Privacy-Preserving Artificial Intelligence Techniques in Biomedicine.


Journal

Methods of information in medicine
ISSN: 2511-705X
Titre abrégé: Methods Inf Med
Pays: Germany
ID NLM: 0210453

Informations de publication

Date de publication:
06 2022
Historique:
pubmed: 22 1 2022
medline: 6 7 2022
entrez: 21 1 2022
Statut: ppublish

Résumé

Artificial intelligence (AI) has been successfully applied in numerous scientific domains. In biomedicine, AI has already shown tremendous potential, e.g., in the interpretation of next-generation sequencing data and in the design of clinical decision support systems. However, training an AI model on sensitive data raises concerns about the privacy of individual participants. For example, summary statistics of a genome-wide association study can be used to determine the presence or absence of an individual in a given dataset. This considerable privacy risk has led to restrictions in accessing genomic and other biomedical data, which is detrimental for collaborative research and impedes scientific progress. Hence, there has been a substantial effort to develop AI methods that can learn from sensitive data while protecting individuals' privacy. This paper provides a structured overview of recent advances in privacy-preserving AI techniques in biomedicine. It places the most important state-of-the-art approaches within a unified taxonomy and discusses their strengths, limitations, and open problems. As the most promising direction, we suggest combining federated machine learning as a more scalable approach with other additional privacy-preserving techniques. This would allow to merge the advantages to provide privacy guarantees in a distributed way for biomedical applications. Nonetheless, more research is necessary as hybrid approaches pose new challenges such as additional network or computation overhead.

Sections du résumé

BACKGROUND
Artificial intelligence (AI) has been successfully applied in numerous scientific domains. In biomedicine, AI has already shown tremendous potential, e.g., in the interpretation of next-generation sequencing data and in the design of clinical decision support systems.
OBJECTIVES
However, training an AI model on sensitive data raises concerns about the privacy of individual participants. For example, summary statistics of a genome-wide association study can be used to determine the presence or absence of an individual in a given dataset. This considerable privacy risk has led to restrictions in accessing genomic and other biomedical data, which is detrimental for collaborative research and impedes scientific progress. Hence, there has been a substantial effort to develop AI methods that can learn from sensitive data while protecting individuals' privacy.
METHOD
This paper provides a structured overview of recent advances in privacy-preserving AI techniques in biomedicine. It places the most important state-of-the-art approaches within a unified taxonomy and discusses their strengths, limitations, and open problems.
CONCLUSION
As the most promising direction, we suggest combining federated machine learning as a more scalable approach with other additional privacy-preserving techniques. This would allow to merge the advantages to provide privacy guarantees in a distributed way for biomedical applications. Nonetheless, more research is necessary as hybrid approaches pose new challenges such as additional network or computation overhead.

Identifiants

pubmed: 35062032
doi: 10.1055/s-0041-1740630
pmc: PMC9246509
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

e12-e27

Commentaires et corrections

Type : CommentIn

Informations de copyright

The Author(s). This is an open access article published by Thieme under the terms of the Creative Commons Attribution-NonDerivative-NonCommercial License, permitting copying and reproduction so long as the original work is given appropriate credit. Contents may not be used for commercial purposes, or adapted, remixed, transformed or built upon. (https://creativecommons.org/licenses/by-nc-nd/4.0/).

Déclaration de conflit d'intérêts

None declared.

