A Privacy-Preserving Infrastructure for Analyzing Personal Health Data in a Vertically Partitioned Scenario

Chang Sun; Lianne Ippel; Johan van Soest; Birgit Wouters; Alexander Malic; Onaopepo Adekunle; Bob van den Berg; Ole Mussmann; Annemarie Koster; Carla van der Kallen; Claudia van Oppen; David Townend; Andre Dekker; Michel Dumontier

doi:10.3233/SHTI190246

A Privacy-Preserving Infrastructure for Analyzing Personal Health Data in a Vertically Partitioned Scenario

Chang Sun^*, Lianne Ippel, Johan van Soest, Birgit Wouters, Alexander Malic, Onaopepo Adekunle, Bob van den Berg, Ole Mussmann, Annemarie Koster, Carla van der Kallen, Claudia van Oppen, David Townend, Andre Dekker, Michel Dumontier

^*Corresponding author for this work

Research output: Contribution to journal › Article › Academic › peer-review

Abstract

It is widely anticipated that the use and analysis of health-related big data will enable further understanding and improvements in human health and wellbeing. Here, we propose an innovative infrastructure, which supports secure and privacy-preserving analysis of personal health data from multiple providers with different governance policies. Our objective is to use this infrastructure to explore the relation between Type 2 Diabetes Mellitus status and healthcare costs. Our approach involves the use of distributed machine learning to analyze vertically partitioned data from the Maastricht Study, a prospective population-based cohort study, and data from the official statistics agency of the Netherlands, Statistics Netherlands (Centraal Bureau voor de Statistiek; CBS). This project seeks an optimal solution accounting for scientific, technical, and ethical/legal challenges. We describe these challenges, our progress towards addressing them in a practical use case, and a simulation experiment.

Original language	English
Pages (from-to)	373-377
Number of pages	5
Journal	Studies in Health Technology and Informatics
Volume	264
DOIs	https://doi.org/10.3233/SHTI190246
Publication status	Published - 21 Aug 2019

Keywords

Diabetes Mellitus, Type 2
Health Records, Personal
Humans
Netherlands
Privacy
Prospective Studies
Data Science
Health Information Systems
Machine Learning

Access to Document

10.3233/SHTI190246Licence: CC BY-NC

Cite this

Sun, C., Ippel, L., van Soest, J., Wouters, B., Malic, A., Adekunle, O., van den Berg, B., Mussmann, O., Koster, A., van der Kallen, C., van Oppen, C., Townend, D., Dekker, A., & Dumontier, M. (2019). A Privacy-Preserving Infrastructure for Analyzing Personal Health Data in a Vertically Partitioned Scenario. Studies in Health Technology and Informatics, 264, 373-377. https://doi.org/10.3233/SHTI190246

@article{032a06233d81441aa7acc89def46e02d,

title = "A Privacy-Preserving Infrastructure for Analyzing Personal Health Data in a Vertically Partitioned Scenario",

abstract = "It is widely anticipated that the use and analysis of health-related big data will enable further understanding and improvements in human health and wellbeing. Here, we propose an innovative infrastructure, which supports secure and privacy-preserving analysis of personal health data from multiple providers with different governance policies. Our objective is to use this infrastructure to explore the relation between Type 2 Diabetes Mellitus status and healthcare costs. Our approach involves the use of distributed machine learning to analyze vertically partitioned data from the Maastricht Study, a prospective population-based cohort study, and data from the official statistics agency of the Netherlands, Statistics Netherlands (Centraal Bureau voor de Statistiek; CBS). This project seeks an optimal solution accounting for scientific, technical, and ethical/legal challenges. We describe these challenges, our progress towards addressing them in a practical use case, and a simulation experiment.",

keywords = "Diabetes Mellitus, Type 2, Health Records, Personal, Humans, Netherlands, Privacy, Prospective Studies, Data Science, Health Information Systems, Machine Learning",

