Skip to main content
Produce a clear, accessible summary of clinical or scientific information for patients, carers, or the general public — accurately representing the evidence in language that non-specialists can understand.
Risk tier: High  ·  Review requirement: Expert review by a medical writer and medical professional; lay reader testing recommendedPlain language summaries go directly to patients and the public. Oversimplified or inaccurate claims can create false reassurance or misunderstanding about treatment benefits and risks. Every claim must be verified against the source and assessed for meaning by a qualified reviewer.

​
What AI does

  • Translates dense clinical language into plain terms rapidly
  • Structures PLS content into standard formats
  • Produces a first draft that captures the main findings in accessible language
  • Suggests simplified explanations for complex medical concepts (randomisation, placebo, confidence intervals)

​
What AI cannot do

AI does not know whether a simplified claim still means what the original said, whether safety information is proportionate, whether the tone is appropriate for patients facing a serious condition, or whether the output meets the specific regulatory requirements that apply to your PLS. All of this requires human judgement.

​
Before you start

  • Identify format, structure, reading level, and any regulatory template requirements before starting. PLS for clinical trial disclosure (e.g., EU CTR) must meet specific requirements — start from the regulatory template, not from a general AI draft.
  • Review the source document yourself. Understand the findings, including safety data and limitations, before generating a draft.
  • Confirm that the source findings are settled and reviewed by the clinical team. Do not produce a PLS from preliminary or still-being-interpreted results.
If the PLS must meet a specific regulatory template (e.g., ICH E6-compliant lay summaries, EU CTR requirements), start from the required template. Use AI to help populate it — not to generate free-form output that you then try to fit to the template.

​
Steps

1

Identify requirements

Determine the format, structure, reading level, and any regulatory template requirements that apply. If a specific template is mandated, gather it before starting.
2

Review the source material

Read the source document yourself — the paper, CSR, or results summary. Understand the study design, efficacy findings, safety data, and limitations before generating a draft.
3

Generate a first draft

Use PLS Generator, Patiently AI, or the prompt pattern below to produce a structured first draft.
4

Verify accuracy against the source

This is the highest-priority review step. Every clinical claim, data point, and conclusion must be checked against the source document. For each simplified statement, ask: is this still true? Does it preserve the scope and certainty of the original?
5

Review safety balance

Assess the proportion of safety content relative to efficacy content. Safety must be a clearly labelled, substantive section — not a footnote. Count sentences or paragraphs if necessary to check balance.
6

Check for jargon

Read the PLS as if you have no medical training. Every technical term — including “randomised,” “placebo-controlled,” and “hazard ratio” — must be explained or replaced with plain language.
7

Expert review

A qualified medical professional must review the PLS before it is published or submitted. This is not optional regardless of how thorough your own review was.
8

Lay reader testing

Where possible, test the summary with representative members of the target audience. Written readability scores (Flesch-Kincaid, SMOG) are useful but do not replace testing with real readers.

​
Prompt pattern

You are a medical writing assistant specialising in plain language summaries. Your task is to create a plain language summary of the following clinical study for a non-specialist audience.

Target audience: [SPECIFY — e.g., patients with Type 2 diabetes, general public, carers of patients with Alzheimer's disease]
Reading level: [SPECIFY — e.g., 8th grade reading level, suitable for adults with average health literacy]
Format: [SPECIFY — e.g., structured with headings: Why was this study done? Who took part? What happened during the study? What were the results? What do the results mean?]

Source document:
[INSERT SOURCE TEXT]

Rules:
- Write in clear, simple language. Avoid medical jargon. Where a medical term must be used, explain it in plain language.
- Accurately represent the study findings. Do not overstate or understate results.
- Include information about side effects and safety findings. Do not focus only on positive results.
- Include the study limitations as described by the authors.
- Do not provide medical advice or recommendations.
- Do not include information that is not in the source document.
- Use short sentences and short paragraphs.
- Explain what the study measured and why, not just the results.

​
Human review checklist

  • All clinical claims are accurate when compared against the source document
  • Data points (numbers, percentages, timeframes) are correctly represented
  • Safety information is included and fairly represents the data
  • Study limitations are noted
  • Language is genuinely accessible to the target audience
  • Medical terms are explained or avoided
  • No medical advice or treatment recommendations are given
  • No unsourced information has been added
  • The PLS is balanced — it does not read as promotional or overly positive
  • Format meets any regulatory or sponsor-specific requirements
  • Reading level is appropriate (consider readability testing tools)
  • Tone is respectful and sensitive to the audience

​
Common failure modes

RiskWhat to look for
Oversimplified claims”The treatment worked” in place of “The primary endpoint was met with statistical significance at Week 24” — different meanings with different implications for patients
Minimised safety dataEfficacy gets 400 words; side effects get two sentences — check balance before signing off
False reassuranceBiomarker endpoint (e.g., reduced HbA1c) described as “patients felt better” — only translate biomarker results into patient experience if the data directly supports it
Jargon persistence”Randomised,” “placebo-controlled,” “hazard ratio” appearing without explanation
Missing regulatory elementsRequired sections, registration numbers, or format elements absent — cross-check against the applicable regulatory template

​
Relevant tools

PLS Generator

Primary tool for generating structured plain language summary drafts.

Patiently AI

Simplifying specific medical explanations within the PLS.

​
Next steps

Verify Claims

Confirm simplified claims still match the source after drafting.

Final Review

Expert QC before the PLS is published or submitted.