Références

BMC Med Inform Decis Mak. 2014;14 Suppl 1:S2
pubmed: 25521306
J Am Med Inform Assoc. 2016 May;23(3):570-9
pubmed: 26554428
JAMA. 2018 Apr 3;319(13):1317-1318
pubmed: 29532063
NPJ Digit Med. 2020 Sep 14;3:119
pubmed: 33015372
Nat Biotechnol. 2018 Jul;36(6):547-551
pubmed: 29734293
AMIA Annu Symp Proc. 2017 Feb 10;2016:1747-1755
pubmed: 28269933
Nat Genet. 2006 Aug;38(8):904-9
pubmed: 16862161
Proc Natl Acad Sci U S A. 2020 Apr 14;117(15):8344-8352
pubmed: 32234789
JMIR Med Inform. 2018 Apr 17;6(2):e19
pubmed: 29666041
BMC Med Genomics. 2014;7 Suppl 1:S14
pubmed: 25079786
Med Image Anal. 2015 Feb;20(1):237-48
pubmed: 25547073
ACM Comput Surv. 2015 Sep;48(1):
pubmed: 26640318
BMC Med Genomics. 2017 Jul 26;10(Suppl 2):39
pubmed: 28786360
J Priv Confid. 2013;5(1):137-166
pubmed: 26525346
IEEE/ACM Trans Comput Biol Bioinform. 2019 Jan-Feb;16(1):93-102
pubmed: 29993695
Biol Direct. 2018 Feb 6;13(1):1
pubmed: 29409513
Cell Syst. 2020 May 20;10(5):408-416.e9
pubmed: 32359425
KDD. 2013 Aug;2013:1079-1087
pubmed: 26691928
Ann N Y Acad Sci. 2017 Jan;1387(1):73-83
pubmed: 27681358
Cell. 2018 Jun 14;173(7):1562-1565
pubmed: 29906441
Stroke Vasc Neurol. 2017 Jun 21;2(4):230-243
pubmed: 29507784
Nat Biomed Eng. 2018 Oct;2(10):719-731
pubmed: 31015651
Nat Rev Cancer. 2018 Aug;18(8):500-510
pubmed: 29777175
Sci Data. 2018 Sep 11;5:180178
pubmed: 30204154
Brief Bioinform. 2017 Sep 1;18(5):851-869
pubmed: 27473064
J Digit Imaging. 2017 Aug;30(4):499-505
pubmed: 28656455
Circ Cardiovasc Qual Outcomes. 2019 Jul;12(7):e005122
pubmed: 31284738
Brainlesion. 2019;11383:92-104
pubmed: 31231720
BMC Bioinformatics. 2018 Dec 20;19(1):537
pubmed: 30572817
Annu Rev Biomed Eng. 2017 Jun 21;19:221-248
pubmed: 28301734
Science. 2008 Oct 3;322(5898):44
pubmed: 18772394
Cell Syst. 2016 Jul;3(1):54-61
pubmed: 27453444
Bioinformatics. 2013 Apr 1;29(7):886-93
pubmed: 23413435
Nat Genet. 2014 Feb;46(2):100-6
pubmed: 24473328
BMC Med Inform Decis Mak. 2014;14 Suppl 1:S3
pubmed: 25521367
Bioinformatics. 2017 Mar 15;33(6):871-878
pubmed: 28065902
BMC Med Inform Decis Mak. 2015;15 Suppl 5:S1
pubmed: 26732892
J Biomed Inform. 2013 Jun;46(3):480-96
pubmed: 23562651
Science. 2016 Jun 10;352(6291):1278-80
pubmed: 27284183
Int J Med Inform. 2018 Apr;112:59-67
pubmed: 29500022
BMC Med Inform Decis Mak. 2016 Jul 25;16 Suppl 3:89
pubmed: 27454168
BMC Med Genomics. 2017 Jul 26;10(Suppl 2):43
pubmed: 28786364
Brief Bioinform. 2019 May 21;20(3):887-895
pubmed: 29121240
Nat Rev Genet. 2015 Jun;16(6):321-32
pubmed: 25948244
BMC Med Inform Decis Mak. 2015;15 Suppl 5:S4
pubmed: 26733307
PLoS Genet. 2008 Aug 29;4(8):e1000167
pubmed: 18769715
J Biomed Inform. 2018 May;81:41-52
pubmed: 29550393
Med Image Anal. 2020 Oct;65:101765
pubmed: 32679533
Nat Rev Genet. 2014 Jun;15(6):409-21
pubmed: 24805122
J Am Med Inform Assoc. 2018 Aug 1;25(8):945-954
pubmed: 29617797
Nat Methods. 2018 Apr;15(4):290-298
pubmed: 29505029
AMIA Annu Symp Proc. 2020 Mar 04;2019:313-322
pubmed: 32308824
BMC Med Inform Decis Mak. 2015;15 Suppl 5:S5
pubmed: 26733391
J Healthc Inform Res. 2021;5(1):1-19
pubmed: 33204939
BMC Med Inform Decis Mak. 2015;15 Suppl 5:S2
pubmed: 26733045
J Am Med Inform Assoc. 2015 Nov;22(6):1212-9
pubmed: 26159465
Nat Commun. 2018 Jun 22;9(1):2453
pubmed: 29934598
JMIR Med Inform. 2019 Apr 29;7(2):e12702
pubmed: 31033449
Med Image Anal. 2017 Dec;42:60-88
pubmed: 28778026
Crit Care Med. 2018 Apr;46(4):547-553
pubmed: 29286945
IEEE Trans Biomed Eng. 2018 Dec;65(12):2720-2730
pubmed: 29993445
Bioinformatics. 2016 May 1;32(9):1293-300
pubmed: 26769317
Genome Biol. 2022 Jan 24;23(1):32
pubmed: 35073941
Genome Biol. 2019 Jul 2;20(1):128
pubmed: 31262363
BMC Med Inform Decis Mak. 2015;15 Suppl 5:S3
pubmed: 26733152
Am J Hum Genet. 2007 Sep;81(3):559-75
pubmed: 17701901
Am J Hum Genet. 2015 Nov 5;97(5):631-46
pubmed: 26522470
Nat Biotechnol. 2019 Mar;37(3):220-224
pubmed: 30833764
IEEE/ACM Trans Comput Biol Bioinform. 2018 Sep-Oct;15(5):1413-1426
pubmed: 30004884
Nat Biotechnol. 2018 Oct;36(9):829-838
pubmed: 30188539
Drug Discov Today. 2018 Jun;23(6):1241-1250
pubmed: 29366762
ACS Cent Sci. 2018 Feb 28;4(2):268-276
pubmed: 29532027
J Am Med Inform Assoc. 2020 May 1;27(5):700-708
pubmed: 32196092
IEEE/ACM Trans Comput Biol Bioinform. 2019 Jul-Aug;16(4):1328-1341
pubmed: 30010584
J Am Med Inform Assoc. 2012 Sep-Oct;19(5):758-64
pubmed: 22511014
JMIR Med Inform. 2018 Apr 13;6(2):e20
pubmed: 29653917

