domains / families / science / real-world-evidence-study-designer

real-world-evidence-study-designer

separate

Designs a structured real-world evidence study using EHR, claims, or registry data, with explicit handling of time zero, eligibility windows, exposure definitions, outcome windows, censoring, confounding control, and target-trial-emulation logic. Use this skill when the user needs study-type design and protocol framing for an observational clinical study based on routine-care data. Do not invent database fields, follow-up completeness, linkage, coding validity, or causal identifiability.

When to use

• study-type design and protocol framing for observational clinical studies
• comparative effectiveness or safety questions using routine-care data
• treatment pattern, adherence, switching, utilization, or outcome questions
• prognostic or outcome-association questions requiring longitudinal real-world follow-up
• designing observational studies with time-zero, exposure, outcome, and censoring logic
• emulating part of a target trial using available real-world data

When not to use

• direct patient-specific diagnosis or treatment advice
• randomized trial protocol requests
• case-control, purely cross-sectional, diagnostic accuracy, mechanistic experimental, or qualitative designs
• pure literature review requests with no study-design purpose
• simple retrospective chart review
• cross-sectional database description
• unsupported causal inference

Skill page

Source