Inferring cancer disease response from radiology reports using large language models with data augmentation and prompting

OBJECTIVE: To assess large language models on their ability to accurately infer cancer disease response from free-text radiology reports. MATERIALS AND METHODS: We assembled 10 602 computed tomography reports from cancer patients seen at a single institution. All reports were classified into: no evi...

Descripción completa

Detalles Bibliográficos
Autores principales: Tan, Ryan Shea Ying Cong, Lin, Qian, Low, Guat Hwa, Lin, Ruixi, Goh, Tzer Chew, Chang, Christopher Chu En, Lee, Fung Fung, Chan, Wei Yin, Tan, Wei Chong, Tey, Han Jieh, Leong, Fun Loon, Tan, Hong Qi, Nei, Wen Long, Chay, Wen Yee, Tai, David Wai Meng, Lai, Gillianne Geet Yi, Cheng, Lionel Tim-Ee, Wong, Fuh Yong, Chua, Matthew Chin Heng, Chua, Melvin Lee Kiang, Tan, Daniel Shao Weng, Thng, Choon Hua, Tan, Iain Bee Huat, Ng, Hwee Tou
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Oxford University Press 2023
Materias:
Research and Applications
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10531105/
https://www.ncbi.nlm.nih.gov/pubmed/37451682
http://dx.doi.org/10.1093/jamia/ocad133

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10531105/
https://www.ncbi.nlm.nih.gov/pubmed/37451682
http://dx.doi.org/10.1093/jamia/ocad133

Ejemplares similares