Nature Medicine

, volume 27 , issue 10 , pages 1735-1743

Federated learning for predicting clinical outcomes in patients with COVID-19

Ittai Dayan ¹

Holger Roth ²

Aoxiao Zhong ^{3, 4}

Ahmed Harouni ²

AMILCARE GENTILI ⁵

Anas Z Abidin ²

Andrew Liu ²

Anthony Costa ⁶

Bradford J. Wood ^{7, 8}

Chien-Sung Tsai ⁹

Chih-Hung Wang ^{10, 11}

Chun-Nan Hsu ¹²

C. K. Lee ²

Peiying Ruan ²

Daguang Xu ²

Dufan Wu ³

Eddie Huang ²

Felipe C. Kitamura ¹³

Griffin Lacey ²

Gustavo César De Antônio Corradi ¹³

Gustavo Nino ¹⁴

Hao-Hsin Shih ¹⁵

Hirofumi Obinata ¹⁶

Hui Ren Hui ³

Jason C Crane ¹⁷

Jesse Tetreault ²

Jiahui Guan ²

John W. Garrett ¹⁸

Joshua D Kaggie ¹⁹

Jun Kyun Park ²⁰

Keith Dreyer ^{1, 21}

Krishna Juluru ¹⁵

Kristopher Kersten ²

Marcio Aloisio Bezerra Cavalcanti Rockenbach ²¹

Marius George Linguraru ^{22, 23}

Masoom A. Haider ^{24, 25}

Meena Abdelmaseeh ²⁵

Nicola Rieke ²

Pablo F. Damasceno ¹⁷

Pedro Mario Cruz E Silva ²

Pochuan Wang ^{26, 27}

Sheng Xu ^{7, 8}

Shuichi Kawano ¹⁶

Sira Sriswasdi ^{28, 29}

Soo Young Park ³⁰

Thomas M. Grist ³¹

Varun Buch ²¹

Watsamon Jantarabenjakul ^{32, 33}

Weichung Wang ^{26, 27}

Won Young Tak ³⁰

X. Li ³

Xihong Lin ³⁴

Young Joon Kwon ⁶

Abood Quraini ²

Andrew Feng ²

Andrew W. Priest ³⁵

Baris Turkbey ^{8, 36}

Benjamin S Glicksberg ³⁷

Bernardo C. Bizzo ²¹

Byung-Seok Kim ³⁸

Carlos Tor Diez ²²

Chia-Cheng Lee ³⁹

Chia-Jung Hsu ³⁹

Chin Lin ^{40, 41, 42}

Chiu-Ling Lai ⁴³

Christopher P. Hess ¹⁷

Colin Compas ²

Deepeksha Bhatia ²

Eric K. Oermann ⁴⁴

Evan Leibovitz ²¹

Hisashi Sasaki ¹⁶

Hitoshi Mori ¹⁶

Isaac Yang ²

Jae Ho Sohn ¹⁷

Krishna Nand Keshava Murthy ¹⁵

Li-Chen Fu ⁴⁵

Matheus Ribeiro Furtado de Mendonça ¹³

Mike Fralick ⁴⁶

Min Kyu Kang ²⁰

Adil Mohammad ²

Natalie Gangai ¹⁵

Peerapon Vateekul ⁴⁷

Pierre Elnajjar ¹⁵

Sarah Hickman ¹⁹

Sharmila Majumdar ¹⁷

Shelley L. McLeod ^{48, 49}

Sheridan Reed ^{7, 8}

Stefan Gräf ⁵⁰

Stephanie Harmon ^{8, 51}

Tatsuya Kodama ¹⁶

Thanyawee Puthanakit ^{32, 33}

Tony Mazzulli ^{52, 53, 54}

Vitor Lima De Lavor ¹³

Yothin Rakvongthai ⁵⁵

Yu Rim Lee ³⁰

Yuhong Wen ²

Fiona J. Gilbert ¹⁹

Mona G. Flores ²

Quanzheng Li ³

Hide authors affiliations Show authors affiliations: 55 affiliations

MGH Radiology and Harvard Medical School, Boston, USA

Harvard University

Massachusetts General Hospital

Nvidia, Santa Clara, USA |

Center for Advanced Medical Computing and Analysis, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, USA

