Academic Journal
View in EDS

User Beware: Inaccuracy and Inconsistency of Large Language Models in Providing Precision Dosing Recommendations for Patients With Kidney Impairment-A Case Series.

Bibliographic Details
Title: User Beware: Inaccuracy and Inconsistency of Large Language Models in Providing Precision Dosing Recommendations for Patients With Kidney Impairment-A Case Series.
Authors: 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.
Source: Pharmacotherapy [Pharmacotherapy] 2026 Oct; Vol. 46 (10), pp. e70207.
Publication Type: Evaluation Study; Journal Article
Language: English
Journal Info: 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-
MeSH Terms: 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
Abstract: 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
Database: MEDLINE
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:cmedm&genre=article&issn=18759114&ISBN=&volume=46&issue=10&date=20261001&spage=e70207&pages=e70207&title=Pharmacotherapy&atitle=User%20Beware%3A%20Inaccuracy%20and%20Inconsistency%20of%20Large%20Language%20Models%20in%20Providing%20Precision%20Dosing%20Recommendations%20for%20Patients%20With%20Kidney%20Impairment-A%20Case%20Series.&aulast=Hambrick%20HR&id=DOI:10.1002/phar.70207
    Name: Full Text Finder (for New FTF UI) (ns324271)
    Category: fullText
    Text: Full Text Finder
    MouseOverText: Full Text Finder
Header DbId: cmedm
DbLabel: MEDLINE
An: 42817723
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: User Beware: Inaccuracy and Inconsistency of Large Language Models in Providing Precision Dosing Recommendations for Patients With Kidney Impairment-A Case Series.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AU" term="%22Hambrick+HR%22">Hambrick HR</searchLink>; 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.<br /><searchLink fieldCode="AU" term="%22Dubinsky+S%22">Dubinsky S</searchLink>; Department of Critical Care, Dalhousie University, Halifax, Nova Scotia, Canada.; Department of Pharmacology, Dalhousie University, Halifax, Nova Scotia, Canada.<br /><searchLink fieldCode="AU" term="%22Quickfall+D%22">Quickfall D</searchLink>; Department of Critical Care, Mayo Clinic, Scottsdale, Arizona, USA.<br /><searchLink fieldCode="AU" term="%22Reinert+S%22">Reinert S</searchLink>; 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.<br /><searchLink fieldCode="AU" term="%22Tang+Girdwood+S%22">Tang Girdwood S</searchLink>; 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.<br /><searchLink fieldCode="AU" term="%22Stitt+G%22">Stitt G</searchLink>; Division of Clinical Pharmacology, University of Utah, Salt Lake City, Utah, USA.
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%228111305%22">Pharmacotherapy</searchLink> [Pharmacotherapy] 2026 Oct; Vol. 46 (10), pp. e70207.
– Name: TypePub
  Label: Publication Type
  Group: TypPub
  Data: Evaluation Study; Journal Article
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: TitleSource
  Label: Journal Info
  Group: Src
  Data: <i>Publisher: </i><searchLink fieldCode="PB" term="%22Wiley-Blackwell%22">Wiley-Blackwell </searchLink><i>Country of Publication: </i>United States <i>NLM ID: </i>8111305 <i>Publication Model: </i>Print <i>Cited Medium: </i>Internet <i>ISSN: </i>1875-9114 (Electronic) <i>Linking ISSN: </i><searchLink fieldCode="IS" term="%2202770008%22">02770008 </searchLink><i>NLM ISO Abbreviation: </i>Pharmacotherapy <i>Subsets: </i>MEDLINE
– Name: PublisherInfo
  Label: Imprint Name(s)
  Group: PubInfo
  Data: <i>Publication</i>: 2012- : Malden, MA : Wiley-Blackwell<br /><i>Original Publication</i>: [Carlisle, MA : Pharmacotherapy Publications, c1981-
– Name: SubjectMESH
  Label: MeSH Terms
  Group: Su
