Abstract
This paper examines AI-assisted translation of ophthalmic optometry texts through a qualitative case-based analysis. Ophthalmic optometry represents a particularly demanding translation domain, combining clinical medicine, optics, diagnostic imaging, and device-related terminology in ways that require not only linguistic fluency but also disciplinary familiarity and genre awareness. Five representative English source segments were compared across AI-generated drafts and human post-edited versions, evaluated along three dimensions: terminology accuracy, semantic accuracy, and professional adequacy. Findings show that while AI performs adequately in generating initial drafts and preserving broad semantic content, it consistently falls short in disciplinary terminology, clinical register, and target-language naturalness. Typical errors include nonstandard term choices, overly literal structural transfers, and register mismatches that render outputs readable but professionally suboptimal. Human post-editing effectively addresses these weaknesses and remains essential for professional quality assurance. The paper concludes that the optimal model is disciplined human–AI collaboration: AI contributes speed and baseline drafting, while the human translator serves as terminological gatekeeper, semantic verifier, and register-sensitive editor. Rather than replacing specialist judgment, AI reshapes the translator’s role toward evaluation and decision-making. These findings align with broader healthcare AI research emphasizing human oversight, evaluation frameworks, and risk awareness rather than uncritical automation.
References
Algaraady, J., & Mahyoob, M. (2025). Exploring ChatGPT’s potential for augmenting post-editing in machine translation across multiple domains: Challenges and opportunities. Frontiers in Artificial Intelligence, 8, 1526293.
Biro, J. M., et al. (2025). Evaluating human-in-the-loop strategies for artificial intelligence-enabled translation of patient discharge instructions: A multidisciplinary analysis. npj Digital Medicine.
Chatzikoumi, E. (2020). How to evaluate machine translation: A review of automated and human metrics. Natural Language Engineering, 26(2), 137-161.
Herrera-Espejel, P. S., & Rach, S. (2023). The use of machine translation for outreach and health communication in epidemiology and public health: Scoping review. JMIR Public Health and Surveillance, 9, e50814.
Läubli, S., Sennrich, R., & Volk, M. (2018). Has machine translation achieved human parity? A critical look at the ACL 2018 shared task. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (pp. 3820-3823). Association for Computational Linguistics.
Lopez, I., et al. (2025). Operationalizing machine-assisted translation in healthcare. npj Digital Medicine, 8, 584.
Noll, R., Bastian, L., Bubenzer, J., Boeker, M., & Schulz, S. (2025). Assessing GPT and DeepL for terminology translation in the medical domain: A comparative study on the Human Phenotype Ontology. BMC Medical Informatics and Decision Making, 25, Article 30.
Reddy, S. (2023). Evaluating large language models for use in healthcare: A framework for translational value assessment. Informatics in Medicine Unlocked, 41, 101304.
How to cite this paper
AI-assisted Translation of Ophthalmic Optometry Texts: A Case-based Analysis
How to cite this paper: Fangzhou Jiang. (2026) AI-assisted Translation of Ophthalmic Optometry Texts: A Case-based Analysis. Journal of Humanities, Arts and Social Science, 10(4), 482-486.
DOI: http://dx.doi.org/10.26855/jhass.2026.04.014