Large Language Models for Supporting Clear Writing and Detecting Spin in Randomized Controlled Trials in Oncology: Comparative Analysis of GPT Models and Prompts.

Carole Koechli; Fabio Dennstädt; Christina Schröder; Daniel M. Aebersold; Robert Förster; Daniel Rudolf Zwahlen; Paul Windisch

doi:10.2196/78221

January 21, 2026Open Access

Large Language Models for Supporting Clear Writing and Detecting Spin in Randomized Controlled Trials in Oncology: Comparative Analysis of GPT Models and Prompts.

View Full Paper

Ask AI

Bookmark

Share

Key Points

The research aims to explore the ability of large language models to detect spin in oncology randomized controlled trials.
Employed large language models to analyze trial reporting language.
Compared conclusions with full abstracts to identify discrepancies.
Conducted a feasibility study on recognized trials.
Large language models effectively identified potential spin in trial reports.
Noted discrepancies are significant in enhancing transparency.
Recommendations indicate the need for further development to handle complex trials.

Ask about this paper

Answers are grounded in this paper and cite their sources.

Implication

Comparative analysis examines how large language models improve transparency in oncology randomized controlled trials, suggesting further development is needed.

Abstract

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.

Large Language Models for Supporting Clear Writing and Detecting Spin in Randomized Controlled Trials in Oncology: Comparative Analysis of GPT Models and Prompts.

Key Points

Ask about this paper

Implication

Abstract

Discussion

Cite This Study

Large Language Models for Supporting Clear Writing and Detecting Spin in Randomized Controlled Trials in Oncology: Comparative Analysis of GPT Models and Prompts.

Key Points

Ask about this paper

Implication

Abstract

Discussion

Cite This Study

Keep reading

Keep reading