Imagen de Portada

Can chatGPT-4o reliably standardize PSMA PET/CT and PET/MRI reports using PROMISE V2 criteria?: an exploratory study

Structured reporting standardizes and facilitates reporting, improves accurate communication, and ultimately clinical decision-making. Although standardized frameworks such as PROMISE criteria are available for prostate-specific membrane antigen positron emission tomography (PSMA PET) for prostate c...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Hinterberger, Anna (Autor) , Mangold, Maurin Helen (Autor) , Weigel, Caroline (Autor) , Hartmann, Henri (Autor) , Nörenberg, Dominik (Autor) , Froelich, Matthias F. (Autor) , Ebner, Ricarda (Autor) , Haney, Caelán Max (Autor) , Kowalewski, Karl-Friedrich (Autor) , Schönberg, Stefan (Autor) , Grawe, Freba (Autor)
Formato: Article (Journal)
Lenguaje:inglés
Publicado: 26 June 2026
In: EJNMMI Research
Year: 2026, Volumen: 16, Pages: 1-12
ISSN:2191-219X
DOI:10.1186/s13550-026-01475-z
Acceso en línea:Verlag, kostenfrei, Volltext: https://doi.org/10.1186/s13550-026-01475-z
Verlag, kostenfrei, Volltext: https://link.springer.com/article/10.1186/s13550-026-01475-z
Enlace del recurso
Notas de Autor:Anna Hinterberger, Maurin H. Mangold, Caroline Weigel, Henri Hartmann, Dominik Nörenberg, Matthias F. Froelich, Ricarda Ebner, Caelán Max Haney-Aubert, Karl-Friedrich Kowalewski, Stefan O. Schönberg and Freba Grawe
Descripción
Sumario:Structured reporting standardizes and facilitates reporting, improves accurate communication, and ultimately clinical decision-making. Although standardized frameworks such as PROMISE criteria are available for prostate-specific membrane antigen positron emission tomography (PSMA PET) for prostate cancer patients, free-text reporting remains predominant in both clinical routine and trials. Large language models (LLMs) may enable low-effort, time-efficient extraction of structured classifications from narrative reports. This study evaluated the performance of ChatGPT-4o for extracting PROMISE V2-based classifications from unstructured PSMA-PET/CT and PET/MRI reports.
Notas:Gesehen am 22.07.2026
Descripción Física:Online Resource
ISSN:2191-219X
DOI:10.1186/s13550-026-01475-z

Ejemplares similares