Large Language Models for Supporting Clear Writing and Detecting Spin in Randomized Controlled Trials in Oncology: Comparative Analysis of GPT Models and Prompts
LLMs can effectively detect potential spin in oncology RCT reporting by identifying discrepancies between how trials are presented in the conclusions vs the full abstracts. This approach could serve as a supplementary tool for improving transparency in scientific reporting, although further development is needed to address more complex trial designs beyond those examined in this feasibility study.
Authors
- Fabio Dennstädt (ORCID: https://orcid.org/0000-0002-5374-8720)
- Carole Koechli (ORCID: https://orcid.org/0000-0001-9448-0786)
- Christina Schröder (ORCID: https://orcid.org/0000-0002-4168-2795)
- Paul Windisch (ORCID: https://orcid.org/0000-0003-1040-4888)
- Daniel M. Aebersold (ORCID: https://orcid.org/0000-0002-9493-3834)
- Robert Förster
- Daniel Rudolf Zwahlen
Institutions
- University of Bern (CH)
- University Hospital of Bern (CH)
- Kantonsspital Winterthur (CH)
Publication Details
- Journal
- JMIR Cancer
- Published
- 2026-01-21
- DOI
- https://doi.org/10.2196/78221
- Citations
- 2
- Primary Topic
- Meta-analysis and systematic reviews
- Type
- article
- Field-Weighted Citation Impact
- 56.17