Large Language Model–Generated Patient Instructions for Prescriptions in Primary Health Care: Preclinical Algorithm Validation

Zilma Silveira Nogueira Reis, Elisa Tuler Albergaria, Adriana Silvina Pagano, Eura Martins Lage, Flávia Ribeiro de Oliveira, Cristiane dos Santos Dias, Juliana Almeida Oliveira, Gláucia Miranda Varella Pereira, Isaias Jose Ramos de Oliveira, Érico Franco Mineiro, Igor Carvalho Lima Oliveira, Davi do · 2026

Read Large Language Model–Generated Patient Instructions for Prescriptions in Primary Health Care: Preclinical Algorithm Validation by Zilma Silveira Nogueira Reis, Elisa Tuler Albergaria, Adriana Silvina Pagano, Eura Martins Lage, Flávia Ribeiro de Oliveira, Cristiane dos Santos Dias, Juliana Almeida Oliveira, Gláucia Miranda Varella Pereira, Isaias Jose Ramos de Oliveira, Érico Franco Mineiro, Igor Carvalho Lima Oliveira, Davi do (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13250494.txt.

Description

Zilma Silveira Nogueira Reis leads a large team in a 2026 validation study of drug instructions written by language models. The study tested whether three artificial intelligence systems could turn prescriptions into clear guidance for patients in primary care. Clear instructions matter because confusion about medicines leads people to stop treatment early.

Sixty-two health professionals graded model-written instructions for invented prescription cases while blinded to which system wrote each text. ChatGPT-4.0 earned the highest overall scores, with a median mark of 88.4 points on the grading scale used. A smaller open model scored lower on its own, but its mark rose to 79.9 points when it could draw on patient leaflets. The authors conclude that leaflet support helps smaller models approach the quality of the largest system. They frame the work as a preclinical check, done before any use with real patients.

Catalog record

CREATORZilma Silveira Nogueira Reis, Elisa Tuler Albergaria, Adriana Silvina Pagano, Eura Martins Lage, Flávia Ribeiro de Oliveira, Cristiane dos Santos Dias, Juliana Almeida Oliveira, Gláucia Miranda Varella Pereira, Isaias Jose Ramos de Oliveira, Érico Franco Mineiro, Igor Carvalho Lima Oliveira, Davi do
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE55 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13250494

Browse the full library · About the Tower of Babel