Harvard University

Massachusetts General Hospital

⁴

School of Engineering and Applied Sciences, Harvard University, Boston, USA |

⁵

San Diego VA Health Care System, San Diego, USA |

⁶

Department of Neurosurgery, Icahn School of Medicine at Mount Sinai, New York, USA |

⁷

Radiology & Imaging Sciences/Clinical Center, National Institutes of Health, Bethesda, USA |

⁸

National Cancer Institute, National Institutes of Health, Bethesda, USA |

⁹

Division of Cardiovascular surgery, Department of Surgery, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan |

¹⁰

Department of Otolaryngology–Head and Neck Surgery, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan |

¹¹

Graduate Institute of Medical Sciences, National Defense Medical Center, Taipei, Taiwan |

¹²

Center for Research in Biological Systems, University of California, San Diego, USA |

¹³

DasaInova, Diagnósticos da América SA, Barueri, Brazil |

¹⁴

Division of Pediatric Pulmonary and Sleep Medicine, Children’s National Hospital, Washington, USA |

¹⁵

Memorial Sloan Kettering Cancer Center, New York, USA |

¹⁶

Self-Defense Forces Central Hospital, Tokyo, Japan |

¹⁷

Center for Intelligent Imaging, Department of Radiology and Biomedical Imaging, University of California, San Francisco, USA |

¹⁸

Departments of Radiology and Medical Physics, The University of Wisconsin-Madison School of Medicine and Public Health, Madison, USA |

¹⁹

Department of Radiology, NIHR Cambridge Biomedical Resource Centre, University of Cambridge, Cambridge, UK

University of Cambridge

NIHR Cambridge Biomedical Research Centre

²⁰

Department of Internal Medicine, Yeungnam University College of medicine, Daegu, South Korea |

²¹

Center for Clinical Data Science, Massachusetts General Brigham, Boston, USA |

²²

Sheikh Zayed Institute for Pediatric Surgical Innovation, Children’s National Hospital, Washington, USA |

²³

Departments of Radiology and Pediatrics, The George Washington University School of Medicine and Health Sciences, Washington, USA |

²⁴

Joint Dept. of Medical Imaging, Sinai Health System, University of Toronto, Toronto, Canada |

²⁵

Lunenfeld-Tanenbaum Research Institute, Toronto, Canada |

²⁶

MeDA Lab Institute of Applied Mathematical Sciences, National Taiwan University, Taipei, Taiwan |

²⁷

Department of Computer Science and Information Engineering, National Taiwan University, Taipei, TAIWAN |

²⁸

Research Affairs, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand |

²⁹

Center for Artificial Intelligence in Medicine, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand |

³⁰

Department of Internal Medicine, School of Medicine, Kyungpook National University, Daegu, South Korea |

³¹

Departments of Radiology, Medical Physics, and Biomedical Engineering, The University of Wisconsin-Madison School of Medicine and Public Health, Madison, USA |

³²

Department of Pediatrics, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand |

³³

Thai Red Cross Emerging Infectious Diseases Clinical Center, King Chulalongkorn Memorial Hospital, Bangkok, Thailand |

³⁴

Harvard T.H. Chan School of Public Health, Harvard University, Boston, USA |

³⁵

Department of Radiology, NIHR Cambridge Biomedical Resource Centre, Cambridge University Hospital, Cambridge, UK

Cambridge University Hospitals NHS Foundation Trust

NIHR Cambridge Biomedical Research Centre

³⁶

Department of Radiology and Imaging Sciences, National Institutes of Health, Bethesda, USA |

