Generic medical concept embedding and time decay for diverse patient outcome prediction tasks

Many fields, including Natural Language Processing (NLP), have recently witnessed the benefit of pre-training with large generic datasets to improve the accuracy of prediction tasks. However, there exist key differences between the longitudinal healthcare data (e.g., claims) and NLP tasks, which mak...

Descripción completa

Detalles Bibliográficos
Autores principales: Li, Yupeng, Dong, Wei, Ru, Boshu, Black, Adam, Zhang, Xinyuan, Guan, Yuanfang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2022
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9418804/
https://www.ncbi.nlm.nih.gov/pubmed/36039302
http://dx.doi.org/10.1016/j.isci.2022.104880

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9418804/
https://www.ncbi.nlm.nih.gov/pubmed/36039302
http://dx.doi.org/10.1016/j.isci.2022.104880

Ejemplares similares