  Data: <searchLink fieldCode="MM" term="%22Acute+Kidney+Injury%22">Acute Kidney Injury*</searchLink>/<searchLink fieldCode="MM" term="%22Acute+Kidney+Injury+drug+therapy%22">drug therapy</searchLink> <br /><searchLink fieldCode="MM" term="%22Precision+Medicine%22">Precision Medicine*</searchLink>/<searchLink fieldCode="MM" term="%22Precision+Medicine+methods%22">methods</searchLink> <br /><searchLink fieldCode="MM" term="%22Precision+Medicine%22">Precision Medicine*</searchLink>/<searchLink fieldCode="MM" term="%22Precision+Medicine+statistics+%26+numerical+data%22">statistics & numerical data</searchLink> <br /><searchLink fieldCode="MM" term="%22Anti-Bacterial+Agents%22">Anti-Bacterial Agents*</searchLink>/<searchLink fieldCode="MM" term="%22Anti-Bacterial+Agents+administration+%26+dosage%22">administration & dosage</searchLink> <br /><searchLink fieldCode="MM" term="%22Large+Language+Models%22">Large Language Models*</searchLink> <br /><searchLink fieldCode="MM" term="%22Drug+Dosage+Calculations%22">Drug Dosage Calculations*</searchLink><br /><searchLink fieldCode="MH" term="%22Cefepime%22">Cefepime</searchLink>/<searchLink fieldCode="MH" term="%22Cefepime+administration+%26+dosage%22">administration & dosage</searchLink> ; <searchLink fieldCode="MH" term="%22Meropenem%22">Meropenem</searchLink>/<searchLink fieldCode="MH" term="%22Meropenem+administration+%26+dosage%22">administration & dosage</searchLink> ; <searchLink fieldCode="MH" term="%22Humans%22">Humans</searchLink> ; <searchLink fieldCode="MH" term="%22Continuous+Renal+Replacement+Therapy%22">Continuous Renal Replacement Therapy</searchLink> ; <searchLink fieldCode="MH" term="%22Reproducibility+of+Results%22">Reproducibility of Results</searchLink> ; <searchLink fieldCode="MH" term="%22Dose-Response+Relationship%2C+Drug%22">Dose-Response Relationship, Drug</searchLink> ; <searchLink fieldCode="MH" term="%22Critical+Illness%22">Critical Illness</searchLink> ; <searchLink fieldCode="MH" term="%22Adult%22">Adult</searchLink> ; <searchLink fieldCode="MH" term="%22Infant%22">Infant</searchLink> ; <searchLink fieldCode="MH" term="%22Child%22">Child</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: 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.<br />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.<br />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.<br />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.<br />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.<br /> (© 2026 The Author(s). Pharmacotherapy: The Journal of Human Pharmacology and Drug Therapy published by Wiley Periodicals LLC on behalf of ACCP Foundation, Ltd.)
– Name: Ref
  Label: References
  Group: RefInfo
  Data: Kidney Med. 2023 Apr 15;5(6):100641. (PMID: <searchLink fieldCode="PM" term="%2237274539%22">37274539)</searchLink><br />R Soc Open Sci. 2025 May 14;12(5):241873. (PMID: <searchLink fieldCode="PM" term="%2240370601%22">40370601)</searchLink><br />Clin J Am Soc Nephrol. 2015 Jan 7;10(1):159-64. (PMID: <searchLink fieldCode="PM" term="%2225189923%22">25189923)</searchLink><br />Commun Med (Lond). 2025 Jan 21;5(1):26. (PMID: <searchLink fieldCode="PM" term="%2239838160%22">39838160)</searchLink><br />NPJ Digit Med. 2024 Nov 27;7(1):339. (PMID: <searchLink fieldCode="PM" term="%2239604549%22">39604549)</searchLink><br />Res Social Adm Pharm. 2025 Mar;21(3):134-141. (PMID: <searchLink fieldCode="PM" term="%2239730225%22">39730225)</searchLink><br />Cureus. 2025 Jan 3;17(1):e76867. (PMID: <searchLink fieldCode="PM" term="%2239897335%22">39897335)</searchLink><br />Biomed J. 2025 Oct;48(5):100868. (PMID: <searchLink fieldCode="PM" term="%2240311872%22">40311872)</searchLink><br />Crit Care. 2017 Nov 14;21(1):276. (PMID: <searchLink fieldCode="PM" term="%2229137682%22">29137682)</searchLink><br />Am J Respir Crit Care Med. 2015 Oct 15;192(8):951-7. (PMID: <searchLink fieldCode="PM" term="%2226120892%22">26120892)</searchLink><br />J Pediatr (Rio J). 