Comparative Evaluation of ChatGPT, Google Translate, and UD Talk for Chinese-to-Japanese Translation in Cardiology and Pulmonology Outpatient Consultations: Prospective Observational Study - Report - MDSpire

Comparative Evaluation of ChatGPT, Google Translate, and UD Talk for Chinese-to-Japanese Translation in Cardiology and Pulmonology Outpatient Consultations: Prospective Observational Study

  • By

  • Ke-Yun Chao

  • Chia-Hui Huang

  • Wei-Lun Liu

  • Chao-Yu Chen

  • Ai Yin Lim

  • Yi-Zhen Chu

  • Atsuko Sasaoka

  • Chung-Yu Lin

  • June 18, 2026

  • 0 min

Share

Clinical Report: Assessment of ChatGPT, Google Translate, and UD Talk

Overview

This study evaluates the translation accuracy of ChatGPT, Google Translate, and UD Talk in outpatient cardiology and pulmonology consultations from Chinese to Japanese.

Background

Language barriers in healthcare can significantly impact patient outcomes and access to care. Effective communication is crucial for providing equitable health services, particularly for patients with limited proficiency in the dominant language.

Data Highlights

No numerical data provided in the source material.

Key Findings

  • ChatGPT, Google Translate, and UD Talk were compared for their translation accuracy in medical consultations.
  • Machine translation tools have varying levels of accuracy and fluency.
  • Professional interpreters provide more reliable translations than machine translation tools.
  • Language barriers can lead to poorer health outcomes for patients with limited language proficiency.
  • AI advancements in translation require careful evaluation for clinical use.

Clinical Implications

Healthcare providers should be aware of the limitations of machine translation tools.

Conclusion

Further research is needed to optimize the use of AI in clinical translation.

Related Resources & Content

  1. International Medical Interpreters Association, Source, Year -- Interpreter's Role
  2. HHS, Language Access Provisions of the Final Rule Implementing Section 1557 of the Affordable Care Act, 2024 -- Language Access Requirements
  3. WHO, WHO releases AI ethics and governance guidance for large multi-modal models, 2024 -- AI in Health Communication
  4. npj Digital Medicine — Evaluating human-in-the-loop strategies for artificial intelligence-enabled translation of patient discharge instructions: a multidisciplinary analysis
  5. The Journal of Clinical Endocrinology & Metabolism — Evaluating Responses to Thyroid-Related Inquiries: A Comparison Between ChatGPT and Surgeons
  6. European Radiology — Evaluation of Diagnostic Accuracy of GPT-4-Driven ChatGPT Compared to Radiologists Analyzing Real-World Brain Tumor Radiology Reports
  7. Frontiers in Cardiovascular Medicine — Retrospective comparison of ChatGPT-4 treatment recommendations with real-world physician management in newly diagnosed hypertension: a single-centre study
  8. Evaluating human-in-the-loop strategies for AI-enabled translation
  9. Evaluating Responses to Thyroid-Related Inquiries: A Comparison Between ChatGPT and Surgeons
  10. Evaluation of Diagnostic Accuracy of GPT-4-Driven ChatGPT Compared to Radiologists
  11. Language Access Provisions of the Final Rule Implementing Section 1557 of the Affordable Care Act
  12. Language Access and Interpreter Services – Understanding The Requirements | Joint Commission
  13. WHO releases AI ethics and governance guidance for large multi-modal models
  14. Evaluating LingualAI: a prospective validation of AI-based real-time translation against certified human interpreters | npj Health Systems
  15. Accuracy of Artificial Intelligence vs Professionally Translated Discharge Instructions | Equity, Diversity, and Inclusion | JAMA Network Open | JAMA Network
  16. Evaluation of the accuracy and safety of machine translation of patient-specific discharge instructions: a comparative analysis | BMJ Quality & Safety
  17. Artificial intelligence in clinical settings: a systematic review of its role in language translation and interpretation - PMC
  18. Interpretation Performance in Chinese and Japanese Medical Consultation Scenarios | MedPath

Original Source(s)

Comparative Evaluation of ChatGPT, Google Translate, and UD Talk for Chinese-to-Japanese Translation in Cardiology and Pulmonology Outpatient Consultations: Prospective Observational Study

  • by Ke-Yun Chao, Chia-Hui Huang, Wei-Lun Liu, Chao-Yu Chen, Ai Yin Lim, Yi-Zhen Chu, Atsuko Sasaoka, Chung-Yu Lin

  • June 18, 2026

Related Content

Exploring unmet needs in patient engagement among cardiovascular disease patients: qualitative research in Italy

Association of LVOT Gradient and LA Strain with Cardiac Events in Pediatric HCM

Association between region-specific epicardial adipose tissue and CT-derived fractional flow reserve-defined myocardial ischemia: a retrospective coronary CTA study stratified by hypertension and type 2 diabetes mellitus