Large Language Models to Aid Gynecological Oncology Treatment
ConditionBreast Cancer
Trial statusRecruiting
Trial phaseNot applicable
Trial typeInterventional
Biological sexAll
Age18+
SponsorPhilipps University Marburg
About this trial
This trial aims to assess the impact of providing medical students with access to large language models, in comparison to treatment guideline pdfs, on treatment concordance with a conventional multidisciplinary tumor board
Eligibility criteria
This trial accepts healthy volunteersQualifiers
None
Disqualifiers
None
Trial design
Design model
Crossover
Treatments tested in this trial
Local language model
Other interventionGroup will be given access to local language model first after using ChatGPT and then will get access to pdf file
Guideline pdf
Other interventionGroup will be given access to pdf file after ChatGPT and then to a local language model
Treatment groups
68 Participants
are divided into 2 treatment groupsGroup A: Local language model firstOther 1 intervention
Group B: Guideline pdf firstOther 1 intervention
Trial outcomes
Primary outcomes
1
Treatment concordance with tumor board decisions
Participants in each group select treatment modalities for case vignettes
Time frame
directly (within 10 minutes) after InterventionSecondary outcomes
1
Treatment confidence
For each case participants will be asked for their treatment confidence (VAS 0-10). The mean score will be compared between decision support groups.
Time frame
directly (within 10 minutes) after Intervention2
Time spent for treatment decision
Time (in seconds) participants spend per case between the decision support groups will be compared.
Time frame
directly (within 10 minutes) after InterventionSponsors and contacts
Click on the lead sponsor to view all of their trials.
Source ClinicalTrials.gov