EichorEICHOR
Study identifier: NCT07739121 Synced from ClinicalTrials.gov · August 07, 2026
● Study status: Recruiting

Benchmarking Large Language Models Against Tumour Boards for Oncology Treatment Recommendations

Condition: Breast Neoplasms · Lung Neoplasms · Urologic Neoplasms  ·  Sponsor: Assistance Publique - Hôpitaux de Paris

PhaseN/A
Planned participants100
Who can joinAll sexes, 18 Years to no upper limit
Healthy volunteersNo

Sponsor, CRO or site team? See where this study is running → — listed sites, countries and recruiting context. Everything below is written for patients and caregivers.

About this study

BEACON (Benchmarking AI for Clinical Oncology decisioNmaking) is a prospective, multicentre, comparative, blinded, non-interventional benchmark evaluating the treatment recommendations of five frontier large language models (LLMs) against the recommendations of multidisciplinary tumour boards (RCP) in oncology treatment planning. One hundred standardised synthetic cases (20 per localisation, across breast, lung, urological, digestive and gynaecological cancers) are submitted as identical structured input to two independent tumour boards per localisation and to five frontier LLMs. Each recommendation - human or model - is decomposed into five predefined decision domains (intent, surgery, radiotherapy, systemic therapy, work-up and biomarkers) and scored 0/1/2 for concordance against a two-tier reference: the consensus of the two tumour boards, complemented by an a priori locked guideline matrix (ESMO, NCCN). The primary endpoint is domain-level concordance between LLM and RCP consensus, expressed as a linearly weighted Cohen's kappa. A co-primary safety endpoint captures the proportion of recommendations carrying serious harm potential, because concordance alone can conceal dangerous errors. Because expert boards may disagree with one another on identical cases, model performance is always interpreted against the human consensus. BEACON is designed as reusable, openly licensed, pre-registered infrastructure: all synthetic cases, evaluation rubrics, the locked guideline matrix,…

This description comes directly from the study's public registry record.

Talk to the study team

Jean-Emmanuel Bibault, MD PhD  ·  01 56 09 34 06  ·  jean-emmanuel.bibault@aphp.fr

Jérôme Lambert, MD PhD  ·  0142499742  ·  jerome.lambert@u-paris.fr

Always discuss trial participation with your own doctor first.

Locations (1)

Hopital Européen Georges PompidouParis, FranceRecruiting

Follow this study

Get one email when the public record changes — results posted, or the study's status changes. Nothing else, ever.

We email about this public record only. Unsubscribe anytime with one click. Never medical advice. By subscribing you agree to our Terms of Use and Privacy Policy.

Look up another condition
Look up another city
Is this your study? This page was generated automatically from the public registry record. Sponsors can claim it — free — to add branding and verified contact routing. Claim this page →