Radiomics machine learning study with a small sample size: Single random training-test set split may lead to unreliable results.
This study aims to determine how randomly splitting a dataset into training and test sets affects the estimated performance of a machine learning model and its gap from the test performance under different conditions, using real-world brain tumor radiomics data. We conducted two classification tasks...
Guardado en:
Autores principales: | Chansik An, Yae Won Park, Sung Soo Ahn, Kyunghwa Han, Hwiyoung Kim, Seung-Koo Lee |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Public Library of Science (PLoS)
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/b7eeddeca55a457896778de5c6af09dc |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
-
Differentiation of recurrent glioblastoma from radiation necrosis using diffusion radiomics with machine learning model development and external validation
por: Yae Won Park, et al.
Publicado: (2021) -
Identifying unreliable predictions in clinical risk models
por: Paul D. Myers, et al.
Publicado: (2020) -
Imagery Representatives of Reliability and Unreliability in Russian Phraseology
por: T. V. Leontyeva
Publicado: (2018) -
A radiomics-based model for predicting prognosis of locally advanced gastric cancer in the preoperative setting
por: Jaeseung Shin, et al.
Publicado: (2021) -
Prioritizing phylogenetic diversity captures functional diversity unreliably
por: Florent Mazel, et al.
Publicado: (2018)