³⁷

Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai and Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, USA |

³⁸

Department of Internal Medicine, Catholic University of Daegu School of Medicine, Daegu, South Korea |

³⁹

Planning and Management Office, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan |

⁴⁰

School of Medicine, National Defense Medical Center, Taipei, Taiwan |

⁴¹

School of Public Health, National Defense Medical Center, Taipei, Taiwan |

⁴²

Graduate Institute of Life Sciences, National Defense Medical Center, Taipei, Taiwan |

⁴³

Medical Review and Pharmaceutical Benefits Division, National Health Insurance Administration, Taipei, Taiwan |

⁴⁴

Department of Neurosurgery, NYU Grossman School of Medicine, New York, USA |

⁴⁵

MOST/NTU All Vista Healthcare Center, Center for Artificial Intelligence and Advanced Robotics, National Taiwan University, Taipei, Taiwan |

⁴⁶

Division of General Internal Medicine and Geriatrics (Fralick), Sinai Health System, Toronto, Canada |

⁴⁷

Department of Computer Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok, Thailand |

⁴⁸

Schwartz/Reisman Emergency Medicine Institute, Sinai Health, Toronto, Canada |

⁴⁹

Department of Family and Community Medicine, University of Toronto, Toronto, Canada |

⁵⁰

Department of Medicine and NIHR BioResource for Translational Research, NIHR Cambridge Biomedical Research Centre, University of Cambridge, Cambridge, UK

University of Cambridge

NIHR Cambridge Biomedical Research Centre

⁵¹

Clinical Research Directorate, Frederick National Laboratory for Cancer, National Cancer Institute, Frederick, USA |

⁵²

Department of Microbiology, Sinai Health/University Health Network, Toronto, Canada |

⁵³

Department of Laboratory Medicine and Pathobiology, University Of Toronto, Toronto, Canada |

⁵⁴

Public Health Ontario Laboratories, Toronto, Canada |

⁵⁵

Chulalongkorn University Biomedical Imaging Group and Division of Nuclear Medicine, Department of Radiology, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand |

Publication type: Journal Article

Publication date: 2021-09-15

Springer Nature

Nature Medicine

scimago Q1

wos Q1

SJR: 18.333

CiteScore: 82.4

Impact factor: 50.0

ISSN: 10788956, 1546170X, 17447933

DOI: 10.1038/s41591-021-01506-3

Copy DOI

PubMed ID: 34526699

General Biochemistry, Genetics and Molecular Biology

General Medicine

Abstract

Federated learning (FL) is a method used for training artificial intelligence models with data from multiple sources while maintaining data anonymity, thus removing many barriers to data sharing. Here we used data from 20 institutes across the globe to train a FL model, called EXAM (electronic medical record (EMR) chest X-ray AI model), that predicts the future oxygen requirements of symptomatic patients with COVID-19 using inputs of vital signs, laboratory data and chest X-rays. EXAM achieved an average area under the curve (AUC) >0.92 for predicting outcomes at 24 and 72 h from the time of initial presentation to the emergency room, and it provided 16% improvement in average AUC measured across all participating sites and an average increase in generalizability of 38% when compared with models trained at a single site using that site’s data. For prediction of mechanical ventilation treatment or death at 24 h at the largest independent test site, EXAM achieved a sensitivity of 0.950 and specificity of 0.882. In this study, FL facilitated rapid data science collaboration without data exchange and generated a model that generalized across heterogeneous, unharmonized datasets for prediction of clinical outcomes in patients with COVID-19, setting the stage for the broader use of FL in healthcare. Federated learning, a method for training artificial intelligence algorithms that protects data privacy, was used to predict future oxygen requirements of symptomatic patients with COVID-19 using data from 20 different institutes across the globe.

