Commentary

Artificial intelligence in clinical practice: A look at ChatGPT

Jiawen Deng, MS-2, Kiyan Heybati, MS-3, MSc(c), Ye-Jean Park, MS-2, Fangwen Zhou, MSc(c) and Anthony Bozzo, MD, MSc, FRCSC
Cleveland Clinic Journal of Medicine March 2024, 91 (3) 173-180; DOI: https://doi.org/10.3949/ccjm.91a.23070

Article Figures & Data

Figures

  • Figure 1
    Figure 1

    (A) Training and (B) output-generation processes of typical general-purpose large language models (LLMs) like ChatGPT.

  • Figure 2
    Figure 2

    Common technical limitations of current general-purpose large language models (LLMs) like ChatGPT include (A) hallucinations, (B) lack of transparency, (C) biases in training data, and (D) randomness. Prompts and responses shown are for illustrative purposes only and do not represent actual output from LLMs.

Tables

Back to top

In this issue

Print
Download PDF
Article Alerts
Email Article
Citation Tools

Jump to section

Subjects