Health data space nodes for privacy-preserving linkage of medical data to support collaborative secondary analyses
IntroductionThe potential for secondary use of health data to improve healthcare is currently not fully exploited. Health data is largely kept in isolated data silos and key infrastructure to aggregate these silos into standardized bodies of knowledge is underdeveloped. We describe the development,...
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-04-01
|
| Series: | Frontiers in Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmed.2024.1301660/full |
| _version_ | 1827288802549301248 |
|---|---|
| author | Martin Baumgartner Martin Baumgartner Karl Kreiner Aaron Lauschensky Bernhard Jammerbund Klaus Donsa Dieter Hayn Dieter Hayn Fabian Wiesmüller Fabian Wiesmüller Fabian Wiesmüller Lea Demelius Lea Demelius Robert Modre-Osprian Sabrina Neururer Sabrina Neururer Gerald Slamanig Sarah Prantl Luca Brunelli Bernhard Pfeifer Bernhard Pfeifer Gerhard Pölzl Günter Schreier Günter Schreier |
| author_facet | Martin Baumgartner Martin Baumgartner Karl Kreiner Aaron Lauschensky Bernhard Jammerbund Klaus Donsa Dieter Hayn Dieter Hayn Fabian Wiesmüller Fabian Wiesmüller Fabian Wiesmüller Lea Demelius Lea Demelius Robert Modre-Osprian Sabrina Neururer Sabrina Neururer Gerald Slamanig Sarah Prantl Luca Brunelli Bernhard Pfeifer Bernhard Pfeifer Gerhard Pölzl Günter Schreier Günter Schreier |
| author_sort | Martin Baumgartner |
| collection | DOAJ |
| description | IntroductionThe potential for secondary use of health data to improve healthcare is currently not fully exploited. Health data is largely kept in isolated data silos and key infrastructure to aggregate these silos into standardized bodies of knowledge is underdeveloped. We describe the development, implementation, and evaluation of a federated infrastructure to facilitate versatile secondary use of health data based on Health Data Space nodes.Materials and methodsOur proposed nodes are self-contained units that digest data through an extract-transform-load framework that pseudonymizes and links data with privacy-preserving record linkage and harmonizes into a common data model (OMOP CDM). To support collaborative analyses a multi-level feature store is also implemented. A feasibility experiment was conducted to test the infrastructures potential for machine learning operations and deployment of other apps (e.g., visualization). Nodes can be operated in a network at different levels of sharing according to the level of trust within the network.ResultsIn a proof-of-concept study, a privacy-preserving registry for heart failure patients has been implemented as a real-world showcase for Health Data Space nodes at the highest trust level, linking multiple data sources including (a) electronical medical records from hospitals, (b) patient data from a telemonitoring system, and (c) data from Austria’s national register of deaths. The registry is deployed at the tirol kliniken, a hospital carrier in the Austrian state of Tyrol, and currently includes 5,004 patients, with over 2.9 million measurements, over 574,000 observations, more than 63,000 clinical free text notes, and in total over 5.2 million data points. Data curation and harmonization processes are executed semi-automatically at each individual node according to data sharing policies to ensure data sovereignty, scalability, and privacy. As a feasibility test, a natural language processing model for classification of clinical notes was deployed and tested.DiscussionThe presented Health Data Space node infrastructure has proven to be practicable in a real-world implementation in a live and productive registry for heart failure. The present work was inspired by the European Health Data Space initiative and its spirit to interconnect health data silos for versatile secondary use of health data. |
| first_indexed | 2024-04-24T11:36:49Z |
| format | Article |
| id | doaj.art-f0a66e9315ce4949bf67f5cd10a25b85 |
| institution | Directory Open Access Journal |
| issn | 2296-858X |
| language | English |
| last_indexed | 2024-04-24T11:36:49Z |
| publishDate | 2024-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Medicine |
