An argument for reporting data standardization procedures in multi-site predictive modeling: case study on the impact of LOINC standardization on model performance

OBJECTIVES: We aimed to gain a better understanding of how standardization of laboratory data can impact predictive model performance in multi-site datasets. We hypothesized that standardizing local laboratory codes to logical observation identifiers names and codes (LOINC) would produce predictive...

Descripción completa

Detalles Bibliográficos
Autores principales: Barda, Amie J, Ruiz, Victor M, Gigliotti, Tony, Tsui, Fuchiang (Rich)
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Oxford University Press 2019
Materias:
Research and Applications
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6435008/
https://www.ncbi.nlm.nih.gov/pubmed/30944914
http://dx.doi.org/10.1093/jamiaopen/ooy063

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6435008/
https://www.ncbi.nlm.nih.gov/pubmed/30944914
http://dx.doi.org/10.1093/jamiaopen/ooy063

Ejemplares similares