Cargando…

MINIMAR (MINimum Information for Medical AI Reporting): Developing reporting standards for artificial intelligence in health care

The rise of digital data and computing power have contributed to significant advancements in artificial intelligence (AI), leading to the use of classification and prediction models in health care to enhance clinical decision-making for diagnosis, treatment and prognosis. However, such advances are...

Descripción completa

Detalles Bibliográficos
Autores principales: Hernandez-Boussard, Tina, Bozkurt, Selen, Ioannidis, John P A, Shah, Nigam H
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Oxford University Press 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7727333/
https://www.ncbi.nlm.nih.gov/pubmed/32594179
http://dx.doi.org/10.1093/jamia/ocaa088
_version_ 1783621076320780288
author Hernandez-Boussard, Tina
Bozkurt, Selen
Ioannidis, John P A
Shah, Nigam H
author_facet Hernandez-Boussard, Tina
Bozkurt, Selen
Ioannidis, John P A
Shah, Nigam H
author_sort Hernandez-Boussard, Tina
collection PubMed
description The rise of digital data and computing power have contributed to significant advancements in artificial intelligence (AI), leading to the use of classification and prediction models in health care to enhance clinical decision-making for diagnosis, treatment and prognosis. However, such advances are limited by the lack of reporting standards for the data used to develop those models, the model architecture, and the model evaluation and validation processes. Here, we present MINIMAR (MINimum Information for Medical AI Reporting), a proposal describing the minimum information necessary to understand intended predictions, target populations, and hidden biases, and the ability to generalize these emerging technologies. We call for a standard to accurately and responsibly report on AI in health care. This will facilitate the design and implementation of these models and promote the development and use of associated clinical decision support tools, as well as manage concerns regarding accuracy and bias.
format Online
Article
Text
id pubmed-7727333
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Oxford University Press
record_format MEDLINE/PubMed
spelling pubmed-77273332020-12-16 MINIMAR (MINimum Information for Medical AI Reporting): Developing reporting standards for artificial intelligence in health care Hernandez-Boussard, Tina Bozkurt, Selen Ioannidis, John P A Shah, Nigam H J Am Med Inform Assoc Perspectives The rise of digital data and computing power have contributed to significant advancements in artificial intelligence (AI), leading to the use of classification and prediction models in health care to enhance clinical decision-making for diagnosis, treatment and prognosis. However, such advances are limited by the lack of reporting standards for the data used to develop those models, the model architecture, and the model evaluation and validation processes. Here, we present MINIMAR (MINimum Information for Medical AI Reporting), a proposal describing the minimum information necessary to understand intended predictions, target populations, and hidden biases, and the ability to generalize these emerging technologies. We call for a standard to accurately and responsibly report on AI in health care. This will facilitate the design and implementation of these models and promote the development and use of associated clinical decision support tools, as well as manage concerns regarding accuracy and bias. Oxford University Press 2020-06-28 /pmc/articles/PMC7727333/ /pubmed/32594179 http://dx.doi.org/10.1093/jamia/ocaa088 Text en © The Author(s) 2020. Published by Oxford University Press on behalf of the American Medical Informatics Association. http://creativecommons.org/licenses/by-nc-nd/4.0/ This is an Open Access article distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs licence (http://creativecommons.org/licenses/by-nc-nd/4.0/), which permits non-commercial reproduction and distribution of the work, in any medium, provided the original work is not altered or transformed in any way, and that the work is properly cited. For commercial re-use, please contact journals.permissions@oup.com
spellingShingle Perspectives
Hernandez-Boussard, Tina
Bozkurt, Selen
Ioannidis, John P A
Shah, Nigam H
MINIMAR (MINimum Information for Medical AI Reporting): Developing reporting standards for artificial intelligence in health care
title MINIMAR (MINimum Information for Medical AI Reporting): Developing reporting standards for artificial intelligence in health care
title_full MINIMAR (MINimum Information for Medical AI Reporting): Developing reporting standards for artificial intelligence in health care
title_fullStr MINIMAR (MINimum Information for Medical AI Reporting): Developing reporting standards for artificial intelligence in health care
title_full_unstemmed MINIMAR (MINimum Information for Medical AI Reporting): Developing reporting standards for artificial intelligence in health care
title_short MINIMAR (MINimum Information for Medical AI Reporting): Developing reporting standards for artificial intelligence in health care
title_sort minimar (minimum information for medical ai reporting): developing reporting standards for artificial intelligence in health care
topic Perspectives
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7727333/
https://www.ncbi.nlm.nih.gov/pubmed/32594179
http://dx.doi.org/10.1093/jamia/ocaa088
work_keys_str_mv AT hernandezboussardtina minimarminimuminformationformedicalaireportingdevelopingreportingstandardsforartificialintelligenceinhealthcare
AT bozkurtselen minimarminimuminformationformedicalaireportingdevelopingreportingstandardsforartificialintelligenceinhealthcare
AT ioannidisjohnpa minimarminimuminformationformedicalaireportingdevelopingreportingstandardsforartificialintelligenceinhealthcare
AT shahnigamh minimarminimuminformationformedicalaireportingdevelopingreportingstandardsforartificialintelligenceinhealthcare