Analysis of responses from artificial intelligence programs to medication-related questions derived from critical care guidelines
Abstract
PURPOSE: To evaluate the recommendations given by 4 publicly available artificial intelligence (AI) programs in comparison to recommendations in current clinical practice guidelines (CPGs) focused on critically ill adults. METHODS: This study evaluated 4 publicly available large language models (LLMs): ChatGPT 4.0, Microsoft Copilot, Google Gemini Version 1.5, and Meta AI. Each AI chatbot was prompted with medication-related questions related to 6 CPGs published by the Society of Critical Care Medicine (SCCM) and also asked to provide references to support its recommendations. Responses were categorized as correct, partially correct, not correct, or "other" (eg, the LLM answered a question not asked). RESULTS: In total, 43 responses were recorded for each AI program, with a significant difference (P = 0.007) in response types by AI program. Microsoft Copilot had the highest proportion of correct recommendations, followed by Meta AI, ChatGPT 4.0, and Google Gemini. All 4 LLMs gave some incorrect recommendations, with Gemini having the most incorrect responses, followed closely by ChatGPT. Copilot had the most responses in the "other" category (n = 5, 11.63%). On average, ChatGPT provided the greatest number of references per question (n = 4.54), followed by Google Gemini (n = 3.43), Meta AI (n = 3.06), and Microsoft Copilot (n = 2.04). CONCLUSION: Although they showed potential for future utility to pharmacists with further development and refinement, the evaluated AI programs did not consistently give accurate medication-related recommendations for the purpose of answering clinical questions such as those pertaining to critical care CPGs.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Prompt-session handling and parameter settings can influence the quality and consistency of LLM responses.
“as prompt-session handling and parameter settings can influence the quality and consistency of LLM responses.57,82,98”
From Large Language Models in Pharmacist-Led Direct Patient Care: A Rapid Review of Published Evaluations (2026) · cites this paper as [82]
Cites
Clinical guidelines: Potential benefits, limitations, and harms of clinical guidelines
Woolf, S. H., Grol, R. P. T. M., Hutchinson, A., Eccles, M., & Grimshaw, J. (1999) · BMJ · doi:10.1136/bmj.318.7182.527 · Cited by 2,549 · see citing works
Xu, L., Sanders, L., Li, K., & Chow, J. C. L. (2021) · JMIR Cancer · doi:10.2196/27850 · Cited by 571 · see citing works
Evaluating the Performance of ChatGPT in Ophthalmology
Antaki, F., Touma, S., Milad, D., El-Khoury, J., & Duval, R. (2023) · Ophthalmology Science · doi:10.1016/j.xops.2023.100324 · Cited by 563 · see citing works
Accuracy and Reliability of Chatbot Responses to Physician Questions
Goodman, R. S., Patrinely, J. R., Stone, C. A., Zimmerman, E., Donald, R. R., Chang, S. S., Berkowitz, S. T., Finn, A. P., Jahangir, E., Scoville, E. A., et al. (2023) · JAMA Network Open · doi:10.1001/jamanetworkopen.2023.36483 · Cited by 484 · see citing works
Guide to clinical practice guidelines: the current state of play
Kredo, T., Bernhardsson, S., Machingaidze, S., Young, T., Louw, Q. A., Ochodo, E., & Grimmer, K. A. (2016) · International Journal for Quality in Health Care · doi:10.1093/intqhc/mzv115 · Cited by 458 · see citing works
Hassani, H., & Silva, E. S. (2023) · Big Data and Cognitive Computing · doi:10.3390/bdcc7020062 · Cited by 401 · see citing works
Honarmand, K., Sirimaturos, M., Hirshberg, E. L., Bircher, N. G., Agus, M. S. D., Carpenter, D. L., Downs, C. R., Farrington, E. A., Freire, A. X., Grow, A., et al. (2024) · Critical Care Medicine · doi:10.1097/ccm.0000000000006174 · Cited by 169 · see citing works
Sallam, M., Barakat, M. M., & Sallam, M. (2023) · Cureus · doi:10.7759/cureus.49373 · Cited by 80 · see citing works
Evaluation of inpatient medication guidance from an artificial intelligence chatbot
Beavers, J. R., Schell, R. F., VanCleave, H. Z., Dillon, R. C., Simmons, A., Chen, H., Chen, Q., Anders, S. H., Weinger, M. B., & Nelson, S. D. (2023) · American Journal of Health-System Pharmacy · doi:10.1093/ajhp/zxad193 · Cited by 23 · see citing works
Dixon, D. L., Harris, I. M., Aljadeed, R., Anderson, K. C., Aycock, A., Beavers, C. J., Beckman, E. J., Isaacs, D. M., McCoy, E., Sandler, A., et al. (2022) · JACCP JOURNAL OF THE AMERICAN COLLEGE OF CLINICAL PHARMACY · doi:10.1002/jac5.1743 · Cited by 7 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Large Language Models in Pharmacist-Led Direct Patient Care: A Rapid Review of Published Evaluations
Yakob, R. A., Bamgboje-Ayodele, A., Collins, J. C., & Aslani, P. (2026) · Research in Social and Administrative Pharmacy · doi:10.1016/j.sapharm.2026.09.007
- Authors
- Williams, B., & Erstad, B. L.
- Affiliations
- University of Arizona (US)
- Corresponding author
- Erstad, Brian L
- ORCID
- Erstad, Brian L
- Venue
- American Journal of Health-System Pharmacy
- Publisher
- Oxford University Press (OUP)
- Published
- 2025-03-22
- Volume
- 82
- Issue
- 19
- Pages
- e842-e847
- ISSN
- 1079-2082 (ISSN-L)
- 1535-2900
- OpenAlex
- W4408763544
- Cited by
- 13
- References
- 10
- Citations by year
- 2026: 8 · 2025: 5
- FWCI
- 3.10
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- American Journal of Health-System Pharmacy (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Health Professions › Health Information Management › Electronic Health Records Systems
- Health Sciences › Medicine › Public Health, Environmental and Occupational Health › Clinical practice guidelines implementation
- Keywords
- large language models, artificial intelligence, intensive care, drug recommendation, ChatGPT, Microsoft Copilot, Google Gemini, Meta AI, AI accuracy, pharmacists, medical question answering
- MeSH terms
- Artificial Intelligence, Critical Care, Humans, Practice Guidelines as Topic
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
