Step 1
You ask
A natural-language question — e.g. "What is the recommended follow-up for a 6 mm Bosniak IIF renal cyst?" or "Differentiate enchondroma from low-grade chondrosarcoma on MRI."
Step 2
We retrieve
Semantic retrieval across a curated corpus — peer-reviewed journals, society guidelines (RCR, ESR, ACR, BSIR, BSGAR…), openly licensed reference works and atlases. Verified web fallback (Exa, Tavily) fills gaps, through the same tier evaluation.
Step 3
We rank
Retrieved passages are ranked by semantic relevance and evidence tier. Tier 1 is guidelines, systematic reviews and randomised trials; Tier 3 is case reports. Higher-tier sources are preferred where they exist.
Step 4
We synthesise with citations
A Claude-family model composes the answer from the retrieved passages with native inline citations. Every claim is anchored to a source passage, and the language is calibrated: assertive for Tier 1, hedged for lower tiers.
Step 5
You verify
Every citation is clickable. Open the primary source, check the context, and apply your clinical judgement. MyRadAssistant is a reference tool, not a substitute for primary sources or clinical reasoning.
What we do not do
We do not interpret images. We do not process patient-identifiable information. We do not give patient-specific clinical recommendations and are not for use at the point of care on an individual patient. We are not a substitute for clinical judgement.
Where it runs
UK and EEA-based hosting. Frontend served via UK CDN. Backend on Hetzner (Germany). Vector store on Qdrant Cloud (Germany). Model API calls to Anthropic, OpenAI, Google, and Cohere are governed by Standard Contractual Clauses and the EU–US Data Privacy Framework where relevant. Web fallback queries to Exa and Tavily (US) are similarly covered under the Data Privacy Framework. See Privacy policy for full detail.