Gaussian noise up-sampling is better suited than SMOTE and ADASYN for clinical decision making

Abstract Clinical data sets have very special properties and suffer from many caveats in machine learning. They typically show a high-class imbalance, have a small number of samples and a large number of parameters, and have missing values. While feature selection approaches and imputation technique...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jacqueline Beinecke, Dominik Heider
Formato:	article
Lenguaje:	EN
Publicado:	BMC 2021
Materias:	Machine learning Clinical data Data augmentation Synthetic data Computer applications to medicine. Medical informatics R858-859.7 Analysis QA299.6-433
Acceso en línea:	https://doaj.org/article/87bc75d2f5c5416db4f6e104d9286f50
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:87bc75d2f5c5416db4f6e104d9286f50
record_format	dspace
spelling	oai:doaj.org-article:87bc75d2f5c5416db4f6e104d9286f502021-12-05T12:03:55ZGaussian noise up-sampling is better suited than SMOTE and ADASYN for clinical decision making10.1186/s13040-021-00283-61756-0381https://doaj.org/article/87bc75d2f5c5416db4f6e104d9286f502021-11-01T00:00:00Zhttps://doi.org/10.1186/s13040-021-00283-6https://doaj.org/toc/1756-0381Abstract Clinical data sets have very special properties and suffer from many caveats in machine learning. They typically show a high-class imbalance, have a small number of samples and a large number of parameters, and have missing values. While feature selection approaches and imputation techniques address the former problems, the class imbalance is typically addressed using augmentation techniques. However, these techniques have been developed for big data analytics, and their suitability for clinical data sets is unclear. This study analyzed different augmentation techniques for use in clinical data sets and subsequent employment of machine learning-based classification. It turns out that Gaussian Noise Up-Sampling (GNUS) is not always but generally, is as good as SMOTE and ADASYN and even outperform those on some datasets. However, it has also been shown that augmentation does not improve classification at all in some cases.Jacqueline BeineckeDominik HeiderBMCarticleMachine learningClinical dataData augmentationSynthetic dataComputer applications to medicine. Medical informaticsR858-859.7AnalysisQA299.6-433ENBioData Mining, Vol 14, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Machine learning Clinical data Data augmentation Synthetic data Computer applications to medicine. Medical informatics R858-859.7 Analysis QA299.6-433
spellingShingle	Machine learning Clinical data Data augmentation Synthetic data Computer applications to medicine. Medical informatics R858-859.7 Analysis QA299.6-433 Jacqueline Beinecke Dominik Heider Gaussian noise up-sampling is better suited than SMOTE and ADASYN for clinical decision making
description	Abstract Clinical data sets have very special properties and suffer from many caveats in machine learning. They typically show a high-class imbalance, have a small number of samples and a large number of parameters, and have missing values. While feature selection approaches and imputation techniques address the former problems, the class imbalance is typically addressed using augmentation techniques. However, these techniques have been developed for big data analytics, and their suitability for clinical data sets is unclear. This study analyzed different augmentation techniques for use in clinical data sets and subsequent employment of machine learning-based classification. It turns out that Gaussian Noise Up-Sampling (GNUS) is not always but generally, is as good as SMOTE and ADASYN and even outperform those on some datasets. However, it has also been shown that augmentation does not improve classification at all in some cases.
format	article
author	Jacqueline Beinecke Dominik Heider
author_facet	Jacqueline Beinecke Dominik Heider
author_sort	Jacqueline Beinecke
title	Gaussian noise up-sampling is better suited than SMOTE and ADASYN for clinical decision making
title_short	Gaussian noise up-sampling is better suited than SMOTE and ADASYN for clinical decision making
title_full	Gaussian noise up-sampling is better suited than SMOTE and ADASYN for clinical decision making
title_fullStr	Gaussian noise up-sampling is better suited than SMOTE and ADASYN for clinical decision making
title_full_unstemmed	Gaussian noise up-sampling is better suited than SMOTE and ADASYN for clinical decision making
title_sort	gaussian noise up-sampling is better suited than smote and adasyn for clinical decision making
publisher	BMC
publishDate	2021
url	https://doaj.org/article/87bc75d2f5c5416db4f6e104d9286f50
work_keys_str_mv	AT jacquelinebeinecke gaussiannoiseupsamplingisbettersuitedthansmoteandadasynforclinicaldecisionmaking AT dominikheider gaussiannoiseupsamplingisbettersuitedthansmoteandadasynforclinicaldecisionmaking
_version_	1718372267469045760

Gaussian noise up-sampling is better suited than SMOTE and ADASYN for clinical decision making

Ejemplares similares