https://scholars.lib.ntu.edu.tw/handle/123456789/606448
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.author | Dayan I | en_US |
dc.contributor.author | Roth H.R | en_US |
dc.contributor.author | Zhong A | en_US |
dc.contributor.author | Harouni A | en_US |
dc.contributor.author | Gentili A | en_US |
dc.contributor.author | Abidin A.Z | en_US |
dc.contributor.author | Liu A | en_US |
dc.contributor.author | Costa A.B | en_US |
dc.contributor.author | Wood B.J | en_US |
dc.contributor.author | Tsai C.-S | en_US |
dc.contributor.author | Wang C.-H | en_US |
dc.contributor.author | Hsu C.-N | en_US |
dc.contributor.author | Lee C.K | en_US |
dc.contributor.author | Ruan P | en_US |
dc.contributor.author | Xu D | en_US |
dc.contributor.author | Wu D | en_US |
dc.contributor.author | Huang E | en_US |
dc.contributor.author | Kitamura F.C | en_US |
dc.contributor.author | Lacey G | en_US |
dc.contributor.author | de Antônio Corradi G.C | en_US |
dc.contributor.author | Nino G | en_US |
dc.contributor.author | Shin H.-H | en_US |
dc.contributor.author | Obinata H | en_US |
dc.contributor.author | Ren H | en_US |
dc.contributor.author | Crane J.C | en_US |
dc.contributor.author | Tetreault J | en_US |
dc.contributor.author | Guan J | en_US |
dc.contributor.author | Garrett J.W | en_US |
dc.contributor.author | Kaggie J.D | en_US |
dc.contributor.author | Park J.G | en_US |
dc.contributor.author | Dreyer K | en_US |
dc.contributor.author | Juluru K | en_US |
dc.contributor.author | Kersten K | en_US |
dc.contributor.author | Rockenbach M.A.B.C | en_US |
dc.contributor.author | Linguraru M.G | en_US |
dc.contributor.author | Haider M.A | en_US |
dc.contributor.author | AbdelMaseeh M | en_US |
dc.contributor.author | Rieke N | en_US |
dc.contributor.author | Damasceno P.F | en_US |
dc.contributor.author | e Silva P.M.C | en_US |
dc.contributor.author | Wang P | en_US |
dc.contributor.author | Xu S | en_US |
dc.contributor.author | Kawano S | en_US |
dc.contributor.author | Sriswasdi S | en_US |
dc.contributor.author | Park S.Y | en_US |
dc.contributor.author | Grist T.M | en_US |
dc.contributor.author | Buch V | en_US |
dc.contributor.author | Jantarabenjakul W | en_US |
dc.contributor.author | WEICHUNG WANG | en_US |
dc.contributor.author | Tak W.Y | en_US |
dc.contributor.author | Li X | en_US |
dc.contributor.author | Lin X | en_US |
dc.contributor.author | Kwon Y.J | en_US |
dc.contributor.author | Quraini A | en_US |
dc.contributor.author | Feng A | en_US |
dc.contributor.author | Priest A.N | en_US |
dc.contributor.author | Turkbey B | en_US |
dc.contributor.author | Glicksberg B | en_US |
dc.contributor.author | Bizzo B | en_US |
dc.contributor.author | Kim B.S | en_US |
dc.contributor.author | Tor-Díez C | en_US |
dc.contributor.author | Lee C.-C | en_US |
dc.contributor.author | Hsu C.-J | en_US |
dc.contributor.author | Lin C | en_US |
dc.contributor.author | Lai C.-L | en_US |
dc.contributor.author | Hess C.P | en_US |
dc.contributor.author | Compas C | en_US |
dc.contributor.author | Bhatia D | en_US |
dc.contributor.author | Oermann E.K | en_US |
dc.contributor.author | Leibovitz E | en_US |
dc.contributor.author | Sasaki H | en_US |
dc.contributor.author | Mori H | en_US |
dc.contributor.author | Yang I | en_US |
dc.contributor.author | Sohn J.H | en_US |
dc.contributor.author | Murthy K.N.K | en_US |
dc.contributor.author | LI-CHEN FU | en_US |
dc.contributor.author | de Mendonça M.R.F | en_US |
dc.contributor.author | Fralick M | en_US |
dc.contributor.author | Kang M.K | en_US |
dc.contributor.author | Adil M | en_US |
dc.contributor.author | Gangai N | en_US |
dc.contributor.author | Vateekul P | en_US |
dc.contributor.author | Elnajjar P | en_US |
dc.contributor.author | Hickman S | en_US |
dc.contributor.author | Majumdar S | en_US |
dc.contributor.author | McLeod S.L | en_US |
dc.contributor.author | Reed S | en_US |
dc.contributor.author | Gräf S | en_US |
dc.contributor.author | Harmon S | en_US |
dc.contributor.author | Kodama T | en_US |
dc.contributor.author | Puthanakit T | en_US |
dc.contributor.author | Mazzulli T | en_US |
dc.contributor.author | de Lavor V.L | en_US |
dc.contributor.author | Rakvongthai Y | en_US |
dc.contributor.author | Lee Y.R | en_US |
dc.contributor.author | Wen Y | en_US |
dc.contributor.author | Gilbert F.J | en_US |
dc.contributor.author | Flores M.G | en_US |
dc.contributor.author | Li Q. | en_US |
