Cargando…
Combining Kernel and Model Based Learning for HIV Therapy Selection
We present a mixture-of-experts approach for HIV therapy selection. The heterogeneity in patient data makes it difficult for one particular model to succeed at providing suitable therapy predictions for all patients. An appropriate means for addressing this heterogeneity is through combining kernel...
Autores principales: | Parbhoo, Sonali, Bogojeska, Jasmina, Zazzi, Maurizio, Roth, Volker, Doshi-Velez, Finale |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
American Medical Informatics Association
2017
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5543338/ https://www.ncbi.nlm.nih.gov/pubmed/28815137 |
Ejemplares similares
-
Improving counterfactual reasoning with kernelised dynamic mixing models
por: Parbhoo, Sonali, et al.
Publicado: (2018) -
Improved functional prediction of proteins by learning kernel combinations in multilabel settings
por: Roth, Volker, et al.
Publicado: (2007) -
How machine-learning recommendations influence clinician treatment selections: the example of antidepressant selection
por: Jacobs, Maia, et al.
Publicado: (2021) -
Information Bottleneck for Estimating Treatment Effects with Systematically Missing Covariates
por: Parbhoo, Sonali, et al.
Publicado: (2020) -
Generalization in Clinical Prediction Models: The Blessing and Curse of Measurement Indicator Variables
por: Futoma, Joseph, et al.
Publicado: (2021)