Using the Personal Health Train for Automated and Privacy-Preserving Analytics on Vertically Partitioned Data

Johan van Soest; Chang Sun; Ole Mussmann; Marco Puts; Bob van den Berg; Alexander Malic; Claudia van Oppen; David Townend; Andre Dekker; Michel Dumontier

doi:10.3233/978-1-61499-852-5-581

Using the Personal Health Train for Automated and Privacy-Preserving Analytics on Vertically Partitioned Data

Johan van Soest^*, Chang Sun, Ole Mussmann, Marco Puts, Bob van den Berg, Alexander Malic, Claudia van Oppen, David Townend, Andre Dekker, Michel Dumontier

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

Abstract

Conventional data mining algorithms are unable to satisfy the current requirements on analyzing big data in some fields such as medicine, policy making, judicial, and tax records. However, applying diverse datasets from different institutes (both healthcare and non-healthcare related) can enrich information and insights. So far, analyzing this data in an automated, privacy-preserving manner does not exist to our knowledge. In this work, we propose an infrastructure, and proof-of-concept for privacy-preserving analytics on vertically partitioned data.

Original language	English
Title of host publication	BUILDING CONTINENTS OF KNOWLEDGE IN OCEANS OF DATA: THE FUTURE OF CO-CREATED EHEALTH
Publisher	IOS Press
Pages	581-585
Number of pages	5
Volume	247
ISBN (Print)	9781614998518
DOIs	https://doi.org/10.3233/978-1-61499-852-5-581
Publication status	Published - 2018
Event	Conference on Medical Informatics Europe (MIE) - SWEDEN Duration: 24 Apr 2018 → 26 Apr 2018

Publication series

Series	Studies in Health Technology and Informatics
Volume	247
ISSN	0926-9630

Conference

Conference	Conference on Medical Informatics Europe (MIE)
Period	24/04/18 → 26/04/18

Keywords

Infrastructure
machine learning
data mining
statistics
privacy-preserving
secondary use of data
METHODOLOGY

Access to Document

10.3233/978-1-61499-852-5-581

https://www.ncbi.nlm.nih.gov/pubmed/29678027

Cite this

van Soest, J., Sun, C., Mussmann, O., Puts, M., van den Berg, B., Malic, A., van Oppen, C., Townend, D., Dekker, A., & Dumontier, M. (2018). Using the Personal Health Train for Automated and Privacy-Preserving Analytics on Vertically Partitioned Data. In BUILDING CONTINENTS OF KNOWLEDGE IN OCEANS OF DATA: THE FUTURE OF CO-CREATED EHEALTH (Vol. 247, pp. 581-585). IOS Press. https://doi.org/10.3233/978-1-61499-852-5-581

@inproceedings{fc553d50254f46b1b09f0e0978addbad,

title = "Using the Personal Health Train for Automated and Privacy-Preserving Analytics on Vertically Partitioned Data",

abstract = "Conventional data mining algorithms are unable to satisfy the current requirements on analyzing big data in some fields such as medicine, policy making, judicial, and tax records. However, applying diverse datasets from different institutes (both healthcare and non-healthcare related) can enrich information and insights. So far, analyzing this data in an automated, privacy-preserving manner does not exist to our knowledge. In this work, we propose an infrastructure, and proof-of-concept for privacy-preserving analytics on vertically partitioned data.",

keywords = "Infrastructure, machine learning, data mining, statistics, privacy-preserving, secondary use of data, METHODOLOGY",

author = "{van Soest}, Johan and Chang Sun and Ole Mussmann and Marco Puts and {van den Berg}, Bob and Alexander Malic and {van Oppen}, Claudia and David Townend and Andre Dekker and Michel Dumontier",

year = "2018",

doi = "10.3233/978-1-61499-852-5-581",

language = "English",

isbn = "9781614998518",

volume = "247",

series = "Studies in Health Technology and Informatics",

publisher = "IOS Press",

pages = "581--585",

booktitle = "BUILDING CONTINENTS OF KNOWLEDGE IN OCEANS OF DATA: THE FUTURE OF CO-CREATED EHEALTH",

address = "Netherlands",

note = "Conference on Medical Informatics Europe (MIE) ; Conference date: 24-04-2018 Through 26-04-2018",

