Prescription Errors: The Role of Language Models in Patient Safety in an Expert Evaluation Study
DOI:
https://doi.org/10.59681/2175-4411.v18.2026.1570Palavras-chave:
Clinical Decision Support Systems, Artificial Intelligence, Large Language ModelsResumo
Objective: This study investigates the potential of Large Language Models (LLMs) to support medical prescription processes and enhance patient safety. Methods: Six LLMs answered four prescription-related questions on contraindications, drug interactions, and dosage. A panel of 34 physicians blindly evaluated 24 responses based on consistency, focus, coherence, completeness, and detail. Results: LLM performance varied by criteria and question type; LLM6 excelled in completeness and detail, especially in complex cases. Simpler questions, like contraindications, scored higher overall, while complex queries showed more variation. Conclusion: LLMs show promise as digital assistants in prescription tasks, improving access to medical info and reducing errors. However, reliability depends on question complexity. They should support, not replace, clinical judgment and require ongoing validation for healthcare adoption.
Downloads
Referências
Tariq RA, Vashisht R, Sinha A. Medication Dispensing Errors and Prevention. In: StatPearls, Treasure Island: StatPearls Publishing; https://www.ncbi.nlm.nih.gov/books/NBK519065/ ; 2025 (accessed 14 May 2025).
National Coordinating Council for Medication Error Reporting and Prevention. About medication errors: What is a medication error?, https://www.nccmerp.org/about-medication-errors ; 2025 (accessed 02 February 2025).
Cruzeta APS, Dourado ACL, Monteiro MTM, Martins RO, Calegario TA, Galato D. Fatores associados à compreensão da prescrição médica no Sistema Único de Saúde de um município do Sul do Brasil. Cien Saude Colet. 2013;18(12):3731-3737.
World Health Organization. Medication Without Harm, https://www.who.int/initiatives/medication-without-harm ; 2025 (accessed 03 February 2025).
Academy of Managed Care Pharmacy. Medication Errors, https://www.amcp.org/concepts-managed-care-pharmacy/medication-errors ; 2025 (accessed 03 February 2025).
Cohen MR, Smetzer JL. ISMP Medication Error Report Analysis. Hospital pharmacy 2017; 52: 390-393. https://doi.org/10.1177/0018578717715346
Shah K., Xu AY, Sharma Y, Daher M, McDonald C, Diebo BG, Daniels AH. Large Language Model Prompting Techniques for Advancement in Clinical Medicine. Journal of Clinical Medicine 2024; 13: 1-12. https://doi.org/10.3390/jcm13175101
Netto AV, Berton L, Takahata AK. Ciência de dados e a inteligência artificial na área da saúde. Editora dos Editores; 2021.
Netto AV. Ciência de dados em saúde: contribuições e tendências para aplicações. Revista Saúde.com, 2021;(17) 1-5. https://doi.org/10.22481/rsc.v17i3.6290
Software & Data: Osford’s DrugGPT AI tool enhances medication prescriptions. The Healthcare Technology Report, https://thehealthcaretechnologyreport.com/oxfords-druggpt-ai-tool-enhances-medication-prescriptions ; 2024 (accessed 04 February 2025).
OpenAI. Hello ChatGPT-4o, https://openai.com/index/hello-gpt-4o ; 2024 (accessed 08 February 2025).
Cortex. Your Exclusive Corporate AI. https://sinapse.tech/cortex ; 2025 (accessed 08 February 2025).
Anthropic. Introducing Claude 3.5 Sonnet information. https://www.anthropic.com/news/claude-3-5-sonnet ; 2024 (accessed 08 February 2025).
Meta. Introducing Llama 3.1: Our most capable models to date, https://ai.meta.com/blog/meta-llama-3-1 ; 2024 (accessed 08 February 2025).
Cohere. The all-in-one platform for private and secure AI. https://cohere.com/ ; 2024 (accessed 08 February 2025).
Google. Gemini models, https://ai.google.dev/gemini-api/docs/models/gemini ; 2025 (accessed 08 February 2025).
Medeiros CH, Kauark FD, Manhães FC. Metodologia da pesquisa: Guia prático. Via Litterarum, Itabuna; 2010.
Downloads
Publicado
Como Citar
Edição
Secção
Licença
Direitos de Autor (c) 2026 Antonio Valerio Netto, Camila de Brito Pontes

Este trabalho encontra-se publicado com a Licença Internacional Creative Commons Atribuição-NãoComercial-CompartilhaIgual 4.0.
A submissão de um artigo ao Journal of Health Informatics é entendida como exclusiva e que não está sendo considerada para publicação em outra revista (Declaração de Exclusividade). A permissão dos autores para a publicação de seu artigo no J. Health Inform. implica na exclusiva autorização concedida aos editores para incluí-lo na revista. Ao submeter um artigo, ao autor será solicitada a permissão de um Termo de Transferência de Direitos de Publicação. Uma mensagem eletrônica será enviada ao autor correspondente confirmando o recibo do manuscrito e o aceite da Declaração de Direito de Publicação.
