Objective:

To systematically map the intellectual landscape and trace the research trajectory of large language models (LLMs) in diagnostic medicine through bibliometric analysis, highlighting the significance of this emerging field.

Approach:

Key Findings:

• LLM-assisted diagnostic research has gained significant scholarly attention since the release of ChatGPT in late 2022, with over X publications in the first year.
• The literature on LLMs in diagnostics has expanded across multiple clinical specialties, including X, Y, and Z.
• Surveys indicate a high percentage of psychiatrists using LLMs like ChatGPT in their diagnostic processes, with X% reporting regular use.
• Preliminary findings suggest potential clinical utility of LLM-assisted diagnostic tools in specific settings, with accuracy rates of X%.

Interpretation:

The integration of LLMs into clinical practice is growing, but ethical, legal, and practical challenges remain, including concerns about data privacy and model reliability, which could hinder widespread adoption.

Limitations:

• The study does not provide direct guidance for the design or validation of LLM-assisted diagnostic tools, which may limit practical application.
• The bibliometric analysis is trend-based and may not capture all nuances of the field, potentially overlooking emerging areas of research.

Conclusion:

A comprehensive synthesis of the existing literature on LLMs in diagnostic medicine is essential for understanding their potential and challenges, and future research should focus on addressing the identified limitations.

Attribution Notice

This content is an AI-generated, fully rewritten summary based on a published scholarly article. It does not reproduce the original text and is not a substitute for the original publication. Readers are encouraged to consult the source for full context, data, and methodology.