}

van Soest, J , Sun, C, Mussmann, O, Puts, M, van den Berg, B, Malic, A, van Oppen, C , Townend, D , Dekker, A & Dumontier, M 2018, Using the Personal Health Train for Automated and Privacy-Preserving Analytics on Vertically Partitioned Data. in BUILDING CONTINENTS OF KNOWLEDGE IN OCEANS OF DATA: THE FUTURE OF CO-CREATED EHEALTH. vol. 247, IOS Press, Studies in Health Technology and Informatics, vol. 247, pp. 581-585, Conference on Medical Informatics Europe (MIE), 24/04/18. https://doi.org/10.3233/978-1-61499-852-5-581

Using the Personal Health Train for Automated and Privacy-Preserving Analytics on Vertically Partitioned Data. / van Soest, Johan ; Sun, Chang; Mussmann, Ole et al.
BUILDING CONTINENTS OF KNOWLEDGE IN OCEANS OF DATA: THE FUTURE OF CO-CREATED EHEALTH. Vol. 247 IOS Press, 2018. p. 581-585 (Studies in Health Technology and Informatics, Vol. 247).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

TY - GEN

T1 - Using the Personal Health Train for Automated and Privacy-Preserving Analytics on Vertically Partitioned Data

AU - van Soest, Johan

AU - Sun, Chang

AU - Mussmann, Ole

AU - Puts, Marco

AU - van den Berg, Bob

AU - Malic, Alexander

AU - van Oppen, Claudia

AU - Townend, David

AU - Dekker, Andre

AU - Dumontier, Michel

PY - 2018

Y1 - 2018

N2 - Conventional data mining algorithms are unable to satisfy the current requirements on analyzing big data in some fields such as medicine, policy making, judicial, and tax records. However, applying diverse datasets from different institutes (both healthcare and non-healthcare related) can enrich information and insights. So far, analyzing this data in an automated, privacy-preserving manner does not exist to our knowledge. In this work, we propose an infrastructure, and proof-of-concept for privacy-preserving analytics on vertically partitioned data.

AB - Conventional data mining algorithms are unable to satisfy the current requirements on analyzing big data in some fields such as medicine, policy making, judicial, and tax records. However, applying diverse datasets from different institutes (both healthcare and non-healthcare related) can enrich information and insights. So far, analyzing this data in an automated, privacy-preserving manner does not exist to our knowledge. In this work, we propose an infrastructure, and proof-of-concept for privacy-preserving analytics on vertically partitioned data.

KW - Infrastructure

KW - machine learning

KW - data mining

KW - statistics

KW - privacy-preserving

KW - secondary use of data

KW - METHODOLOGY

U2 - 10.3233/978-1-61499-852-5-581

DO - 10.3233/978-1-61499-852-5-581

M3 - Conference article in proceeding

SN - 9781614998518

VL - 247

T3 - Studies in Health Technology and Informatics

SP - 581

EP - 585

BT - BUILDING CONTINENTS OF KNOWLEDGE IN OCEANS OF DATA: THE FUTURE OF CO-CREATED EHEALTH

PB - IOS Press

T2 - Conference on Medical Informatics Europe (MIE)

Y2 - 24 April 2018 through 26 April 2018

ER -

van Soest J , Sun C, Mussmann O, Puts M, van den Berg B, Malic A et al. Using the Personal Health Train for Automated and Privacy-Preserving Analytics on Vertically Partitioned Data. In BUILDING CONTINENTS OF KNOWLEDGE IN OCEANS OF DATA: THE FUTURE OF CO-CREATED EHEALTH. Vol. 247. IOS Press. 2018. p. 581-585. (Studies in Health Technology and Informatics, Vol. 247). doi: 10.3233/978-1-61499-852-5-581