User Beware: Inaccuracy and Inconsistency of Large Language Models in Providing Precision Dosing Recommendations for Patients With Kidney Impairment—A Case Series
Pharmacotherapy: The Journal of Human Pharmacology and Drug Therapy · 2026
DOI: 10.1002/phar.70207 ↗Kurz gefasst
Evaluationsstudie in der Zeitschrift Pharmacotherapy: The Journal of Human Pharmacology and Drug Therapy, 2026. Verfasst von H Rhodes Hambrick und 5 weiteren Autor:innen. Beteiligte Einrichtung: Division of Nephrology, Ann & Robert H. Lurie Children's Hospital of Chicago, Chicago, Illinois, USA. Hauptthemen laut MEDLINE: Acute Kidney Injury, Large Language Models, Precision Medicine, Drug Dosage Calculations. Die Arbeit nennt 18 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Introduction
Evidence‐based dosing guidance for medications in critically ill patients with acute kidney injury (AKI) and receiving continuous kidney replacement therapy (CKRT) is limited. Freely available large language models (LLMs) can generate confident, human‐like outputs. The accuracy and reproducibility of LLMs in providing precision drug dosing recommendations in the setting of AKI and CKRT have not been evaluated.
Objectives
We sought to characterize literature concordance and internal consistency of LLM‐generated dosing recommendations for cefepime and meropenem in patients with AKI and receiving CKRT.
Methods
Six investigators queried the freely available versions of six LLMs (ChatGPT, Claude, Google Gemini, Microsoft Copilot, OpenEvidence, and Perplexity) from July to September 2025 using three standardized vignettes asking for dosing recommendations and rationale to meet prespecified pharmacodynamic targets: (i) adult with AKI not on dialysis receiving cefepime, (ii) child receiving CKRT and cefepime, and (iii) toddler receiving high‐effluent CKRT and meropenem. To assess inter‐iteration consistency, each investigator also prompted one LLM three times for each vignette. Responses were parsed for concordance with recommendations in primary literature. LLM “reasoning” was evaluated for use of pharmacokinetic (PK) equations, citation accuracy versus confabulation, acknowledgment of uncertainty, and recommendations for therapeutic drug monitoring (TDM) for efficacy or safety.
Results
LLM‐generated dosing recommendations varied widely. Mean concordance with literature‐based recommendations was 63% (range: 28%–94%). LLMs produced variable responses to the same user upon multiple iterations, with variance in daily maintenance doses recommended ranging from 0 to 1000%. OpenEvidence universally cited relevant sources, whereas other LLMs leveraged sources inconsistently or confabulated them. Each recommended TDM, though only Claude consistently acknowledged its own uncertainty.
Conclusion
Freely available LLMs produce highly variable and often discordant antibiotic dosing recommendations for patients with AKI and receiving CKRT. Although valuable for hypothesis generation and literature retrieval, LLM outputs should not be used in isolation for drug dosing in critically ill patients with kidney dysfunction.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Division of Nephrology, Ann & Robert H. Lurie Children's Hospital of Chicago, Chicago, Illinois, USA.
- Department of Pediatrics, Northwestern University Feinberg School of Medicine, Chicago, Illinois, USA.
- Department of Critical Care, Dalhousie University, Halifax, Nova Scotia, Canada.
- Department of Pharmacology, Dalhousie University, Halifax, Nova Scotia, Canada.
- Department of Critical Care, Mayo Clinic, Scottsdale, Arizona, USA.
- Division of Nephrology and Hypertension, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio, USA.
ORCID-Profile: H Rhodes Hambrick, Samuel Dubinsky, Danica Quickfall, Shannon Reinert, Sonya Tang Girdwood, Gideon Stitt
Zitieren
APA
Hambrick, H. R., Dubinsky, S., Quickfall, D., Reinert, S., Tang Girdwood, S., & Stitt, G. (2026). User Beware: Inaccuracy and Inconsistency of Large Language Models in Providing Precision Dosing Recommendations for Patients With Kidney Impairment—A Case Series. Pharmacotherapy: The Journal of Human Pharmacology and Drug Therapy. https://doi.org/10.1002/phar.70207
Vancouver
Hambrick HR, Dubinsky S, Quickfall D, Reinert S, Tang Girdwood S, Stitt G. User Beware: Inaccuracy and Inconsistency of Large Language Models in Providing Precision Dosing Recommendations for Patients With Kidney Impairment—A Case Series. Pharmacotherapy: The Journal of Human Pharmacology and Drug Therapy. 2026. doi:10.1002/phar.70207
BibTeX
@article{Hambrick2026,
author = {Hambrick, H Rhodes and Dubinsky, Samuel and Quickfall, Danica and Reinert, Shannon and Tang Girdwood, Sonya and Stitt, Gideon},
title = {User Beware: Inaccuracy and Inconsistency of Large Language Models in Providing Precision Dosing Recommendations for Patients With Kidney Impairment—A Case Series},
journal = {Pharmacotherapy: The Journal of Human Pharmacology and Drug Therapy},
year = {2026},
doi = {10.1002/phar.70207}
}
EUVIMED