From general to specific: Tailoring large language models for real‐world medical communications
2025

Tailoring AI for Medical Communication

Commentary Evidence: moderate

Author Information

Author(s): Sun Xinti, Tang Wenjun, Huang Zigeng, Long Erping, Wan Peixing

Primary Institution: State Key Laboratory of Respiratory Health and Multimorbidity, Institute of Basic Medical Sciences, Chinese Academy of Medical Sciences and Peking Union Medical College

Hypothesis

Can large language models be effectively tailored for real-world medical communications?

Conclusion

The site-specific prompt engineering chatbot (SSPEC) significantly improves healthcare worker efficiency and reduces patient-provider conflicts.

Supporting Evidence

  • Generative AI models have shown proficiency in interpreting instructions and generating responses.
  • Medical LLMs have been developed to improve communication in healthcare settings.
  • SSPEC has improved healthcare worker efficiency and reduced patient-provider conflicts.

Takeaway

This study shows how a special AI chatbot can help doctors and nurses communicate better with patients, making healthcare smoother and less stressful.

Methodology

The study developed a site-specific prompt engineering chatbot (SSPEC) using a fine-tuned GPT-3.5 Turbo model, incorporating site-specific knowledge and iterative refinement through training and clinical trials.

Potential Biases

Over-reliance on AI could weaken essential human connections in healthcare.

Limitations

Challenges include maintaining human connection in patient interactions and ensuring AI acceptance across different age groups.

Participant Demographics

Healthcare providers in China, including doctors and nurses.

Digital Object Identifier (DOI)

10.1002/ctm2.70157

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication