Skip to content

Large Language Models for Tumor Board Decision Making

Large Language Models for Tumor Board Decision Making

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
DRKS
Registry ID
DRKS00039200
Enrollment
50
Registered
2026-02-12
Start date
2026-02-23
Completion date
Unknown
Last updated
2026-03-02

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

C34

Interventions

Group 1: Retrospective analysis of therapeutic agreement between computer-generated suggestions and multidisciplinary tumor board decisions in patients from 2021 to 2026

Sponsors

Universitätsmedizin Essen
Lead Sponsor

Eligibility

Sex/Gender
All
Age
18 Years to No maximum

Inclusion criteria

Inclusion criteria: Data analysis of patients who were in treatment between 2021 and 2026

Exclusion criteria

Exclusion criteria: Exclusion of all cases without a full board decision, without sufficient imaging findings, or with incomplete documentation of the relevant routine data.

Design outcomes

Primary

MeasureTime frame
Rate of complete therapeutic agreement between the treatment recommendations generated by the Large Language Model (LLM) and the decisions of the interdisciplinary tumor board, determined retrospectively and once after completion of data collection and anonymization by blind comparison (percentage + Cohen’s Kappa).

Secondary

MeasureTime frame
Agreement rate in the indication for interventional therapy procedures (yes/no) as well as type and direction of discordances (aggressive/conservative/other modality), determined retrospectively once after completion of data collection by blinded expert comparison and standardized categorization.

Countries

Germany

Contacts

Public ContactMax Eberts

Universitätsmedizin Essen

max.eberts@uk-essen.de0049 201 723 82846

Outcome results

None listed

Source: DRKS (via WHO ICTRP) · Data processed: Mar 14, 2026