Evaluation of a Retrieval Augmented Large Language Model as a Diagnostic Copilot in Rheumatology

NCT07166692 | Completed

• 1 other identifier: 24-221-1
• Study Type: interventional
• Target: 82
• Locations: 1 country
• Sites: 1

Brief Summary

This trial evaluates whether providing physicians with access to Prof. Valmed, a clinical decision support medical product, improves identification of rheumatic diseases and formulation of differential diagnoses compared with conventional decision support.

Conditions

Diagnosis

Keywords

Clinical reasoning; Large language models; Computer-assissted diagnosis; Rheumatology

Outcome Measures

Primary Outcomes (1)

• Diagnostic accuracy of top diagnosis

  Participants in each group will make at least one disease suggestion (top diagnosis) and up to a total of a maximum of 3 suggestions. Percentage of exact matches of the top suggestion with the actual diagnosis will be analyzed

  directly (within 10 minutes) after Intervention

Secondary Outcomes (6)

• Diagnostic accuracy of top 3 suggestions

  directly (within 10 minutes) after Intervention

• Diagnostic confidence

  directly (within 10 minutes) after Intervention

• Time spent for diagnosis

  directly (within 10 minutes) after Intervention

• Perceived Information Timeliness

  directly (within 10 minutes) after Intervention

• Perceived diagnostic support quality

  directly (within 10 minutes) after Intervention

Study Arms (2)

Prof. Valmed

EXPERIMENTAL

Group will be given access to Prof. Valmed.

Other: Prof. Valmed

Control group

NO INTERVENTION

Group will not be given access to Prof. Valmed but will be encouraged to use any resources they wish besides large language models (UpToDate, etc).

Interventions

Prof. Valmed OTHER

Prof Valmed. decision support system.

Prof. Valmed

Eligibility Criteria

• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)

You may qualify if:

• Participants must be licensed physicians.
• Training in rheumatology, internal medicine, emergency medicine, family medicine, dermatology or orthopedics.

You may not qualify if:

• Not currently practicing clinically.

Sponsors & Collaborators

• Philipps University Marburg: lead
• University Medical Center Hamburg-Eppendorf (UKE): collaborator
• Oslo University Hospital: collaborator
• Diakonhjemmet Hospital: collaborator
• University Hospital Erlangen: collaborator
• Charite University, Berlin, Germany: collaborator
• Rheumazentrum Ruhrgebiet: collaborator
• University of Lausanne Hospitals: collaborator
• Klinikum Fulda: collaborator

Study Sites (1)

Institute for Digital Medicine, University Hospital of Giessen and Marburg, Philipps University Marburg

Marburg, 35043, Germany

Location

MeSH Terms

Conditions

Disease

Condition Hierarchy (Ancestors)

Pathologic Processes; Pathological Conditions, Signs and Symptoms

Study Officials

• Johannes Knitza, MD PhD

  University Marburg

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: SINGLE
• Who Masked: OUTCOMES ASSESSOR
• Masking Details: The evaluation of responses will be performed by assessors blinded to participant identity and treatment assignment.
• Purpose: DIAGNOSTIC
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: August 25, 2025
• First Posted: September 10, 2025
• Study Start: October 12, 2025
• Primary Completion: February 1, 2026
• Study Completion: February 1, 2026
• Last Updated: April 8, 2026

Record last verified: 2026-04

Data Sharing

• IPD Sharing: Will not share

Locations

DE (1)