Found

2 citations

Bujotzek Markus

3 publications, 14 citations

h-index: 3

German Cancer Research Center

Heidelberg University

1 citation

Nadella Geeta Sandeep

🥼 🤝

PhD in Engineering, full member of the Academia Europaea

51 publications, 212 citations, 396 reviews

h-index: 9

University of the Cumberlands

Human-Computer Interaction

Information systems

Statistics

Top-30

Journals

	5 10 15 20 25
Lecture Notes in Computer Science	Lecture Notes in Computer Science, 22, 4.21% Lecture Notes in Computer Science 22 publications, 4.21%
npj Digital Medicine	npj Digital Medicine, 11, 2.1% npj Digital Medicine 11 publications, 2.1%
IEEE Access	IEEE Access, 10, 1.91% IEEE Access 10 publications, 1.91%
IEEE Transactions on Medical Imaging	IEEE Transactions on Medical Imaging, 10, 1.91% IEEE Transactions on Medical Imaging 10 publications, 1.91%
Nature Communications	Nature Communications, 8, 1.53% Nature Communications 8 publications, 1.53%
Scientific Reports	Scientific Reports, 8, 1.53% Scientific Reports 8 publications, 1.53%
Diagnostics	Diagnostics, 6, 1.15% Diagnostics 6 publications, 1.15%
Medical Image Analysis	Medical Image Analysis, 6, 1.15% Medical Image Analysis 6 publications, 1.15%
Patterns	Patterns, 6, 1.15% Patterns 6 publications, 1.15%
IEEE Internet of Things Journal	IEEE Internet of Things Journal, 6, 1.15% IEEE Internet of Things Journal 6 publications, 1.15%
Communications in Computer and Information Science	Communications in Computer and Information Science, 6, 1.15% Communications in Computer and Information Science 6 publications, 1.15%
Electronics (Switzerland)	Electronics (Switzerland), 5, 0.96% Electronics (Switzerland) 5 publications, 0.96%
IEEE Journal of Biomedical and Health Informatics	IEEE Journal of Biomedical and Health Informatics, 5, 0.96% IEEE Journal of Biomedical and Health Informatics 5 publications, 0.96%
IEEE Transactions on Neural Networks and Learning Systems	IEEE Transactions on Neural Networks and Learning Systems, 5, 0.96% IEEE Transactions on Neural Networks and Learning Systems 5 publications, 0.96%
Applied Sciences (Switzerland)	Applied Sciences (Switzerland), 4, 0.76% Applied Sciences (Switzerland) 4 publications, 0.76%
BMC Medical Informatics and Decision Making	BMC Medical Informatics and Decision Making, 4, 0.76% BMC Medical Informatics and Decision Making 4 publications, 0.76%
Computers in Biology and Medicine	Computers in Biology and Medicine, 4, 0.76% Computers in Biology and Medicine 4 publications, 0.76%
Journal of the American Medical Informatics Association : JAMIA	Journal of the American Medical Informatics Association : JAMIA, 4, 0.76% Journal of the American Medical Informatics Association : JAMIA 4 publications, 0.76%
Journal of Medical Internet Research	Journal of Medical Internet Research, 4, 0.76% Journal of Medical Internet Research 4 publications, 0.76%
Advances in Healthcare Information Systems and Administration	Advances in Healthcare Information Systems and Administration, 4, 0.76% Advances in Healthcare Information Systems and Administration 4 publications, 0.76%
British Journal of Radiology	British Journal of Radiology, 3, 0.57% British Journal of Radiology 3 publications, 0.57%
Radiology Artificial Intelligence	Radiology Artificial Intelligence, 3, 0.57% Radiology Artificial Intelligence 3 publications, 0.57%
Digital Health	Digital Health, 3, 0.57% Digital Health 3 publications, 0.57%
Healthcare	Healthcare, 3, 0.57% Healthcare 3 publications, 0.57%
Sensors	Sensors, 3, 0.57% Sensors 3 publications, 0.57%
Future Generation Computer Systems	Future Generation Computer Systems, 3, 0.57% Future Generation Computer Systems 3 publications, 0.57%
Knowledge-Based Systems	Knowledge-Based Systems, 3, 0.57% Knowledge-Based Systems 3 publications, 0.57%
IEEE Reviews in Biomedical Engineering	IEEE Reviews in Biomedical Engineering, 3, 0.57% IEEE Reviews in Biomedical Engineering 3 publications, 0.57%
Lecture Notes in Networks and Systems	Lecture Notes in Networks and Systems, 3, 0.57% Lecture Notes in Networks and Systems 3 publications, 0.57%
	5 10 15 20 25