Auteurs

Reihaneh Torkzadehmahani (R)

Institute for Artificial Intelligence in Medicine and Healthcare, Technical University of Munich, Munich, Germany.

Reza Nasirigerdeh (R)

Institute for Artificial Intelligence in Medicine and Healthcare, Technical University of Munich, Munich, Germany.
Klinikum Rechts der Isar, Technical University of Munich, Munich, Germany.

David B Blumenthal (DB)

Department of Artificial Intelligence in Biomedical Engineering (AIBE), Friedrich-Alexander University Erlangen-Nürnberg (FAU), Erlangen, Germany.

Tim Kacprowski (T)

Division of Data Science in Biomedicine, Peter L. Reichertz Institute for Medical Informatics of TU Braunschweig and Medical School Hannover, Braunschweig, Germany.
Braunschweig Integrated Centre of Systems Biology (BRICS), TU Braunschweig, Braunschweig, Germany.

Markus List (M)

Chair of Experimental Bioinformatics, Technical University of Munich, Munich, Germany.

Julian Matschinske (J)

E.U. Horizon2020 FeatureCloud Project Consortium.
Chair of Computational Systems Biology, University of Hamburg, Hamburg, Germany.

Julian Spaeth (J)

E.U. Horizon2020 FeatureCloud Project Consortium.
Chair of Computational Systems Biology, University of Hamburg, Hamburg, Germany.

Nina Kerstin Wenke (NK)

E.U. Horizon2020 FeatureCloud Project Consortium.
Chair of Computational Systems Biology, University of Hamburg, Hamburg, Germany.

Jan Baumbach (J)

E.U. Horizon2020 FeatureCloud Project Consortium.
Chair of Computational Systems Biology, University of Hamburg, Hamburg, Germany.
Institute of Mathematics and Computer Science, University of Southern Denmark, Odense, Denmark.

Articles similaires

[Redispensing of expensive oral anticancer medicines: a practical application].

Lisanne N van Merendonk, Kübra Akgöl, Bastiaan Nuijen
1.00
Humans Antineoplastic Agents Administration, Oral Drug Costs Counterfeit Drugs

Smoking Cessation and Incident Cardiovascular Disease.

Jun Hwan Cho, Seung Yong Shin, Hoseob Kim et al.
1.00
Humans Male Smoking Cessation Cardiovascular Diseases Female
Humans United States Aged Cross-Sectional Studies Medicare Part C
1.00
Humans Yoga Low Back Pain Female Male

Classifications MeSH