Potential limitations in COVID-19 machine learning due to data source variability: A case study in the nCov2019 dataset

OBJECTIVE: The lack of representative coronavirus disease 2019 (COVID-19) data is a bottleneck for reliable and generalizable machine learning. Data sharing is insufficient without data quality, in which source variability plays an important role. We showcase and discuss potential biases from data s...

Descripción completa

Detalles Bibliográficos
Autores principales: Sáez, Carlos, Romero, Nekane, Conejero, J Alberto, García-Gómez, Juan M
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Oxford University Press 2020
Materias:
Brief Communications
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7797735/
https://www.ncbi.nlm.nih.gov/pubmed/33027509
http://dx.doi.org/10.1093/jamia/ocaa258

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7797735/
https://www.ncbi.nlm.nih.gov/pubmed/33027509
http://dx.doi.org/10.1093/jamia/ocaa258

Ejemplares similares