Journal

OpenAI has connected ChatGPT for Healthcare to Epic and added a nine-source public data plugin spanning PubMed, DailyMed and openFDA. What was actually announced on 1 September 202...

A nine-step workflow for using iatroX around, never instead of, an authorised diagnostic AI device: from receiving a flag through evidence retrieval, alternative-explanation checki...

A research conversational-diagnostic system, a research multi-agent orchestrator, and a currently accessible clinical-reasoning tool are not equivalent products. AMIE and MAI-DxO w...

The strongest CPD starts with a real clinical problem and ends with a change in practice; the workflow that turns one Ask-iatroX question into complete revalidation evidence, with ...

AI should increase active reasoning and source navigation on a V300, not complete assignments or bypass pharmacology; the appropriate and high-risk lists, and the six-step learning...

Two locations in the knowledge stack: Ask Eolas answers from your organisation's own approved protocols; iatroX serves national guidance, medicines information and learning; why bo...

AI does not add an eleventh competency; it changes how prescribers demonstrate the existing ten. The full mapping: appropriate use, unsafe shortcut and portfolio evidence for every...

Heidi is an integrated care partner whose evidence function sits beside documentation; iatroX is a dedicated knowledge, reasoning and learning layer; the full-consultation walkthro...

Three UK clinical answer engines, three architectures of trust: direct source retrieval, national-plus-organisational search, and a curated GP-authored archive; six test questions ...

Single-condition guidelines collide in real patients; how ANPs can use AI to organise the collisions, seven sorting categories for a fourteen-medicine review, and why an AI-optimis...

A real citation can sit under a wrong answer: five citation failures, the 2026 evidence that even the best AI drug-information tools score below pharmacists, and the verification s...

Students use AI weekly while faculty confidence and policy vary wildly; why educator development, not student training, is the binding constraint, and the five-component faculty cu...