| spelling | doaj.art-f0a66e9315ce4949bf67f5cd10a25b852024-04-10T05:04:25ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2024-04-011110.3389/fmed.2024.13016601301660Health data space nodes for privacy-preserving linkage of medical data to support collaborative secondary analysesMartin Baumgartner0Martin Baumgartner1Karl Kreiner2Aaron Lauschensky3Bernhard Jammerbund4Klaus Donsa5Dieter Hayn6Dieter Hayn7Fabian Wiesmüller8Fabian Wiesmüller9Fabian Wiesmüller10Lea Demelius11Lea Demelius12Robert Modre-Osprian13Sabrina Neururer14Sabrina Neururer15Gerald Slamanig16Sarah Prantl17Luca Brunelli18Bernhard Pfeifer19Bernhard Pfeifer20Gerhard Pölzl21Günter Schreier22Günter Schreier23Center for Health and Bioresources, AIT Austrian Institute of Technology, Vienna, AustriaInstitute of Neural Engineering, Graz University of Technology, Graz, AustriaCenter for Health and Bioresources, AIT Austrian Institute of Technology, Vienna, AustriaCenter for Health and Bioresources, AIT Austrian Institute of Technology, Vienna, AustriaCenter for Health and Bioresources, AIT Austrian Institute of Technology, Vienna, AustriaCenter for Health and Bioresources, AIT Austrian Institute of Technology, Vienna, AustriaCenter for Health and Bioresources, AIT Austrian Institute of Technology, Vienna, AustriaLudwig Boltzmann Institute for Digital Health and Prevention, Salzburg, AustriaCenter for Health and Bioresources, AIT Austrian Institute of Technology, Vienna, AustriaInstitute of Neural Engineering, Graz University of Technology, Graz, AustriaLudwig Boltzmann Institute for Digital Health and Prevention, Salzburg, AustriaInstitute of Interactive Systems and Data Science, Graz University of Technology, Graz, AustriaKnow-Center GmbH, Graz, Austriatelbiomed Medizintechnik und IT Service GmbH, Graz, AustriaDepartment of Clinical Epidemiology, Tyrolean Federal Institute for Integrated Care, Tirol Kliniken GmbH, Innsbruck, AustriaDivision for Digital Health and Telemedicine, UMIT TIROL—Private University for Health Sciences and Technology, Hall in Tyrol, AustriaTirol Kliniken GmbH, Innsbruck, AustriaTirol Kliniken GmbH, Innsbruck, Austria0Department of Internal Medicine III, Cardiology and Angiology, Medical University of Innsbruck, Innsbruck, AustriaDivision for Digital Health and Telemedicine, UMIT TIROL—Private University for Health Sciences and Technology, Hall in Tyrol, Austria1Tyrolean Federal Institute for Integrated Care, Tirol Kliniken GmbH, Innsbruck, Austria0Department of Internal Medicine III, Cardiology and Angiology, Medical University of Innsbruck, Innsbruck, AustriaCenter for Health and Bioresources, AIT Austrian Institute of Technology, Vienna, AustriaInstitute of Neural Engineering, Graz University of Technology, Graz, AustriaIntroductionThe potential for secondary use of health data to improve healthcare is currently not fully exploited. Health data is largely kept in isolated data silos and key infrastructure to aggregate these silos into standardized bodies of knowledge is underdeveloped. We describe the development, implementation, and evaluation of a federated infrastructure to facilitate versatile secondary use of health data based on Health Data Space nodes.Materials and methodsOur proposed nodes are self-contained units that digest data through an extract-transform-load framework that pseudonymizes and links data with privacy-preserving record linkage and harmonizes into a common data model (OMOP CDM). To support collaborative analyses a multi-level feature store is also implemented. A feasibility experiment was conducted to test the infrastructures potential for machine learning operations and deployment of other apps (e.g., visualization). Nodes can be operated in a network at different levels of sharing according to the level of trust within the network.ResultsIn a proof-of-concept study, a privacy-preserving registry for heart failure patients has been implemented as a real-world showcase for Health Data Space nodes at the highest trust level, linking multiple data sources including (a) electronical medical records from hospitals, (b) patient data from a telemonitoring system, and (c) data from Austria’s national register of deaths. The registry is deployed at the tirol kliniken, a hospital carrier in the Austrian state of Tyrol, and currently includes 5,004 patients, with over 2.9 million measurements, over 574,000 observations, more than 63,000 clinical free text notes, and in total over 5.2 million data points. Data curation and harmonization processes are executed semi-automatically at each individual node according to data sharing policies to ensure data sovereignty, scalability, and privacy. As a feasibility test, a natural language processing model for classification of clinical notes was deployed and tested.DiscussionThe presented Health Data Space node infrastructure has proven to be practicable in a real-world implementation in a live and productive registry for heart failure. The present work was inspired by the European Health Data Space initiative and its spirit to interconnect health data silos for versatile secondary use of health data.https://www.frontiersin.org/articles/10.3389/fmed.2024.1301660/fulldata-driven healthcareprivacy-preservationrecord linkageadvanced analyticsinteroperabilitymachine learning |
