What AI does
- Scans text for superlative and comparative language that may require substantiation
- Identifies potential off-label implications or suggestions
- Flags areas where fair balance may be insufficient
- Detects language patterns commonly raised in MLR review (unqualified superiority claims, emotive language, implied guarantees)
- Highlights inconsistencies between claims and cited references
What AI cannot do
AI cannot determine whether a flagged item is genuinely non-compliant in context, apply the correct market-specific advertising code, make a fair balance determination, or sign off content as compliant. These require qualified human reviewers.Before you start
- Use this workflow on near-final drafts. Running pre-screening on rough drafts generates noise and provides limited value.
- Know which advertising code or regulatory framework applies. MedCheckr flags general patterns — market-specific requirements need market-specific expertise.
- Have the approved prescribing information (SmPC or USPI), the approved indication, and any approved messaging framework available for reference.
Steps
Prepare a near-final draft
Compliance pre-screening is most valuable when the content is close to its final form. Running it on early drafts generates flags for issues that will be revised anyway.
Identify the applicable code and context
Confirm which advertising code or regulatory framework applies (e.g., ABPI Code, IFPMA Code, FDA promotional regulations). Specify this when running the pre-screen.
Run MedCheckr
Submit the content to MedCheckr for automated compliance signal scanning. Provide the product, approved indication, target audience, and intended channel.
Review flagged items in context
Assess each flag against the applicable code and the approved messaging framework. Not every flagged item is a genuine issue — a superlative is acceptable if substantiated; a comparative claim is acceptable if correctly referenced.
Verify claims against references
Use RefCheckr or the Verify Claims workflow to confirm that the claims underlying any compliance flags are supported by cited references.
Revise as needed
Address genuine compliance concerns. Distinguish between high-priority issues (potential off-label claim, unsupported superiority) and lower-priority style concerns.
Document changes
Record what was flagged, what was changed, and why. This documentation is useful if questions arise during MLR review.
Prompt pattern
Understanding pre-screen output
- HIGH concern
- MEDIUM concern
- LOW concern
Potential off-label claim, unsupported superiority statement, or significant fair balance gap. Resolve before proceeding to MLR review. Discuss with your regulatory or medical reviewer.
Human review checklist
- All flagged items have been assessed in context by a qualified reviewer
- Superlative and comparative claims are substantiated by cited references
- Fair balance of efficacy and safety information is appropriate for the content type and audience
- No off-label implications or suggestions are present
- Claims are consistent with the approved indication(s)
- Language is appropriate for the content type and channel
- Prescribing information or SmPC references are included where required
- Content is consistent with any approved messaging framework or claims matrix
- Changes made during pre-screening are documented
- Content is ready for formal MLR review
Common failure modes
| Risk | What to look for |
|---|---|
| Over-reliance on pre-screening | A clean MedCheckr scan does not replace your own compliance review — it supplements it. A clean scan means the tool found nothing, not that nothing is there. |
| False positives | Expect MedCheckr to flag valid, substantiated language. Each flag is a prompt to check, not a finding. |
| Market-specific gaps | Pre-screening tools catch general patterns but may miss market-specific code requirements — have a reviewer with the appropriate local expertise assess results |
| Evolving regulations | Check results against the current published code — tool training data may not reflect recent updates |
Relevant tools
MedCheckr
Primary tool — automated compliance signal detection.
RefCheckr
Supporting tool — verify that promotional claims are supported by cited references.
Next steps
Verify Claims
Confirm claims are reference-supported before MLR submission.
Final Review
Complete the QC process before the deliverable enters the approval queue.