Cargando…
Removing Confounding Factors Associated Weights in Deep Neural Networks Improves the Prediction Accuracy for Healthcare Applications
The proliferation of healthcare data has brought the opportunities of applying data-driven approaches, such as machine learning methods, to assist diagnosis. Recently, many deep learning methods have been shown with impressive successes in predicting disease status with raw input data. However, the...
Autores principales: | Wang, Haohan, Wu, Zhenglin, Xing, Eric P. |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
2019
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6417810/ https://www.ncbi.nlm.nih.gov/pubmed/30864310 |
Ejemplares similares
-
How to remove or control confounds in predictive models, with applications to brain biomarkers
por: Chyzhyk, Darya, et al.
Publicado: (2022) -
Confound-leakage: confound removal in machine learning leads to leakage
por: Hamdan, Sami, et al.
Publicado: (2023) -
Deep learning predicts hip fracture using confounding patient and healthcare variables
por: Badgeley, Marcus A., et al.
Publicado: (2019) -
Deep learning-based unlearning of dataset bias for MRI harmonisation and confound removal
por: Dinsdale, Nicola K., et al.
Publicado: (2021) -
Using deep maxout neural networks to improve the accuracy of function prediction from protein interaction networks
por: Wan, Cen, et al.
Publicado: (2019)