The future of digital health with federated learning

被引：1253

作者：

Rieke, Nicola ^{[1
,2
]}

Hancox, Jonny ^{[3
]}

Li, Wenqi ^{[4
]}

Milletari, Fausto ^{[1
]}

Roth, Holger R. ^{[5
]}

Albarqouni, Shadi ^{[2
,6
]}

Bakas, Spyridon ^{[7
]}

Galtier, Mathieu N. ^{[8
]}

Landman, Bennett A. ^{[9
]}

Maier-Hein, Klaus ^{[10
,11
]}

Ourselin, Sebastien ^{[12
]}

Sheller, Micah ^{[13
]}

Summers, Ronald M. ^{[14
]}

Trask, Andrew ^{[15
,16
,17
]}

Xu, Daguang ^{[5
]}

Baust, Maximilian ^{[1
]}

Cardoso, M. Jorge ^{[12
]}

机构：

[1] NVIDIA GmbH, Munich, Germany

[2] Tech Univ Munich TUM, Munich, Germany

[3] NVIDIA Ltd, Reading, Berks, England

[4] NVIDIA Ltd, Cambridge, England

[5] NVIDIA Corp, Bethesda, MD USA

[6] Imperial Coll London, London, England

[7] Univ Penn UPenn, Philadelphia, PA USA

[8] Owkin, Paris, France

[9] Vanderbilt Univ, 221 Kirkland Hall, Nashville, TN 37235 USA

[10] German Canc Res Ctr, Heidelberg, Germany

[11] Heidelberg Univ Hosp, Heidelberg, Germany

[12] Kings Coll London KCL, London, England

[13] Intel Corp, Santa Clara, CA USA

[14] NIH, Ctr Clin, Bethesda, MD 20892 USA

[15] OpenMined, Oxford, England

[16] Univ Oxford, Oxford, England

[17] Ctr Governance AI GovAI, Oxford, England

来源：

NPJ DIGITAL MEDICINE | 2020年 / 3卷 / 01期

基金：

英国工程与自然科学研究理事会; 英国科研创新办公室; 美国国家卫生研究院;

关键词：

E-learning;

D O I：

10.1038/s41746-020-00323-1

中图分类号：

R19 [保健组织与事业（卫生事业管理）];

学科分类号：

摘要：

Data-driven machine learning (ML) has emerged as a promising approach for building accurate and robust statistical models from medical data, which is collected in huge volumes by modern healthcare systems. Existing medical data is not fully exploited by ML primarily because it sits in data silos and privacy concerns restrict access to this data. However, without access to sufficient data, ML will be prevented from reaching its full potential and, ultimately, from making the transition from research to clinical practice. This paper considers key factors contributing to this issue, explores how federated learning (FL) may provide a solution for the future of digital health and highlights the challenges and considerations that need to be addressed.

引用

页数：7

共 58 条

[1] Deep Learning with Differential Privacy [J].

Abadi, Martin ;

Chu, Andy ;

Goodfellow, Ian ;

McMahan, H. Brendan ;

Mironov, Ilya ;

Talwar, Kunal ;

Zhang, Li .

CCS'16: PROCEEDINGS OF THE 2016 ACM SIGSAC CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY, 2016, :308-318

[2]

[Anonymous], 2020, GRAND CHALLENGE PLAT

[3]

[Anonymous], 2015, NHS SCOTLANDS NATL S

[4]

[Anonymous], 2020, MACHINE LEARNING LED

[5]

Bakas S, 2019, IDENTIFYING BEST MAC

[6] Data Descriptor: Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features [J].

Bakas, Spyridon ;

Akbari, Hamed ;

Sotiras, Aristeidis ;

Bilello, Michel ;

Rozycki, Martin ;

Kirby, Justin S. ;

Freymann, John B. ;

Farahani, Keyvan ;

Davatzikos, Christos .

SCIENTIFIC DATA, 2017, 4

[7] Federated learning of predictive models from federated Electronic Health Records [J].

Brisimi, Theodora S. ;

Chen, Ruidi ;

Mela, Theofanie ;

Olshevsky, Alex ;

Paschalidis, Ioannis Ch. ;

Shi, Wei .

INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS, 2018, 112 :59-67

[8]

Carlini N, 2019, PROCEEDINGS OF THE 28TH USENIX SECURITY SYMPOSIUM, P267

[9] Distributed deep learning networks among institutions for medical imaging [J].

Chang, Ken ;

Balachandar, Niranjan ;

Lam, Carson ;

Yi, Darvin ;

Brown, James ;

Beers, Andrew ;

Rosen, Bruce ;

Rubin, Daniel L. ;

Kalpathy-Cramer, Jayashree .

JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION, 2018, 25 (08) :945-954

[10] Deep Learning: A Primer for Radiologists [J].

Chartrand, Gabriel ;

Cheng, Phillip M. ;

Vorontsov, Eugene ;

Drozdzal, Michal ;

Turcotte, Simon ;

Pal, Christopher J. ;

Kadoury, Samuel ;

Tang, An .

RADIOGRAPHICS, 2017, 37 (07) :2113-2131

← 1 2 3 4 5 6 →