Cargando…
Development and external validation of a pretrained deep learning model for the prediction of non-accidental trauma
Non-accidental trauma (NAT) is deadly and difficult to predict. Transformer models pretrained on large datasets have recently produced state of the art performance on diverse prediction tasks, but the optimal pretraining strategies for diagnostic predictions are not known. Here we report the develop...
Autores principales: | Huang, David, Cogill, Steven, Hsia, Renee Y., Yang, Samuel, Kim, David |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10356774/ https://www.ncbi.nlm.nih.gov/pubmed/37468526 http://dx.doi.org/10.1038/s41746-023-00875-y |
Ejemplares similares
-
A Pretraining-Retraining Strategy of Deep Learning Improves Cell-Specific Enhancer Predictions
por: Niu, Xiaohui, et al.
Publicado: (2020) -
Enhanced Tooth Region Detection Using Pretrained Deep Learning Models
por: Al-Sarem, Mohammed, et al.
Publicado: (2022) -
An Empirical Analysis of an Optimized Pretrained Deep Learning Model for COVID-19 Diagnosis
por: Sangeetha, S. K. B., et al.
Publicado: (2022) -
Assessment of emerging pretraining strategies in interpretable multimodal deep learning for cancer prognostication
por: Azher, Zarif L., et al.
Publicado: (2023) -
To pretrain or not? A systematic analysis of the benefits of pretraining in diabetic retinopathy
por: Srinivasan, Vignesh, et al.
Publicado: (2022)