Using an Artificial Intelligence (AI) Tool (ChatGPT) to Identify the Main Indications and Side Effects of Drugs

Document Type

Conference Proceeding

Publication Date

4-2024

Publication Title

Academic Pathology

Abstract

Objectives: Drug history is an important clinical information for the correct histological diagnosis of a wide variety of non-neoplastic diseases, such as hepatitis, gastritis, and colitis. As pathologists, however, memorizing the side effects of many drugs can be challenging. Using online databases to find relevant drug information one at a can be time-consuming too. Methods: ChatGPT (Generative Pre-trained Transformer) is an artificial intelligence-powered language model developed by OpenAI, that has the ability to generate human-like text based on current and past conversations, was instructed to identify the main clinical indications and the major side effects of 160 frequently prescribed drugs. This was done using the prompt: [List the major indications and side effects of the following drugs: "cyclobenzaprine,...".]. We then had a list of 160 drugs with their main indications and side effects. We compared the results from ChatGPT with those listed in the UpToDate drug information section. Results: ChatGPT responded within few seconds by listing the required information (indications and side effects) for 160 drugs, 25 drugs at a time. On the other hand, we could only get the same information via UpToDate one drug at a time, and it took hours to obtain the same information. Most of the indications and side effects were similar to those found on UpToDate (Table 1). Conclusions: Utilizing ChatGPT by pathologists is not only a fast and efficient way to obtain relevant information on multiple drugs simultaneously, but it also has comparable efficacy to well-known medical drug websites. We also believe that another professional drug website should be used as a confirmatory reference. worth to mention that some institutions may block the access to the AI websites on their domain. I presented this topic at the CAP meeting in Chicago October, 9th, 2023. It was a poster presentation under "Informatics"

Volume

11

Issue

2 Suppl

First Page

5

Comments

Association for Academic Pathology Annual Meeting, July 21-24, 2024, Washington, DC

DOI

10.1016/j.acpath.2024.100137

Link to Full Text

Share

COinS