Hostname: page-component-6898cfcb55-zsp5v Total loading time: 0 Render date: 2026-11-11T11:07:12.475Z Has data issue: false hasContentIssue false

All aboard the ChatGPT steamroller: Top 10 ways to make artificial intelligence work for healthcare professionals

Published online by Cambridge University Press:  18 December 2023

Lemuel R. Non*
Affiliation:
Division of Infectious Diseases, Department of Medicine, University of Iowa Hospitals and Clinics, Iowa City, IA, USA

Abstract

Chat Generative Pre-trained Transformer (ChatGPT), the flagship generative artificial intelligence (AI) chatbot by OpenAI, is transforming many things in medicine, from healthcare and research to medical education. It is anticipated to integrate in many aspects of the medical industry, and we should brace for this inevitability and use it to our advantage. Here are proposed ways you can use ChatGPT in medicine with some specific use cases in antimicrobial stewardship and hospital epidemiology.

Information

Type
Commentary
Creative Commons
Creative Common License - CCCreative Common License - BY
This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted re-use, distribution and reproduction, provided the original article is properly cited.
Copyright
© The Author(s), 2023. Published by Cambridge University Press on behalf of The Society for Healthcare Epidemiology of America
Figure 0

Table 1.Sample prompts for ChatGPT

Figure 1

Figure 1.ChatGPT output showing well-formatted bulleted points about vancomycin resistance in Enterococci with suggestions regarding additional visuals and design.

Figure 2

Figure 2.A cartoon showing a bacterium developing antibiotic resistance generated by ChatGPT-4.

Figure 3

Figure 3.Simple prompt for asking ChatGPT-4 to perform χ2 analysis on an uploaded data set with output.

Figure 4

Figure 4.Bar graph output of the same data set used in χ2 analysis after asking ChatGPT-4 to “visualize” data.