2017 Jan - Feb;93(1):28-34. (PMID: <searchLink fieldCode="PM" term="%2227379973%22">27379973)</searchLink><br />Can J Hosp Pharm. 2010 Mar;63(2):130-7. (PMID: <searchLink fieldCode="PM" term="%2222478968%22">22478968)</searchLink><br />Semin Dial. 2014 Sep-Oct;27(5):441-5. (PMID: <searchLink fieldCode="PM" term="%2225204875%22">25204875)</searchLink><br />J Am Pharm Assoc (2003). 2025 Jan-Feb;65(1):102306. (PMID: <searchLink fieldCode="PM" term="%2239615589%22">39615589)</searchLink><br />Pharmacotherapy. 2026 Oct;46(10):e70207. (PMID: <searchLink fieldCode="PM" term="%2242817723%22">42817723)</searchLink>
– Name: SubjectMinor
  Label: Contributed Indexing
  Group:
  Data: <i>Keywords: </i>acute kidney injury; artificial intelligence; beta lactams; continuous kidney replacement therapy; large language models; pharmacokinetics
– Name: NumberCAS
  Label: Substance Nomenclature
  Group: ID
  Data: 807PW4VQE3 (Cefepime)<br />FV9J3JU8B1 (Meropenem)<br />0 (Anti-Bacterial Agents)
– Name: DateEntry
  Label: Entry Date(s)
  Group: Date
  Data: <i>Date Created: </i>20261001 <i>Date Completed: </i>20261006 <i>Latest Revision: </i>20261006
– Name: DateUpdate
  Label: Update Code
  Group: Date
  Data: 20261006
– Name: PubmedCentralID
  Label: PubMed Central ID
  Group: ID
  Data: PMC13628145
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1002/phar.70207
– Name: AN
  Label: PMID
  Group: ID
  Data: 42817723
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=cmedm&AN=42817723
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1002/phar.70207
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        StartPage: e70207
    Subjects:
      – SubjectFull: Cefepime administration & dosage
        Type: general
      – SubjectFull: Meropenem administration & dosage
        Type: general
      – SubjectFull: Humans
        Type: general
      – SubjectFull: Continuous Renal Replacement Therapy
        Type: general
      – SubjectFull: Reproducibility of Results
        Type: general
      – SubjectFull: Dose-Response Relationship, Drug
        Type: general
      – SubjectFull: Critical Illness
        Type: general
      – SubjectFull: Adult
        Type: general
      – SubjectFull: Infant
        Type: general
      – SubjectFull: Child
        Type: general
      – SubjectFull: Acute Kidney Injury drug therapy
        Type: general
      – SubjectFull: Precision Medicine methods
        Type: general
      – SubjectFull: Precision Medicine statistics & numerical data
        Type: general
      – SubjectFull: Anti-Bacterial Agents administration & dosage
        Type: general
      – SubjectFull: Large Language Models
        Type: general
      – SubjectFull: Drug Dosage Calculations
        Type: general
    Titles:
      – TitleFull: User Beware: Inaccuracy and Inconsistency of Large Language Models in Providing Precision Dosing Recommendations for Patients With Kidney Impairment-A Case Series.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Hambrick HR
      – PersonEntity:
          Name:
            NameFull: Dubinsky S
      – PersonEntity:
          Name:
            NameFull: Quickfall D
      – PersonEntity:
          Name:
            NameFull: Reinert S
      – PersonEntity:
          Name:
            NameFull: Tang Girdwood S
      – PersonEntity:
          Name:
            NameFull: Stitt G
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 10
              Text: 2026 Oct
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-electronic
              Value: 1875-9114
          Numbering:
            – Type: volume
              Value: 46
            – Type: issue
              Value: 10
          Titles:
            – TitleFull: Pharmacotherapy
              Type: main
ResultId 1