Academic Journal
User Beware: Inaccuracy and Inconsistency of Large Language Models in Providing Precision Dosing Recommendations for Patients With Kidney Impairment-A Case Series.
| Τίτλος: | User Beware: Inaccuracy and Inconsistency of Large Language Models in Providing Precision Dosing Recommendations for Patients With Kidney Impairment-A Case Series. |
|---|---|
| Συγγραφείς: | Hambrick HR; 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., Dubinsky S; Department of Critical Care, Dalhousie University, Halifax, Nova Scotia, Canada.; Department of Pharmacology, Dalhousie University, Halifax, Nova Scotia, Canada., Quickfall D; Department of Critical Care, Mayo Clinic, Scottsdale, Arizona, USA., Reinert S; Division of Nephrology and Hypertension, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio, USA.; Division of Translational and Clinical Pharmacology, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio, USA., Tang Girdwood S; Division of Translational and Clinical Pharmacology, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio, USA.; Division of Hospital Medicine, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio, USA.; Center for Acute Care Nephrology, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio, USA.; Department of Pediatrics, University of Cincinnati College of Medicine, Cincinnati, Ohio, USA., Stitt G; Division of Clinical Pharmacology, University of Utah, Salt Lake City, Utah, USA. |
| Πηγή: | Pharmacotherapy [Pharmacotherapy] 2026 Oct; Vol. 46 (10), pp. e70207. |
| Τύπος έκδοσης: | Evaluation Study; Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: Wiley-Blackwell Country of Publication: United States NLM ID: 8111305 Publication Model: Print Cited Medium: Internet ISSN: 1875-9114 (Electronic) Linking ISSN: 02770008 NLM ISO Abbreviation: Pharmacotherapy Subsets: MEDLINE |
| Imprint Name(s): | Publication: 2012- : Malden, MA : Wiley-Blackwell Original Publication: [Carlisle, MA : Pharmacotherapy Publications, c1981- |
| Ιατρικοί όροι (MeSH): | Acute Kidney Injury*/drug therapy , Precision Medicine*/methods , Precision Medicine*/statistics & numerical data , Anti-Bacterial Agents*/administration & dosage , Large Language Models* , Drug Dosage Calculations*, Cefepime/administration & dosage ; Meropenem/administration & dosage ; Humans ; Continuous Renal Replacement Therapy ; Reproducibility of Results ; Dose-Response Relationship, Drug ; Critical Illness ; Adult ; Infant ; Child |
| Περίληψη: | 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. (© 2026 The Author(s). Pharmacotherapy: The Journal of Human Pharmacology and Drug Therapy published by Wiley Periodicals LLC on behalf of ACCP Foundation, Ltd.) |
| References: | Kidney Med. 2023 Apr 15;5(6):100641. (PMID: 37274539) R Soc Open Sci. 2025 May 14;12(5):241873. (PMID: 40370601) Clin J Am Soc Nephrol. 2015 Jan 7;10(1):159-64. (PMID: 25189923) Commun Med (Lond). 2025 Jan 21;5(1):26. (PMID: 39838160) NPJ Digit Med. 2024 Nov 27;7(1):339. (PMID: 39604549) Res Social Adm Pharm. 2025 Mar;21(3):134-141. (PMID: 39730225) Cureus. 2025 Jan 3;17(1):e76867. (PMID: 39897335) Biomed J. 2025 Oct;48(5):100868. (PMID: 40311872) Crit Care. 2017 Nov 14;21(1):276. (PMID: 29137682) Am J Respir Crit Care Med. 2015 Oct 15;192(8):951-7. (PMID: 26120892) J Pediatr (Rio J). 2017 Jan - Feb;93(1):28-34. (PMID: 27379973) Can J Hosp Pharm. 2010 Mar;63(2):130-7. (PMID: 22478968) Semin Dial. 2014 Sep-Oct;27(5):441-5. (PMID: 25204875) J Am Pharm Assoc (2003). 2025 Jan-Feb;65(1):102306. (PMID: 39615589) Pharmacotherapy. 2026 Oct;46(10):e70207. (PMID: 42817723) |
| Contributed Indexing: | Keywords: acute kidney injury; artificial intelligence; beta lactams; continuous kidney replacement therapy; large language models; pharmacokinetics |
| Substance Nomenclature: | 807PW4VQE3 (Cefepime) FV9J3JU8B1 (Meropenem) 0 (Anti-Bacterial Agents) |
| Entry Date(s): | Date Created: 20261001 Date Completed: 20261006 Latest Revision: 20261006 |
| Update Code: | 20261006 |
| PubMed Central ID: | PMC13628145 |
| DOI: | 10.1002/phar.70207 |
| PMID: | 42817723 |
| Βάση Δεδομένων: | MEDLINE |
καταχωρήστε σχόλιο πρώτοι!