Stress Testing Pathology Models with Generated Artifacts

BACKGROUND: Machine learning models provide significant opportunities for improvement in health care, but their “black-box” nature poses many risks. METHODS: We built a custom Python module as part of a framework for generating artifacts that are meant to be tunable and describable to allow for futu...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Nicholas Chandler, Kaplan, Jeremy, Lee, Joonsang, Hodgin, Jeffrey, Udager, Aaron, Rao, Arvind
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Wolters Kluwer - Medknow 2021
Materias:
Original Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8721870/
https://www.ncbi.nlm.nih.gov/pubmed/35070483
http://dx.doi.org/10.4103/jpi.jpi_6_21

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8721870/
https://www.ncbi.nlm.nih.gov/pubmed/35070483
http://dx.doi.org/10.4103/jpi.jpi_6_21

Ejemplares similares