dc.creator | Dayan I;Roth H.R;Zhong A;Harouni A;Gentili A;Abidin A.Z;Liu A;Costa A.B;Wood B.J;Tsai C.-S;Wang C.-H;Hsu C.-N;Lee C.K;Ruan P;Xu D;Wu D;Huang E;Kitamura F.C;Lacey G;de Ant?nio Corradi G.C;Nino G;Shin H.-H;Obinata H;Ren H;Crane J.C;Tetreault J;Guan J;Garrett J.W;Kaggie J.D;Park J.G;Dreyer K;Juluru K;Kersten K;Rockenbach M.A.B.C;Linguraru M.G;Haider M.A;AbdelMaseeh M;Rieke N;Damasceno P.F;e Silva P.M.C;Wang P;Xu S;Kawano S;Sriswasdi S;Park S.Y;Grist T.M;Buch V;Jantarabenjakul W;Wang W;Tak W.Y;Li X;Lin X;Kwon Y.J;Quraini A;Feng A;Priest A.N;Turkbey B;Glicksberg B;Bizzo B;Kim B.S;Tor-D?ez C;Lee C.-C;Hsu C.-J;Lin C;Lai C.-L;Hess C.P;Compas C;Bhatia D;Oermann E.K;Leibovitz E;Sasaki H;Mori H;Yang I;Sohn J.H;Murthy K.N.K;Fu L.-C;de Mendon?a M.R.F;Fralick M;Kang M.K;Adil M;Gangai N;Vateekul P;Elnajjar P;Hickman S;Majumdar S;McLeod S.L;Reed S;Gr?f S;Harmon S;Kodama T;Puthanakit T;Mazzulli T;de Lavor V.L;Rakvongthai Y;Lee Y.R;Wen Y;Gilbert F.J;Flores M.G;Li Q. | - |
dc.date.accessioned | 2022-04-25T06:25:25Z | - |
dc.date.available | 2022-04-25T06:25:25Z | - |
dc.date.issued | 2021 | - |
dc.identifier.issn | 10788956 | - |
dc.identifier.uri | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85115148251&doi=10.1038%2fs41591-021-01506-3&partnerID=40&md5=170b35467280264a48c10b40677c61ea | - |
dc.identifier.uri | https://scholars.lib.ntu.edu.tw/handle/123456789/606448 | - |
dc.description.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. ? 2021, The Author(s), under exclusive licence to Springer Nature America, Inc. | - |
dc.description.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. © 2021, The Author(s), under exclusive licence to Springer Nature America, Inc. | - |
dc.relation.ispartof | Nature Medicine | - |
dc.subject | C reactive protein | - |
dc.subject | oxygen | - |
dc.subject | adult | - |
dc.subject | Article | - |
dc.subject | artificial ventilation | - |
dc.subject | clinical outcome | - |
dc.subject | cohort analysis | - |
dc.subject | comparative study | - |
dc.subject | controlled study | - |
dc.subject | coronavirus disease 2019 | - |
dc.subject | electronic medical record | - |
dc.subject | emergency ward | - |
dc.subject | female | - |
dc.subject | health care system | - |
dc.subject | human | - |
dc.subject | male | - |
dc.subject | oxygen consumption | - |
dc.subject | oxygen therapy | - |
dc.subject | prediction | - |
dc.subject | sensitivity and specificity | - |
dc.subject | thorax radiography | - |
dc.subject | electronic health record | - |
dc.subject | isolation and purification | - |
dc.subject | machine learning | - |
dc.subject | pathophysiology | - |
dc.subject | prognosis | - |
dc.subject | therapy | - |
dc.subject | virology | - |
dc.subject | COVID-19 | - |
dc.subject | Electronic Health Records | - |
dc.subject | Humans | - |
dc.subject | Machine Learning | - |
dc.subject | Outcome Assessment, Health Care | - |
dc.subject | Prognosis | - |
dc.subject | SARS-CoV-2 | - |
dc.subject.classification | [SDGs]SDG3 | - |
dc.subject.other | C reactive protein; oxygen; adult; Article; artificial ventilation; clinical outcome; cohort analysis; comparative study; controlled study; coronavirus disease 2019; electronic medical record; emergency ward; female; health care system; human; male; oxygen consumption; oxygen therapy; prediction; sensitivity and specificity; thorax radiography; electronic health record; isolation and purification; machine learning; pathophysiology; prognosis; therapy; virology; COVID-19; Electronic Health Records; Humans; Machine Learning; Outcome Assessment, Health Care; Prognosis; SARS-CoV-2 | - |
dc.title | Federated learning for predicting clinical outcomes in patients with COVID-19 | en_US |
dc.type | journal article | en |
dc.identifier.doi | 10.1038/s41591-021-01506-3 | - |
dc.identifier.pmid | 34526699 | - |
dc.identifier.scopus | 2-s2.0-85115148251 | - |
dc.relation.pages | 1735-1743 | - |
dc.relation.journalvolume | 27 | - |
dc.relation.journalissue | 10 | - |
item.fulltext | no fulltext | - |
item.cerifentitytype | Publications | - |
item.openairetype | journal article | - |
item.openairecristype | http://purl.org/coar/resource_type/c_6501 | - |
item.grantfulltext | none | - |
crisitem.author.dept | Applied Mathematical Sciences | - |
crisitem.author.dept | Center for Artificial Intelligence and Advanced Robotics | - |
crisitem.author.dept | Electrical Engineering | - |
crisitem.author.dept | Computer Science and Information Engineering | - |
crisitem.author.dept | Center for Artificial Intelligence and Advanced Robotics | - |
crisitem.author.orcid | 0000-0002-6154-7750 | - |
crisitem.author.orcid | 0000-0002-6947-7646 | - |
crisitem.author.parentorg | College of Science | - |
crisitem.author.parentorg | Others: University-Level Research Centers | - |
crisitem.author.parentorg | College of Electrical Engineering and Computer Science | - |
crisitem.author.parentorg | College of Electrical Engineering and Computer Science | - |
crisitem.author.parentorg | Others: University-Level Research Centers | - |
顯示於: | 應用數學科學研究所 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。