| spellingShingle | Martin Baumgartner Martin Baumgartner Karl Kreiner Aaron Lauschensky Bernhard Jammerbund Klaus Donsa Dieter Hayn Dieter Hayn Fabian Wiesmüller Fabian Wiesmüller Fabian Wiesmüller Lea Demelius Lea Demelius Robert Modre-Osprian Sabrina Neururer Sabrina Neururer Gerald Slamanig Sarah Prantl Luca Brunelli Bernhard Pfeifer Bernhard Pfeifer Gerhard Pölzl Günter Schreier Günter Schreier Health data space nodes for privacy-preserving linkage of medical data to support collaborative secondary analyses Frontiers in Medicine data-driven healthcare privacy-preservation record linkage advanced analytics interoperability machine learning |
| title | Health data space nodes for privacy-preserving linkage of medical data to support collaborative secondary analyses |
| title_full | Health data space nodes for privacy-preserving linkage of medical data to support collaborative secondary analyses |
| title_fullStr | Health data space nodes for privacy-preserving linkage of medical data to support collaborative secondary analyses |
| title_full_unstemmed | Health data space nodes for privacy-preserving linkage of medical data to support collaborative secondary analyses |
| title_short | Health data space nodes for privacy-preserving linkage of medical data to support collaborative secondary analyses |
| title_sort | health data space nodes for privacy preserving linkage of medical data to support collaborative secondary analyses |
| topic | data-driven healthcare privacy-preservation record linkage advanced analytics interoperability machine learning |
| url | https://www.frontiersin.org/articles/10.3389/fmed.2024.1301660/full |
| work_keys_str_mv | AT martinbaumgartner healthdataspacenodesforprivacypreservinglinkageofmedicaldatatosupportcollaborativesecondaryanalyses AT martinbaumgartner healthdataspacenodesforprivacypreservinglinkageofmedicaldatatosupportcollaborativesecondaryanalyses AT karlkreiner healthdataspacenodesforprivacypreservinglinkageofmedicaldatatosupportcollaborativesecondaryanalyses AT aaronlauschensky healthdataspacenodesforprivacypreservinglinkageofmedicaldatatosupportcollaborativesecondaryanalyses AT bernhardjammerbund healthdataspacenodesforprivacypreservinglinkageofmedicaldatatosupportcollaborativesecondaryanalyses AT klausdonsa healthdataspacenodesforprivacypreservinglinkageofmedicaldatatosupportcollaborativesecondaryanalyses AT dieterhayn healthdataspacenodesforprivacypreservinglinkageofmedicaldatatosupportcollaborativesecondaryanalyses AT dieterhayn healthdataspacenodesforprivacypreservinglinkageofmedicaldatatosupportcollaborativesecondaryanalyses AT fabianwiesmuller healthdataspacenodesforprivacypreservinglinkageofmedicaldatatosupportcollaborativesecondaryanalyses AT fabianwiesmuller healthdataspacenodesforprivacypreservinglinkageofmedicaldatatosupportcollaborativesecondaryanalyses AT fabianwiesmuller healthdataspacenodesforprivacypreservinglinkageofmedicaldatatosupportcollaborativesecondaryanalyses AT leademelius healthdataspacenodesforprivacypreservinglinkageofmedicaldatatosupportcollaborativesecondaryanalyses AT leademelius healthdataspacenodesforprivacypreservinglinkageofmedicaldatatosupportcollaborativesecondaryanalyses AT robertmodreosprian healthdataspacenodesforprivacypreservinglinkageofmedicaldatatosupportcollaborativesecondaryanalyses AT sabrinaneururer healthdataspacenodesforprivacypreservinglinkageofmedicaldatatosupportcollaborativesecondaryanalyses AT sabrinaneururer healthdataspacenodesforprivacypreservinglinkageofmedicaldatatosupportcollaborativesecondaryanalyses AT geraldslamanig healthdataspacenodesforprivacypreservinglinkageofmedicaldatatosupportcollaborativesecondaryanalyses AT sarahprantl healthdataspacenodesforprivacypreservinglinkageofmedicaldatatosupportcollaborativesecondaryanalyses AT lucabrunelli healthdataspacenodesforprivacypreservinglinkageofmedicaldatatosupportcollaborativesecondaryanalyses AT bernhardpfeifer healthdataspacenodesforprivacypreservinglinkageofmedicaldatatosupportcollaborativesecondaryanalyses AT bernhardpfeifer healthdataspacenodesforprivacypreservinglinkageofmedicaldatatosupportcollaborativesecondaryanalyses AT gerhardpolzl healthdataspacenodesforprivacypreservinglinkageofmedicaldatatosupportcollaborativesecondaryanalyses AT gunterschreier healthdataspacenodesforprivacypreservinglinkageofmedicaldatatosupportcollaborativesecondaryanalyses AT gunterschreier healthdataspacenodesforprivacypreservinglinkageofmedicaldatatosupportcollaborativesecondaryanalyses |