What type of study is this?

This is a Experimental Study study.

October 3, 2025Open Access

Comparing Large Language Models and Traditional Machine Translation Tools for Translating Medical Consultation Summaries – A Pilot Feasibility Study (Preprint)

View Full Paper

Ask AI

Bookmark

Authors

ALAndy LiMonash University WZWei ZhouSun Yat-sen University RHRashina HodaAustralian Regenerative Medicine Institute

Discussion

Member takes

Implication

Pilot study assesses translation performance of large language models and traditional MT tools for medical summaries, suggesting the need for human oversight.

Key Points

Translation performance varied by language and tool, with traditional MT tools generally outperforming LLMs in surface-level metrics.
Semantic similarity was notably better in LLMs for Vietnamese and Chinese, indicating strengths in specific languages for complex summaries.
Use of established benchmarks like BLEU, CHR-F, and METEOR highlighted both the feasibility of AI translation and associated risks in clinical contexts.
Importance of human oversight and domain-specific evaluations was emphasized to promote safe use of AI translation tools in healthcare.

Cite This Study

Li et al. (2025) studied this question.

synapsesocial.com/papers/68e02f34f0e39f13e7fa226d https://doi.org/10.2196/preprints.85169

View Full Paper

Ask AI

Bookmark

Implication

Pilot study assesses translation performance of large language models and traditional MT tools for medical summaries, suggesting the need for human oversight.

Comparing Large Language Models and Traditional Machine Translation Tools for Translating Medical Consultation Summaries – A Pilot Feasibility Study (Preprint)

Discussion

Member takes

Implication

Key Points

Cite This Study

Comparing Large Language Models and Traditional Machine Translation Tools for Translating Medical Consultation Summaries – A Pilot Feasibility Study (Preprint)

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider