Impact of a deep learning assistant on the histopathologic classification of liver cancer

Abstract Artificial intelligence (AI) algorithms continue to rival human performance on a variety of clinical tasks, while their actual impact on human diagnosticians, when incorporated into clinical workflows, remains relatively unexplored. In this study, we developed a deep learning-based assistan...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Amirhossein Kiani, Bora Uyumazturk, Pranav Rajpurkar, Alex Wang, Rebecca Gao, Erik Jones, Yifan Yu, Curtis P. Langlotz, Robyn L. Ball, Thomas J. Montine, Brock A. Martin, Gerald J. Berry, Michael G. Ozawa, Florette K. Hazard, Ryanne A. Brown, Simon B. Chen, Mona Wood, Libby S. Allard, Lourdes Ylagan, Andrew Y. Ng, Jeanne Shen
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/615de5de8f5543b69db4c81e88e47231
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:615de5de8f5543b69db4c81e88e47231
record_format	dspace
spelling	oai:doaj.org-article:615de5de8f5543b69db4c81e88e472312021-12-02T13:34:33ZImpact of a deep learning assistant on the histopathologic classification of liver cancer10.1038/s41746-020-0232-82398-6352https://doaj.org/article/615de5de8f5543b69db4c81e88e472312020-02-01T00:00:00Zhttps://doi.org/10.1038/s41746-020-0232-8https://doaj.org/toc/2398-6352Abstract Artificial intelligence (AI) algorithms continue to rival human performance on a variety of clinical tasks, while their actual impact on human diagnosticians, when incorporated into clinical workflows, remains relatively unexplored. In this study, we developed a deep learning-based assistant to help pathologists differentiate between two subtypes of primary liver cancer, hepatocellular carcinoma and cholangiocarcinoma, on hematoxylin and eosin-stained whole-slide images (WSI), and evaluated its effect on the diagnostic performance of 11 pathologists with varying levels of expertise. Our model achieved accuracies of 0.885 on a validation set of 26 WSI, and 0.842 on an independent test set of 80 WSI. Although use of the assistant did not change the mean accuracy of the 11 pathologists (p = 0.184, OR = 1.281), it significantly improved the accuracy (p = 0.045, OR = 1.499) of a subset of nine pathologists who fell within well-defined experience levels (GI subspecialists, non-GI subspecialists, and trainees). In the assisted state, model accuracy significantly impacted the diagnostic decisions of all 11 pathologists. As expected, when the model’s prediction was correct, assistance significantly improved accuracy (p = 0.000, OR = 4.289), whereas when the model’s prediction was incorrect, assistance significantly decreased accuracy (p = 0.000, OR = 0.253), with both effects holding across all pathologist experience levels and case difficulty levels. Our results highlight the challenges of translating AI models into the clinical setting, and emphasize the importance of taking into account potential unintended negative consequences of model assistance when designing and testing medical AI-assistance tools.Amirhossein KianiBora UyumazturkPranav RajpurkarAlex WangRebecca GaoErik JonesYifan YuCurtis P. LanglotzRobyn L. BallThomas J. MontineBrock A. MartinGerald J. BerryMichael G. OzawaFlorette K. HazardRyanne A. BrownSimon B. ChenMona WoodLibby S. AllardLourdes YlaganAndrew Y. NgJeanne ShenNature PortfolioarticleComputer applications to medicine. Medical informaticsR858-859.7ENnpj Digital Medicine, Vol 3, Iss 1, Pp 1-8 (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 Amirhossein Kiani Bora Uyumazturk Pranav Rajpurkar Alex Wang Rebecca Gao Erik Jones Yifan Yu Curtis P. Langlotz Robyn L. Ball Thomas J. Montine Brock A. Martin Gerald J. Berry Michael G. Ozawa Florette K. Hazard Ryanne A. Brown Simon B. Chen Mona Wood Libby S. Allard Lourdes Ylagan Andrew Y. Ng Jeanne Shen Impact of a deep learning assistant on the histopathologic classification of liver cancer
