What type of study is this?

This is a Quantitative Study study.

September 19, 2025Cancer Epidemiology Biomarkers & Prevention

Abstract B163: Evaluation of large language models for the translational equivalency of oncology informed consent forms from English to Spanish

View Full Paper

Ask AI

Bookmark

Authors

SKSahil KhannaMayo Clinic SSSandra Patricia Susanibar-AdaniyaUniversity of Pennsylvania XBXimena Jordan BrunoUniversity of Vermont

Discussion

Member takes

Implication

Machine-generated translations of ICFs in English to Spanish improve access for limited English proficiency patients, suggesting potential for enhanced trial enrollment.

Key Points

Machine-generated translations using DeepL Pro and ChatGPT-4o are shown to be fairly accurate for oncology informed consent forms.
The mean score for certified translations was 4.99, indicating high accuracy, while Med English-2-Spanish had the lowest accuracy at 3.32.
Interrater reliability was confirmed with a Weighted Cohen’s Kappa of 0.95, demonstrating agreement between two experienced evaluators.
Assessing translations with a 5-point Likert Scale highlighted the importance of language equivalence for ensuring patient comprehension.

Cite This Study

Khanna et al. (2025) studied this question.

synapsesocial.com/papers/68d464f131b076d99fa643b2 https://doi.org/10.1158/1538-7755.disp25-b163

View Full Paper

Ask AI

Bookmark

Implication

Machine-generated translations of ICFs in English to Spanish improve access for limited English proficiency patients, suggesting potential for enhanced trial enrollment.

Abstract B163: Evaluation of large language models for the translational equivalency of oncology informed consent forms from English to Spanish

Discussion

Member takes

Implication

Key Points

Cite This Study

Abstract B163: Evaluation of large language models for the translational equivalency of oncology informed consent forms from English to Spanish

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider