Automated detection of poor-quality data: case studies in healthcare

Abstract The detection and removal of poor-quality data in a training set is crucial to achieve high-performing AI models. In healthcare, data can be inherently poor-quality due to uncertainty or subjectivity, but as is often the case, the requirement for data privacy restricts AI practitioners from...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	M. A. Dakka, T. V. Nguyen, J. M. M. Hall, S. M. Diakiw, M. VerMilyea, R. Linke, M. Perugini, D. Perugini
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/92ef4fc958d544dcababaa3db903e24e
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:92ef4fc958d544dcababaa3db903e24e
record_format	dspace
spelling	oai:doaj.org-article:92ef4fc958d544dcababaa3db903e24e2021-12-02T17:19:16ZAutomated detection of poor-quality data: case studies in healthcare10.1038/s41598-021-97341-02045-2322https://doaj.org/article/92ef4fc958d544dcababaa3db903e24e2021-09-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-97341-0https://doaj.org/toc/2045-2322Abstract The detection and removal of poor-quality data in a training set is crucial to achieve high-performing AI models. In healthcare, data can be inherently poor-quality due to uncertainty or subjectivity, but as is often the case, the requirement for data privacy restricts AI practitioners from accessing raw training data, meaning manual visual verification of private patient data is not possible. Here we describe a novel method for automated identification of poor-quality data, called Untrainable Data Cleansing. This method is shown to have numerous benefits including protection of private patient data; improvement in AI generalizability; reduction in time, cost, and data needed for training; all while offering a truer reporting of AI performance itself. Additionally, results show that Untrainable Data Cleansing could be useful as a triage tool to identify difficult clinical cases that may warrant in-depth evaluation or additional testing to support a diagnosis.M. A. DakkaT. V. NguyenJ. M. M. HallS. M. DiakiwM. VerMilyeaR. LinkeM. PeruginiD. PeruginiNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q M. A. Dakka T. V. Nguyen J. M. M. Hall S. M. Diakiw M. VerMilyea R. Linke M. Perugini D. Perugini Automated detection of poor-quality data: case studies in healthcare
description	Abstract The detection and removal of poor-quality data in a training set is crucial to achieve high-performing AI models. In healthcare, data can be inherently poor-quality due to uncertainty or subjectivity, but as is often the case, the requirement for data privacy restricts AI practitioners from accessing raw training data, meaning manual visual verification of private patient data is not possible. Here we describe a novel method for automated identification of poor-quality data, called Untrainable Data Cleansing. This method is shown to have numerous benefits including protection of private patient data; improvement in AI generalizability; reduction in time, cost, and data needed for training; all while offering a truer reporting of AI performance itself. Additionally, results show that Untrainable Data Cleansing could be useful as a triage tool to identify difficult clinical cases that may warrant in-depth evaluation or additional testing to support a diagnosis.
format	article
author	M. A. Dakka T. V. Nguyen J. M. M. Hall S. M. Diakiw M. VerMilyea R. Linke M. Perugini D. Perugini
author_facet	M. A. Dakka T. V. Nguyen J. M. M. Hall S. M. Diakiw M. VerMilyea R. Linke M. Perugini D. Perugini
author_sort	M. A. Dakka
title	Automated detection of poor-quality data: case studies in healthcare
title_short	Automated detection of poor-quality data: case studies in healthcare
title_full	Automated detection of poor-quality data: case studies in healthcare
title_fullStr	Automated detection of poor-quality data: case studies in healthcare
title_full_unstemmed	Automated detection of poor-quality data: case studies in healthcare
title_sort	automated detection of poor-quality data: case studies in healthcare
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/92ef4fc958d544dcababaa3db903e24e
work_keys_str_mv	AT madakka automateddetectionofpoorqualitydatacasestudiesinhealthcare AT tvnguyen automateddetectionofpoorqualitydatacasestudiesinhealthcare AT jmmhall automateddetectionofpoorqualitydatacasestudiesinhealthcare AT smdiakiw automateddetectionofpoorqualitydatacasestudiesinhealthcare AT mvermilyea automateddetectionofpoorqualitydatacasestudiesinhealthcare AT rlinke automateddetectionofpoorqualitydatacasestudiesinhealthcare AT mperugini automateddetectionofpoorqualitydatacasestudiesinhealthcare AT dperugini automateddetectionofpoorqualitydatacasestudiesinhealthcare
_version_	1718381039053701120

Automated detection of poor-quality data: case studies in healthcare

Ejemplares similares