Publishers

	20 40 60 80 100 120 140
Springer Nature	Springer Nature, 121, 23.14% Springer Nature 121 publications, 23.14%
Institute of Electrical and Electronics Engineers (IEEE)	Institute of Electrical and Electronics Engineers (IEEE), 119, 22.75% Institute of Electrical and Electronics Engineers (IEEE) 119 publications, 22.75%
Elsevier	Elsevier, 96, 18.36% Elsevier 96 publications, 18.36%
MDPI	MDPI, 44, 8.41% MDPI 44 publications, 8.41%
Cold Spring Harbor Laboratory	Cold Spring Harbor Laboratory, 16, 3.06% Cold Spring Harbor Laboratory 16 publications, 3.06%
Wiley	Wiley, 14, 2.68% Wiley 14 publications, 2.68%
Oxford University Press	Oxford University Press, 13, 2.49% Oxford University Press 13 publications, 2.49%
Frontiers Media S.A.	Frontiers Media S.A., 10, 1.91% Frontiers Media S.A. 10 publications, 1.91%
Ovid Technologies (Wolters Kluwer Health)	Ovid Technologies (Wolters Kluwer Health), 10, 1.91% Ovid Technologies (Wolters Kluwer Health) 10 publications, 1.91%
Association for Computing Machinery (ACM)	Association for Computing Machinery (ACM), 9, 1.72% Association for Computing Machinery (ACM) 9 publications, 1.72%
IGI Global	IGI Global, 8, 1.53% IGI Global 8 publications, 1.53%
SAGE	SAGE, 7, 1.34% SAGE 7 publications, 1.34%
Taylor & Francis	Taylor & Francis, 6, 1.15% Taylor & Francis 6 publications, 1.15%
Public Library of Science (PLoS)	Public Library of Science (PLoS), 5, 0.96% Public Library of Science (PLoS) 5 publications, 0.96%
JMIR Publications	JMIR Publications, 5, 0.96% JMIR Publications 5 publications, 0.96%
Radiological Society of North America (RSNA)	Radiological Society of North America (RSNA), 4, 0.76% Radiological Society of North America (RSNA) 4 publications, 0.76%
British Institute of Radiology	British Institute of Radiology, 3, 0.57% British Institute of Radiology 3 publications, 0.57%
Bentham Science Publishers Ltd.	Bentham Science Publishers Ltd., 2, 0.38% Bentham Science Publishers Ltd. 2 publications, 0.38%
Georg Thieme Verlag KG	Georg Thieme Verlag KG, 2, 0.38% Georg Thieme Verlag KG 2 publications, 0.38%
Institute for Operations Research and the Management Sciences (INFORMS)	Institute for Operations Research and the Management Sciences (INFORMS), 2, 0.38% Institute for Operations Research and the Management Sciences (INFORMS) 2 publications, 0.38%
American Medical Association (AMA)	American Medical Association (AMA), 2, 0.38% American Medical Association (AMA) 2 publications, 0.38%
BMJ	BMJ, 2, 0.38% BMJ 2 publications, 0.38%
American Chemical Society (ACS)	American Chemical Society (ACS), 2, 0.38% American Chemical Society (ACS) 2 publications, 0.38%
Emerald	Emerald, 1, 0.19% Emerald 1 publication, 0.19%
American Society for Microbiology	American Society for Microbiology, 1, 0.19% American Society for Microbiology 1 publication, 0.19%
AIP Publishing	AIP Publishing, 1, 0.19% AIP Publishing 1 publication, 0.19%
Institute of Electronics, Information and Communications Engineers (IEICE)	Institute of Electronics, Information and Communications Engineers (IEICE), 1, 0.19% Institute of Electronics, Information and Communications Engineers (IEICE) 1 publication, 0.19%
American Association for the Advancement of Science (AAAS)	American Association for the Advancement of Science (AAAS), 1, 0.19% American Association for the Advancement of Science (AAAS) 1 publication, 0.19%
Mary Ann Liebert	Mary Ann Liebert, 1, 0.19% Mary Ann Liebert 1 publication, 0.19%
	20 40 60 80 100 120 140

