Systematic auditing is essential to debiasing machine learning in biology
Fatma-Elzahraa Eid et al. illustrate a principled approach for identifying biases that can inflate the performance of biological machine learning models. When applied to three biomedical prediction problems, they identify previously unrecognized biases and ultimately show that models are likely to l...
Guardado en:
Autores principales: | , , , , , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Nature Portfolio
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/99b8c372383a4995a2577d5c731b5219 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:99b8c372383a4995a2577d5c731b5219 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:99b8c372383a4995a2577d5c731b52192021-12-02T13:30:21ZSystematic auditing is essential to debiasing machine learning in biology10.1038/s42003-021-01674-52399-3642https://doaj.org/article/99b8c372383a4995a2577d5c731b52192021-02-01T00:00:00Zhttps://doi.org/10.1038/s42003-021-01674-5https://doaj.org/toc/2399-3642Fatma-Elzahraa Eid et al. illustrate a principled approach for identifying biases that can inflate the performance of biological machine learning models. When applied to three biomedical prediction problems, they identify previously unrecognized biases and ultimately show that models are likely to learn primarily from data biases when there is insufficient learnable signal in the data.Fatma-Elzahraa EidHaitham A. ElmarakebyYujia Alina ChanNadine FornelosMahmoud ElHefnawiEliezer M. Van AllenLenwood S. HeathKasper LageNature PortfolioarticleBiology (General)QH301-705.5ENCommunications Biology, Vol 4, Iss 1, Pp 1-9 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Biology (General) QH301-705.5 |
spellingShingle |
Biology (General) QH301-705.5 Fatma-Elzahraa Eid Haitham A. Elmarakeby Yujia Alina Chan Nadine Fornelos Mahmoud ElHefnawi Eliezer M. Van Allen Lenwood S. Heath Kasper Lage Systematic auditing is essential to debiasing machine learning in biology |
description |
Fatma-Elzahraa Eid et al. illustrate a principled approach for identifying biases that can inflate the performance of biological machine learning models. When applied to three biomedical prediction problems, they identify previously unrecognized biases and ultimately show that models are likely to learn primarily from data biases when there is insufficient learnable signal in the data. |
format |
article |
author |
Fatma-Elzahraa Eid Haitham A. Elmarakeby Yujia Alina Chan Nadine Fornelos Mahmoud ElHefnawi Eliezer M. Van Allen Lenwood S. Heath Kasper Lage |
author_facet |
Fatma-Elzahraa Eid Haitham A. Elmarakeby Yujia Alina Chan Nadine Fornelos Mahmoud ElHefnawi Eliezer M. Van Allen Lenwood S. Heath Kasper Lage |
author_sort |
Fatma-Elzahraa Eid |
title |
Systematic auditing is essential to debiasing machine learning in biology |
title_short |
Systematic auditing is essential to debiasing machine learning in biology |
title_full |
Systematic auditing is essential to debiasing machine learning in biology |
title_fullStr |
Systematic auditing is essential to debiasing machine learning in biology |
title_full_unstemmed |
Systematic auditing is essential to debiasing machine learning in biology |
title_sort |
systematic auditing is essential to debiasing machine learning in biology |
publisher |
Nature Portfolio |
publishDate |
2021 |
url |
https://doaj.org/article/99b8c372383a4995a2577d5c731b5219 |
work_keys_str_mv |
AT fatmaelzahraaeid systematicauditingisessentialtodebiasingmachinelearninginbiology AT haithamaelmarakeby systematicauditingisessentialtodebiasingmachinelearninginbiology AT yujiaalinachan systematicauditingisessentialtodebiasingmachinelearninginbiology AT nadinefornelos systematicauditingisessentialtodebiasingmachinelearninginbiology AT mahmoudelhefnawi systematicauditingisessentialtodebiasingmachinelearninginbiology AT eliezermvanallen systematicauditingisessentialtodebiasingmachinelearninginbiology AT lenwoodsheath systematicauditingisessentialtodebiasingmachinelearninginbiology AT kasperlage systematicauditingisessentialtodebiasingmachinelearninginbiology |
_version_ |
1718392929455702016 |