The abstract is read at the publisher; the summary is JClub's.
AI-mediated automated diagnosis of up to 80% of duodenal biopsies is broadly supported by patients and carers, with 68.4% backing AI-reliant diagnosis.
- Why it matters: Pathologist shortages and variable inter-pathologist concordance for duodenal biopsies can delay diagnosis and limit accuracy, motivating AI adoption that must align with stakeholder expectations.
- What they did: From Feb 2024 to Jun 2026, the team used mixed-methods engagement: an online patient/carer survey (n=231), UK focus groups (four workshops; n=34 matched Likert pairs around education), and a healthcare professional survey (n=37) plus workshops.
- The result: Support for trust, acceptance, and perceived benefit rose after structured education (38.2%→67.6%, 85.3%→97.1%, 52.9%→97.1%; all p<0.003), and professionals preferred an AI assistant model with validation and explainability.
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.