Skip to main content
Rapidly produce accurate, structured summaries of scientific posters or congress presentations — for client briefings, internal reports, congress highlights packages, or as source material for further medical communications work.
Risk tier: Medium  ·  Review requirement: Standard to enhanced review; verify all data points against the original poster

​
What AI does

  • Extracts structured data from visually complex poster layouts rapidly
  • Organises poster content into a consistent summary format
  • Drafts narrative summaries from structured extractions
  • Processes multiple posters in sequence for congress coverage

​
What AI cannot do

AI does not assess clinical significance, contextualise findings within the competitive landscape, or reliably extract data encoded in figures (Kaplan-Meier curves, waterfall plots, forest plots). Every data point extracted from a visual element must be manually verified.

​
Before you start

  • Confirm you have permission to process the poster content. Do not use this workflow on embargoed data without authorisation.
  • Obtain the full poster — not just the abstract. Key results, safety data, and methodology details are often absent from abstracts.
  • Know your target summary format and audience before starting. A one-page client briefing and a structured extraction for a publications group need different outputs.
Do not summarise embargoed poster data without confirming you have permission to do so. Congress embargo policies vary — check before processing.

​
Steps

1

Obtain the full poster

Ensure you have access to the complete poster content. Note the poster reference details: authors, title, congress name, poster number, and date.
2

Extract structured content with PosterLens

Use PosterLens to extract key information from the poster into a structured format: study design, population, endpoints, results, safety, and conclusions.
3

Review the extraction

Verify that PosterLens has accurately captured the poster content. Pay particular attention to data in figures, tables, and footnotes — these are the most common sources of extraction errors.
4

Manually verify data from visual elements

Open the original poster and manually check all figures (Kaplan-Meier curves, waterfall plots, forest plots, bar charts) and tables. Data encoded visually is not reliably extracted by any automated tool.
5

Draft the summary

Using the verified extraction as source material, draft the summary using the prompt pattern below. Specify the target format and audience.
6

Review against the original poster

Confirm every data point and finding in the summary matches the poster. Do not trust the AI draft without this check — particularly for numbers read from figures.
7

Add context if required

If the target audience requires context (e.g., what this study adds to the field), add this from your own clinical knowledge. Clearly distinguish between information from the poster and contextual information you have added.
8

Final review

Confirm accuracy, completeness, and appropriateness for the target audience and format.

​
Prompt pattern

You are a medical writing assistant. Your task is to create a summary of the following scientific poster presentation.

Format the summary with these sections:
- Poster reference (authors, title, congress, poster number)
- Study design and objective
- Key population characteristics
- Primary results
- Secondary / additional results
- Safety findings (if presented)
- Authors' conclusions
- Relevance / significance (brief — what this adds to the field)

Source material:
[INSERT POSTER CONTENT OR POSTERLENS EXTRACTION]

Target audience for this summary: [SPECIFY]
Target length: [SPECIFY — e.g., 300 words, one page, bullet-point format]

Rules:
- Base the summary only on what is presented in the poster. Do not add data from other sources.
- Reproduce data points exactly as presented.
- If safety data is not presented on the poster, note this explicitly rather than omitting the safety section.
- Flag any data points that are unclear or difficult to read in the source with [VERIFY].
- Do not interpret results beyond what the authors state in their conclusions.

​
Multi-poster coverage

When covering a medical congress with multiple posters, organise your workflow to prevent data leakage between summaries.
Summarise one poster at a time in separate sessions. Verify each summary against its specific poster before moving to the next. When AI processes multiple posters in sequence, data from one can appear in the summary of another.
For congress highlights packages, use a consistent extraction template across all posters so the output can be compared and assembled efficiently.

​
Human review checklist

  • Poster reference (authors, title, congress, poster number) is correct
  • Study design is accurately described
  • Population characteristics match the poster
  • All data points are verified against the original poster
  • Results from figures and tables are accurately captured — not estimated from visuals
  • Safety data is included (or noted as not presented)
  • Authors’ conclusions are correctly represented
  • No data from other posters or sources has been mixed in
  • Summary format and length meet the project requirements
  • Summary is appropriate for the target audience

​
Common failure modes

RiskWhat to look for
Data extraction errors from figuresKaplan-Meier curves, waterfall plots, and forest plots — numbers must be manually confirmed from the original poster, not trusted from AI extraction
Missing data from visual elementsFigures and tables contain results that the extraction omits — explicitly check all visual elements against the summary
Overinterpretation”A numerical trend toward improvement (not statistically significant)” becoming “improvement was observed” — compare every result statement against the poster
Missing safety dataSafety table in a lower panel of the poster overlooked by the extraction — explicitly scan the full poster for safety content
Context confusionWhen processing multiple posters, data from one poster appearing in the summary of another — summarise one poster per session

​
Relevant tools

PosterLens

Primary tool — structured extraction of poster content for summarisation.

​
Next steps

Extract Key Messages

Pull out the key findings from your poster summary for use in a messaging framework.

Repurpose Content

Adapt the summary for different deliverable formats (highlights report, client briefing, training material).

Summarise a Source Paper

If the full publication is available alongside the poster, use this workflow for the paper.