loading page

Performance of the ChatGPT Large Language Model for Decision Support in Community Pharmacy
  • Euibeom Shin,
  • Maggie Hartman,
  • Murali Ramanathan
Euibeom Shin
University at Buffalo
Author Profile
Maggie Hartman
University at Buffalo
Author Profile
Murali Ramanathan
University at Buffalo

Corresponding Author:murali@buffalo.edu

Author Profile

Abstract

Purpose: To assess the ChatGPT-4 (ChatGPT) large language model (LLM) on tasks relevant to community pharmacy. Methods: ChatGPT was assessed with community pharmacy-relevant test cases involving drug information retrieval, identifying labeling errors, prescription interpretation, decision making under uncertainty and multi-disciplinary consults. Drug information on rituximab, warfarin, and St. John’s wort was queried. The decision-support scenarios consisted of a subject with swollen eyelids, and a maculopapular rash in a subject on lisinopril and ferrous sulfate. The multi-disciplinary scenarios required integration of medication management with nutrition and physical therapy. Results: The responses from ChatGPT-4 for rituximab, warfarin, and St. John’s wort were satisfactory and cited drug databases and drug-specific monographs. ChatGPT identified labeling errors related to incorrect medication strength, form, administration route, unit conversion, and directions. For the patient with inflamed eyelids, the course of action developed by GPT-4 was comparable to the pharmacist’s approach. For the patient with the maculopapular rash, both the pharmacist and ChatGPT placed a drug reaction to either lisinopril or ferrous sulfate at the top of the differential. ChatGPT provided customized vaccination requirements for travel to Brazil, guidance on management of drug allergies, and recovery from a knee injury. ChatGPT provided satisfactory medication management and wellness information for a diabetic on metformin and semaglutide. Conclusions: LLMs have the potential to become a powerful tool in community pharmacy. However, testing in validation studies across diverse pharmacist queries, drug classes, and populations, and engineering to secure patient privacy will be needed to enhance LLM utility.
08 May 2024Submitted to British Journal of Clinical Pharmacology
09 May 2024Submission Checks Completed
09 May 2024Assigned to Editor
22 Jun 2024Review(s) Completed, Editorial Evaluation Pending
26 Jun 2024Editorial Decision: Revise Major
24 Jul 20241st Revision Received
26 Jul 2024Submission Checks Completed
26 Jul 2024Assigned to Editor
26 Jul 2024Review(s) Completed, Editorial Evaluation Pending
01 Aug 2024Editorial Decision: Accept