We do not take into account publications without a DOI.
Statistics recalculated weekly.

Are you a researcher?

Create a profile to get free access to personal recommendations for colleagues and new articles.

Metrics

526

Cite this

GOST |

Cite this

GOST Copy

Dayan I. et al. Federated learning for predicting clinical outcomes in patients with COVID-19 // Nature Medicine. 2021. Vol. 27. No. 10. pp. 1735-1743.

GOST all authors (up to 50) Copy

Dayan I. et al. Federated learning for predicting clinical outcomes in patients with COVID-19 // Nature Medicine. 2021. Vol. 27. No. 10. pp. 1735-1743.

RIS |

Cite this

RIS

BibTex |

Cite this

BibTex (up to 50 authors) Copy

@article{2021_Dayan,

author = {Ittai Dayan and Holger Roth and Aoxiao Zhong and Ahmed Harouni and AMILCARE GENTILI and Anas Z Abidin and Andrew Liu and Anthony Costa and Bradford J. Wood and Chien-Sung Tsai and Chih-Hung Wang and Chun-Nan Hsu and C. K. Lee and Peiying Ruan and Daguang Xu and Dufan Wu and Eddie Huang and Felipe C. Kitamura and Griffin Lacey and Gustavo César De Antônio Corradi and Gustavo Nino and Hao-Hsin Shih and Hirofumi Obinata and Hui Ren Hui and Jason C Crane and Jesse Tetreault and Jiahui Guan and John W. Garrett and Joshua D Kaggie and Jun Kyun Park and Keith Dreyer and Krishna Juluru and Kristopher Kersten and Marcio Aloisio Bezerra Cavalcanti Rockenbach and Marius George Linguraru and Masoom A. Haider and Meena Abdelmaseeh and Nicola Rieke and Pablo F. Damasceno and Pedro Mario Cruz E Silva and Pochuan Wang and Sheng Xu and Shuichi Kawano and Sira Sriswasdi and Soo Young Park and Thomas M. Grist and Varun Buch and Watsamon Jantarabenjakul and Weichung Wang and Won Young Tak and others},

title = {Federated learning for predicting clinical outcomes in patients with COVID-19},

journal = {Nature Medicine},

year = {2021},

volume = {27},

publisher = {Springer Nature},

month = {sep},

url = {https://doi.org/10.1038/s41591-021-01506-3},

number = {10},

pages = {1735--1743},

doi = {10.1038/s41591-021-01506-3}

}

MLA

Cite this

MLA Copy

Dayan, Ittai, et al. “Federated learning for predicting clinical outcomes in patients with COVID-19.” Nature Medicine, vol. 27, no. 10, Sep. 2021, pp. 1735-1743. https://doi.org/10.1038/s41591-021-01506-3.

Publisher

Springer Nature

Journal

Nature Medicine

scimago Q1

wos Q1

SJR

18.333

CiteScore

82.4

Impact factor

50.0

ISSN

10788956 (Print)

1546170X (Electronic)

17447933 (Electronic)