description	Abstract Artificial intelligence (AI) algorithms continue to rival human performance on a variety of clinical tasks, while their actual impact on human diagnosticians, when incorporated into clinical workflows, remains relatively unexplored. In this study, we developed a deep learning-based assistant to help pathologists differentiate between two subtypes of primary liver cancer, hepatocellular carcinoma and cholangiocarcinoma, on hematoxylin and eosin-stained whole-slide images (WSI), and evaluated its effect on the diagnostic performance of 11 pathologists with varying levels of expertise. Our model achieved accuracies of 0.885 on a validation set of 26 WSI, and 0.842 on an independent test set of 80 WSI. Although use of the assistant did not change the mean accuracy of the 11 pathologists (p = 0.184, OR = 1.281), it significantly improved the accuracy (p = 0.045, OR = 1.499) of a subset of nine pathologists who fell within well-defined experience levels (GI subspecialists, non-GI subspecialists, and trainees). In the assisted state, model accuracy significantly impacted the diagnostic decisions of all 11 pathologists. As expected, when the model’s prediction was correct, assistance significantly improved accuracy (p = 0.000, OR = 4.289), whereas when the model’s prediction was incorrect, assistance significantly decreased accuracy (p = 0.000, OR = 0.253), with both effects holding across all pathologist experience levels and case difficulty levels. Our results highlight the challenges of translating AI models into the clinical setting, and emphasize the importance of taking into account potential unintended negative consequences of model assistance when designing and testing medical AI-assistance tools.
format	article
author	Amirhossein Kiani Bora Uyumazturk Pranav Rajpurkar Alex Wang Rebecca Gao Erik Jones Yifan Yu Curtis P. Langlotz Robyn L. Ball Thomas J. Montine Brock A. Martin Gerald J. Berry Michael G. Ozawa Florette K. Hazard Ryanne A. Brown Simon B. Chen Mona Wood Libby S. Allard Lourdes Ylagan Andrew Y. Ng Jeanne Shen
author_facet	Amirhossein Kiani Bora Uyumazturk Pranav Rajpurkar Alex Wang Rebecca Gao Erik Jones Yifan Yu Curtis P. Langlotz Robyn L. Ball Thomas J. Montine Brock A. Martin Gerald J. Berry Michael G. Ozawa Florette K. Hazard Ryanne A. Brown Simon B. Chen Mona Wood Libby S. Allard Lourdes Ylagan Andrew Y. Ng Jeanne Shen
author_sort	Amirhossein Kiani
title	Impact of a deep learning assistant on the histopathologic classification of liver cancer
title_short	Impact of a deep learning assistant on the histopathologic classification of liver cancer
title_full	Impact of a deep learning assistant on the histopathologic classification of liver cancer
title_fullStr	Impact of a deep learning assistant on the histopathologic classification of liver cancer
title_full_unstemmed	Impact of a deep learning assistant on the histopathologic classification of liver cancer
title_sort	impact of a deep learning assistant on the histopathologic classification of liver cancer
publisher	Nature Portfolio
publishDate	2020
url	https://doaj.org/article/615de5de8f5543b69db4c81e88e47231
work_keys_str_mv	AT amirhosseinkiani impactofadeeplearningassistantonthehistopathologicclassificationoflivercancer AT borauyumazturk impactofadeeplearningassistantonthehistopathologicclassificationoflivercancer AT pranavrajpurkar impactofadeeplearningassistantonthehistopathologicclassificationoflivercancer AT alexwang impactofadeeplearningassistantonthehistopathologicclassificationoflivercancer AT rebeccagao impactofadeeplearningassistantonthehistopathologicclassificationoflivercancer AT erikjones impactofadeeplearningassistantonthehistopathologicclassificationoflivercancer AT yifanyu impactofadeeplearningassistantonthehistopathologicclassificationoflivercancer AT curtisplanglotz impactofadeeplearningassistantonthehistopathologicclassificationoflivercancer AT robynlball impactofadeeplearningassistantonthehistopathologicclassificationoflivercancer AT thomasjmontine impactofadeeplearningassistantonthehistopathologicclassificationoflivercancer AT brockamartin impactofadeeplearningassistantonthehistopathologicclassificationoflivercancer AT geraldjberry impactofadeeplearningassistantonthehistopathologicclassificationoflivercancer AT michaelgozawa impactofadeeplearningassistantonthehistopathologicclassificationoflivercancer AT florettekhazard impactofadeeplearningassistantonthehistopathologicclassificationoflivercancer AT ryanneabrown impactofadeeplearningassistantonthehistopathologicclassificationoflivercancer AT simonbchen impactofadeeplearningassistantonthehistopathologicclassificationoflivercancer AT monawood impactofadeeplearningassistantonthehistopathologicclassificationoflivercancer AT libbysallard impactofadeeplearningassistantonthehistopathologicclassificationoflivercancer AT lourdesylagan impactofadeeplearningassistantonthehistopathologicclassificationoflivercancer AT andrewyng impactofadeeplearningassistantonthehistopathologicclassificationoflivercancer AT jeanneshen impactofadeeplearningassistantonthehistopathologicclassificationoflivercancer
_version_	1718392739021717504

Impact of a deep learning assistant on the histopathologic classification of liver cancer

Ejemplares similares