“Yes, but will it work for my patients?” Driving clinically relevant research with benchmark datasets

Abstract Benchmark datasets have a powerful normative influence: by determining how the real world is represented in data, they define which problems will first be solved by algorithms built using the datasets and, by extension, who these algorithms will work for. It is desirable for these datasets...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Trishan Panch, Tom J. Pollard, Heather Mattie, Emily Lindemer, Pearse A. Keane, Leo Anthony Celi
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2020
Materias:	Computer applications to medicine. Medical informatics R858-859.7
Acceso en línea:	https://doaj.org/article/137ec39e5c7443ce9fa5c7d8216b54ee
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:137ec39e5c7443ce9fa5c7d8216b54ee
record_format	dspace
spelling	oai:doaj.org-article:137ec39e5c7443ce9fa5c7d8216b54ee2021-12-02T17:40:49Z“Yes, but will it work for my patients?” Driving clinically relevant research with benchmark datasets10.1038/s41746-020-0295-62398-6352https://doaj.org/article/137ec39e5c7443ce9fa5c7d8216b54ee2020-06-01T00:00:00Zhttps://doi.org/10.1038/s41746-020-0295-6https://doaj.org/toc/2398-6352Abstract Benchmark datasets have a powerful normative influence: by determining how the real world is represented in data, they define which problems will first be solved by algorithms built using the datasets and, by extension, who these algorithms will work for. It is desirable for these datasets to serve four functions: (1) enabling the creation of clinically relevant algorithms; (2) facilitating like-for-like comparison of algorithmic performance; (3) ensuring reproducibility of algorithms; (4) asserting a normative influence on the clinical domains and diversity of patients that will potentially benefit from technological advances. Without benchmark datasets that satisfy these functions, it is impossible to address two perennial concerns of clinicians experienced in computational research: “the data scientists just go where the data is rather than where the needs are,” and, “yes, but will this work for my patients?” If algorithms are to be developed and applied for the care of patients, then it is prudent for the research community to create benchmark datasets proactively, across specialties. As yet, best practice in this area has not been defined. Broadly speaking, efforts will include design of the dataset; compliance and contracting issues relating to the sharing of sensitive data; enabling access and reuse; and planning for translation of algorithms to the clinical environment. If a deliberate and systematic approach is not followed, not only will the considerable benefits of clinical algorithms fail to be realized, but the potential harms may be regressively incurred across existing gradients of social inequity.Trishan PanchTom J. PollardHeather MattieEmily LindemerPearse A. KeaneLeo Anthony CeliNature PortfolioarticleComputer applications to medicine. Medical informaticsR858-859.7ENnpj Digital Medicine, Vol 3, Iss 1, Pp 1-4 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Computer applications to medicine. Medical informatics R858-859.7
spellingShingle	Computer applications to medicine. Medical informatics R858-859.7 Trishan Panch Tom J. Pollard Heather Mattie Emily Lindemer Pearse A. Keane Leo Anthony Celi “Yes, but will it work for my patients?” Driving clinically relevant research with benchmark datasets
description	Abstract Benchmark datasets have a powerful normative influence: by determining how the real world is represented in data, they define which problems will first be solved by algorithms built using the datasets and, by extension, who these algorithms will work for. It is desirable for these datasets to serve four functions: (1) enabling the creation of clinically relevant algorithms; (2) facilitating like-for-like comparison of algorithmic performance; (3) ensuring reproducibility of algorithms; (4) asserting a normative influence on the clinical domains and diversity of patients that will potentially benefit from technological advances. Without benchmark datasets that satisfy these functions, it is impossible to address two perennial concerns of clinicians experienced in computational research: “the data scientists just go where the data is rather than where the needs are,” and, “yes, but will this work for my patients?” If algorithms are to be developed and applied for the care of patients, then it is prudent for the research community to create benchmark datasets proactively, across specialties. As yet, best practice in this area has not been defined. Broadly speaking, efforts will include design of the dataset; compliance and contracting issues relating to the sharing of sensitive data; enabling access and reuse; and planning for translation of algorithms to the clinical environment. If a deliberate and systematic approach is not followed, not only will the considerable benefits of clinical algorithms fail to be realized, but the potential harms may be regressively incurred across existing gradients of social inequity.
format	article
author	Trishan Panch Tom J. Pollard Heather Mattie Emily Lindemer Pearse A. Keane Leo Anthony Celi
author_facet	Trishan Panch Tom J. Pollard Heather Mattie Emily Lindemer Pearse A. Keane Leo Anthony Celi
author_sort	Trishan Panch
title	“Yes, but will it work for my patients?” Driving clinically relevant research with benchmark datasets
title_short	“Yes, but will it work for my patients?” Driving clinically relevant research with benchmark datasets
title_full	“Yes, but will it work for my patients?” Driving clinically relevant research with benchmark datasets
title_fullStr	“Yes, but will it work for my patients?” Driving clinically relevant research with benchmark datasets
title_full_unstemmed	“Yes, but will it work for my patients?” Driving clinically relevant research with benchmark datasets
title_sort	“yes, but will it work for my patients?” driving clinically relevant research with benchmark datasets
publisher	Nature Portfolio
publishDate	2020
url	https://doaj.org/article/137ec39e5c7443ce9fa5c7d8216b54ee
work_keys_str_mv	AT trishanpanch yesbutwillitworkformypatientsdrivingclinicallyrelevantresearchwithbenchmarkdatasets AT tomjpollard yesbutwillitworkformypatientsdrivingclinicallyrelevantresearchwithbenchmarkdatasets AT heathermattie yesbutwillitworkformypatientsdrivingclinicallyrelevantresearchwithbenchmarkdatasets AT emilylindemer yesbutwillitworkformypatientsdrivingclinicallyrelevantresearchwithbenchmarkdatasets AT pearseakeane yesbutwillitworkformypatientsdrivingclinicallyrelevantresearchwithbenchmarkdatasets AT leoanthonyceli yesbutwillitworkformypatientsdrivingclinicallyrelevantresearchwithbenchmarkdatasets
_version_	1718379690538827776

“Yes, but will it work for my patients?” Driving clinically relevant research with benchmark datasets

Ejemplares similares