they report on six different scales, only one offers a fair AI-versus-human comparison, and exactly one measured whether a patient got better — it was null. An original, cross-checked dataset.