Den här översättningen är inte klar ännu. Den här sidan är just nu på engelska.

Gå till den engelska sidan

Cure My Disease

Don't miss your cure!

 Log in / Sign up

Can AI outthink cancer experts? a landmark trial pits five AIs against tumor boards

NCT ID NCT07739121

Knowledge-focused Sponsor: Assistance Publique - Hôpitaux de Paris Source: ClinicalTrials.gov ↗

What the study statuses mean

This study's is highlighted.

Recruitment status, easiest to join first

Recruiting now This study
This trial is taking on new participants right now.
Not yet recruiting
Registered, but not yet taking participants.
By invitation only
Not open to general applications. Only people the study team invites can take part.
Paused
Paused for now. It may or may not start again.
Ongoing
Running, but no longer taking on new participants.
Completed
The trial has finished. Results may not be published yet.
Stopped early
Stopped early, before it reached the end. That can be for many reasons, including safety.
Cancelled
Cancelled before anyone took part.

Expanded access (not trials)

Expanded access
Not a trial. This treatment can be requested outside a study, case by case, for people who qualify.
Expanded access (paused)
Not a trial. The treatment can normally be requested outside a study, but is unavailable right now.
Expanded access (ended)
Not a trial. The treatment could once be requested outside a study, but no longer can.
Approved
The treatment has been approved, so it is available normally rather than through this programme.

When the status isn't known

Details not published
The full record has not been published yet, so there is little to show here.
Status unknown
This status has not been confirmed recently, so it may be out of date.

First seen Jul 31, 2026 · Last updated Jul 31, 2026

Summary

This trial asks whether five advanced AI models can match the treatment recommendations of expert tumor boards for cancer patients. Using 100 standardized synthetic cases across breast, lung, urological, digestive, and gynecological cancers, each AI and two independent tumor boards provide treatment plans. The plans are scored for agreement with established guidelines and for potential harm. The goal is to see if AI can reliably support cancer treatment decisions, not to replace human experts.

What this could mean

Our plain-language read of the trial. This is informational only, not medical advice or a prediction.

Active substance
Frontier large language models (AI) compared with multidisciplinary tumour board recommendations
What this could lead to
If AI matches expert tumor boards, it could support doctors in making consistent, guideline-based cancer treatment decisions, potentially improving care quality and accessibility.
What could go wrong
This is a non-interventional benchmark using synthetic cases, not real patients. AI may still make dangerous errors, and results may not reflect real-world clinical practice.

This is an AI summary of the original study and may miss details. Read our disclaimer.

Study facts

What this study's own registry entry says, in plain language.

Participants

About 100 people

The number the study aims to enrol. It can still change while the study runs.

Started

May 2026

Expected to finish

Oct 2026

An estimate. End dates often move.

Lead sponsor

Other sponsor

The registry's catch-all category, for sponsors it does not file as a company, a government agency, or a research network.

Who can take part

This study's own entry requirements. Only the study team can say for certain whether you qualify.

Who is studied

100 synthetic oncology treatment-planning cases (20 per localisation) across five localisations: breast, lung, urological (prostate, bladder / upper-tract urothelial, kidney), digestive and gynaecological. Each case is a structured JSON input specifying UICC 8th-edition stage, biomarkers, ECOG performance status, comorbidities and a standardised clinical question. No human participants, no patient data and no identifiable individuals. Recommendations are produced by two independent tumour boards per localisation and by five frontier LLMs (queried May 2026).

Ages

18 years and older

Sex

Anyone

Healthy volunteers

Not accepted

This study is not open to healthy volunteers. The entry requirements below say who it is open to.

Show the full entry requirements

Copied word for word from the study's registry entry, so the wording is the study team's rather than ours.

Inclusion Criteria: * Synthetic oncology case within one of the five predefined localisations (breast, lung, urological, digestive, gynaecological). * Complete structured schema: UICC 8th-edition stage, biomarkers, ECOG performance status, comorbidities and a standardised clinical question. * A clinically answerable treatment-planning question that is mappable to the locked guideline matrix. Exclusion Criteria: * Case outside the five predefined localisations. * Incomplete, internally inconsistent or ambiguous schema. * Duplicate or near-duplicate of an existing case in the set. * Question not resolvable by current guidelines.

Get updates

Get notified about this study

Sign up to get updates when this study changes or when new studies for Artifical intelligence are added.

Vår säkerhetsrekommendation!

Genom att skicka in godkänner du våra Användarvillkor

Conditions

The condition(s) this trial relates to.

benign urinary system neoplasm breast cancer breast neoplasm digestive system cancer digestive system neoplasm Digestive System Neoplasms female reproductive organ cancer kidney cancer kidney neoplasm lung cancer lung neoplasm malignant urinary system neoplasm neoplasm prostate cancer prostate neoplasm urinary bladder neoplasm Urinary Bladder Neoplasms urinary system neoplasm

As listed by the trial registrant

The condition terms exactly as the trial's registrant entered them.

Artifical intelligence Breast neoplasms Decision making Decision support systems, clinical Digestive system neoplasms Genital neoplasms Kidney neoplasms Large language models Lung neoplasms Prostatic neoplasms Urinary bladder neoplasms Urologic neoplasms

How to take part

Only the study team decides who joins. These are the ways to reach them.

  1. The places running it

    1 site. The list below names each one and where it is.

  2. The official record

    ClinicalTrials.gov lists the study team's own contact details, including names and phone numbers. We don't republish those.

    Open the record ↗

  3. A doctor treating you

    A doctor who knows your case can contact a study site on your behalf, and can tell you whether this study is worth pursuing at all.

Contacts and locations

Locations

  • Hopital Européen Georges Pompidou

    RECRUITING

    Paris, France

More trials for these conditions

Other studies related to the condition(s) this trial covers.