• Home
  • Search
  • Large language models management of complex medication regimens: a case-based evaluation
  • Cite Icon2
  • https://doi.org/10.3389/fphar.2025.1514445Copy DOI Icon

Large language models management of complex medication regimens: a case-based evaluation

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

BackgroundLarge language models (LLMs) have shown the ability to diagnose complex medical cases, but only limited studies have evaluated the performance of LLMs in the development of evidence-based treatment plans. The purpose of this evaluation was to test four LLMs on their ability to develop safe and efficacious treatment plans on complex patients managed in the intensive care unit (ICU).MethodsEight high-fidelity patient cases focusing on medication management were developed by critical care clinicians including history of present illness, laboratory values, vital signs, home medications, and current medications. Four LLMs [ChatGPT (GPT-3.5), ChatGPT (GPT-4), Claude-2, and Llama-2–70b] were prompted to develop an optimized medication regimen for each case. LLM generated medication regimens were then reviewed by a panel of seven critical care clinicians to assess safety and efficacy, as defined by medication errors identified and appropriate treatment for the clinical conditions. Appropriate treatment was measured by the average rate of clinician agreement to continue each medication in the regimen and compared using analysis of variance (ANOVA).ResultsClinicians identified a median of 4.1–6.9 medication errors per recommended regimen, and life-threatening medication recommendations were present in 16.3%–57.1% of the regimens, depending on LLM. Clinicians continued LLM-recommended medications at a rate of 54.6%–67.3%, with GPT-4 having the highest rate of medication continuation among all LLMs tested (p < 0.001) and the lowest rate of life-threatening medication errors (p < 0.001).ConclusionCaution is warranted using present LLMs for medication regimens given the number of medication errors that were identified in this pilot study. However, LLMs did demonstrate potential to serve as clinical decision support for the management of complex medication regimens given the need for domain specific prompting and testing.

Similar Papers
  • Research Article
  • Citations29

Evaluation of medication errors with implementation of electronic health record technology in the medical intensive care unit

  • May 01, 2017
  • Open Access Journal of Clinical Trials
  • T Vivian Liao +7
  • Research Article
  • Citations10

The impact of a computerized physician order entry system on medical errors with antineoplastic drugs 5years after its implementation.

  • Jul 14, 2015
  • Journal of Clinical Pharmacy and Therapeutics
  • M Sanchez Cuervo +5
  • Research Article
  • Citations1

Medication errors: What is the pharmacist’s role?

  • Jan 01, 2016
  • Pharmacy Today
  • Randy P Mcdonough
  • Research Article

Effect of a closed-loop medication order executive system on safe medication administration at a tertiary hospital: a quasi-experimental study.

  • Oct 01, 2024
  • Therapeutic advances in drug safety
  • Xuwen Yin +17
  • Research Article
  • Citations3

Frequency and causes of medication errors of nurses in

  • Mar 09, 2015
  • Advances in Nursing & Midwifery
  • Mostafa Yousefi +3
  • PDF
  • Research Article
  • Citations16

Applicability of drug-related problem (DRP) classification system for classifying severe medication errors

  • Jul 10, 2023
  • BMC Health Services Research
  • Carita Linden-Lahti +3
  • Research Article
  • Citations8

Implementation of safeguards to improve patient safety in chemotherapy.

  • Mar 30, 2017
  • Clinical & translational oncology : official publication of the Federation of Spanish Oncology Societies and of the National Cancer Institute of Mexico
  • M J Huertas-Fernández +5
  • Research Article
  • Citations2

Prevalence and Risk Factors of Medication Errors in Enteral Tube Feeding Among ICU Patients: A Comprehensive Cross-Sectional Analysis.

  • Apr 01, 2024
  • Journal of research in pharmacy practice
  • Mansooreh Asghari-Varzaneh +2
  • Research Article
  • Citations196

Effects of the Accreditation Council for Graduate Medical Education Duty Hour Limits on Sleep, Work Hours, and Safety

  • Aug 01, 2008
  • Pediatrics
  • Christopher P Landrigan +9
  • Research Article
  • Citations6

Medication Error Analysis: A Systematic Approach

  • Jan 01, 2010
  • Current Drug Safety
  • Gourang Patel +1
  • Research Article

Analysis of 520 medication errors of traditional Chinese medicine in elderly patients

  • Oct 28, 2015
  • 药物不良反应杂志
  • Haizheng Wang +3
  • Research Article
  • Citations14

Medication errors in Spanish intensive care units

  • Aug 01, 2013
  • Medicina Intensiva (English Edition)
  • P Merino +5
  • Research Article
  • Citations9

Can We Talk? The Bedside Report Project

  • Apr 01, 2017
  • Critical Care Nurse
  • Jonna Rogers +4
  • Research Article
  • Citations100

Incidence of medication errors and adverse drug events in the ICU: a systematic review.

  • Jul 29, 2010
  • Quality & safety in health care
  • Amanda Wilmer +4
  • Research Article

Patient Safety: Grantmakers Join The Effort To Reduce Medical Errors

  • Mar 01, 2001
  • Health Affairs
  • Lauren Leroy +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.