author = "Chang Sun and Lianne Ippel and \{van Soest\}, Johan and Birgit Wouters and Alexander Malic and Onaopepo Adekunle and \{van den Berg\}, Bob and Ole Mussmann and Annemarie Koster and \{van der Kallen\}, Carla and \{van Oppen\}, Claudia and David Townend and Andre Dekker and Michel Dumontier",

year = "2019",

month = aug,

day = "21",

doi = "10.3233/SHTI190246",

language = "English",

volume = "264",

pages = "373--377",

journal = "Studies in Health Technology and Informatics",

issn = "0926-9630",

publisher = "IOS Press",

}

Sun, C, Ippel, L, van Soest, J , Wouters, B, Malic, A, Adekunle, O, van den Berg, B, Mussmann, O, Koster, A , van der Kallen, C , van Oppen, C , Townend, D , Dekker, A & Dumontier, M 2019, 'A Privacy-Preserving Infrastructure for Analyzing Personal Health Data in a Vertically Partitioned Scenario', Studies in Health Technology and Informatics, vol. 264, pp. 373-377. https://doi.org/10.3233/SHTI190246

TY - JOUR

T1 - A Privacy-Preserving Infrastructure for Analyzing Personal Health Data in a Vertically Partitioned Scenario

AU - Sun, Chang

AU - Ippel, Lianne

AU - van Soest, Johan

AU - Wouters, Birgit

AU - Malic, Alexander

AU - Adekunle, Onaopepo

AU - van den Berg, Bob

AU - Mussmann, Ole

AU - Koster, Annemarie

AU - van der Kallen, Carla

AU - van Oppen, Claudia

AU - Townend, David

AU - Dekker, Andre

AU - Dumontier, Michel

PY - 2019/8/21

Y1 - 2019/8/21

N2 - It is widely anticipated that the use and analysis of health-related big data will enable further understanding and improvements in human health and wellbeing. Here, we propose an innovative infrastructure, which supports secure and privacy-preserving analysis of personal health data from multiple providers with different governance policies. Our objective is to use this infrastructure to explore the relation between Type 2 Diabetes Mellitus status and healthcare costs. Our approach involves the use of distributed machine learning to analyze vertically partitioned data from the Maastricht Study, a prospective population-based cohort study, and data from the official statistics agency of the Netherlands, Statistics Netherlands (Centraal Bureau voor de Statistiek; CBS). This project seeks an optimal solution accounting for scientific, technical, and ethical/legal challenges. We describe these challenges, our progress towards addressing them in a practical use case, and a simulation experiment.

AB - It is widely anticipated that the use and analysis of health-related big data will enable further understanding and improvements in human health and wellbeing. Here, we propose an innovative infrastructure, which supports secure and privacy-preserving analysis of personal health data from multiple providers with different governance policies. Our objective is to use this infrastructure to explore the relation between Type 2 Diabetes Mellitus status and healthcare costs. Our approach involves the use of distributed machine learning to analyze vertically partitioned data from the Maastricht Study, a prospective population-based cohort study, and data from the official statistics agency of the Netherlands, Statistics Netherlands (Centraal Bureau voor de Statistiek; CBS). This project seeks an optimal solution accounting for scientific, technical, and ethical/legal challenges. We describe these challenges, our progress towards addressing them in a practical use case, and a simulation experiment.

KW - Diabetes Mellitus, Type 2

KW - Health Records, Personal

KW - Humans

KW - Netherlands

KW - Privacy

KW - Prospective Studies

KW - Data Science

KW - Health Information Systems

KW - Machine Learning

U2 - 10.3233/SHTI190246

DO - 10.3233/SHTI190246

M3 - Article

C2 - 31437948

SN - 0926-9630

VL - 264

SP - 373

EP - 377

JO - Studies in Health Technology and Informatics

JF - Studies in Health Technology and Informatics

ER -

A Privacy-Preserving Infrastructure for Analyzing Personal Health Data in a Vertically Partitioned Scenario

Abstract

Keywords

Access to Document

Fingerprint

Cite this