Sikkerhet og ansvarlig bruk

What MedCite is for

• Looking up guideline material and supporting literature
• Quick clinical orientation during the working day
• Preparing for teaching rounds, journal clubs, and case discussions
• Starting evidence reviews with traceable sources
• Checking medication information against source-linked references
• Finding relevant national and European guidance

What MedCite is not for

• Emergency advice or urgent care decisions
• Autonomous diagnosis or differential diagnosis
• Autonomous prescribing or dosing decisions
• Patient-specific treatment decisions
• Replacing professional clinical judgment
• Replacing systematic review methodology

Human Oversight

Healthcare professionals remain fully responsible for all clinical decisions. MedCite outputs must be verified against primary sources, local guidelines, and institutional protocols. The service is designed to support, not replace, professional medical judgment.

How MedCite supports safe use

• Citation discipline: every paragraph or bullet is grounded in cited sources you can open and inspect
• Source verification: click through to original guidelines, articles, and authority sources
• Patient query detection: queries describing individual patients trigger evidence-only responses with explicit disclaimers
• Emergency detection: potential emergency queries are flagged to indicate this is not an emergency assessment tool
• Prescribing guardrails: dosing queries receive guideline-framed information only, never patient-specific instructions

Regulatory Context

MedCite is intentionally designed as a source-linked clinical evidence search tool — not for diagnosis, prescribing, or patient-specific clinical decision-making.

Clinical Evidence Planner

MedCite uses a Clinical Evidence Planner that makes evidence retrieval auditable. Every query is classified into a clinical task (e.g., drug timing, treatment guideline, diagnosis), key entities are extracted, and evidence retrieval is planned accordingly. This reasoning is exposed so clinicians can inspect why sources were selected and validate the task interpretation.

Key Features

• Transparent task classification: see how MedCite interpreted your clinical question
• Entity extraction: drugs, conditions, and procedures are identified and normalised
• Task-driven retrieval: searches use answer-bearing concepts, not just topic keywords
• Answerability validation: evidence packs are checked for required concepts before synthesis
• Deterministic fallback: known clinical patterns trigger structured query templates as rescue path
• Source-role prioritisation: guidelines and reviews are boosted over case reports and imaging-only papers
• EU AI Act-aligned transparency: audit trail exports task, entities, sources, and validation results