Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 5
Encontrada(s) 1 página(s)

Addi. Archivo Digital para la Docencia y la Investigación
Publicación Artículo científico (JournalArticle)

A secure data publishing and access service for sensitive data from Living Labs: enabling collaboration with external researchers via shareable data

  • Hernández, Mikel
  • Konstantinidis, Evdokimos I.
  • Epelde Unanue, Gorka
  • Londoño, Francisco
  • Petsani, Despoina
  • Timoleon, Michalis
  • Fiska, Vasiliki
  • Mpaltadoros, Lampros
  • Maga-Nteve, Christoniki
  • Machairas, Ilias
  • Bamidis, Panagiotis D.
Intending to enable a broader collaboration with the scientific community while maintaining privacy of the data stored and generated in Living Labs, this paper presents the Shareable Data Publishing and Access Service for Living Labs, implemented within the framework of the H2020 VITALISE project. Building upon previous work, significant enhancements and improvements are presented in the architecture enabling Living Labs to securely publish collected data in an internal and isolated node for external use. External researchers can access a portal to discover and download shareable data versions (anonymised or synthetic data) derived from the data stored across different Living Labs that they can use to develop, test, and debug their processing scripts locally, adhering to legal and ethical data handling practices. Subsequently, they may request remote execution of the same algorithms against the real internal data in Living Lab nodes, comparing the outcomes with those obtained using shareable data. The paper details the architecture, data flows, technical details and validation of the service with real-world usage examples, demonstrating its efficacy in promoting data-driven research in digital health while preserving privacy. The presented service can be used as an intermediary between Living Labs and external researchers for secure data exchange and to accelerate research on data analytics paradigms in digital health, ensuring compliance with data protection laws., This research was partly funded by the VITALISE (Virtual Health and Wellbeing Living Lab Infrastructure) project, funded by the Horizon 2020 Framework Program of the European Union for Research Innovation (grant agreement 101007990).
Addi. Archivo Digital para la Docencia y la Investigación
Publicación Artículo científico (JournalArticle)

Comparative assessment of synthetic time series generation approaches in healthcare: leveraging patient metadata for accurate data synthesis

  • Isasa, Imanol
  • Hernández, Mikel
  • Epelde Unanue, Gorka
  • Londoño, Francisco
  • Beristain Iraola, Andoni
  • Larrea, Xabat
  • Alberdi Aramendi, Ane
  • Bamidis, Panagiotis D.
  • Konstantinidis, Evdokimos I.
Background Synthetic data is an emerging approach for addressing legal and regulatory concerns in biomedical research that deals with personal and clinical data, whether as a single tool or through its combination with other privacy enhancing technologies. Generating uncompromised synthetic data could significantly benefit external researchers performing secondary analyses by providing unlimited access to information while fulfilling pertinent regulations. However, the original data to be synthesized (e.g., data acquired in Living Labs) may consist of subjects’ metadata (static) and a longitudinal component (set of time-dependent measurements), making it challenging to produce coherent synthetic counterparts. Methods Three synthetic time series generation approaches were defined and compared in this work: only generating the metadata and coupling it with the real time series from the original data (A1), generating both metadata and time series separately to join them afterwards (A2), and jointly generating both metadata and time series (A3). The comparative assessment of the three approaches was carried out using two different synthetic data generation models: the Wasserstein GAN with Gradient Penalty (WGAN-GP) and the DöppelGANger (DGAN). The experiments were performed with three different healthcare-related longitudinal datasets: Treadmill Maximal Effort Test (TMET) measurements from the University of Malaga (1), a hypotension subset derived from the MIMIC-III v1.4 database (2), and a lifelogging dataset named PMData (3). Results Three pivotal dimensions were assessed on the generated synthetic data: resemblance to the original data (1), utility (2), and privacy level (3). The optimal approach fluctuates based on the assessed dimension and metric. Conclusion The initial characteristics of the datasets to be synthesized play a crucial role in determining the best approach. Coupling synthetic metadata with real time series (A1), as well as jointly generating synthetic time series and metadata (A3), are both competitive methods, while separately generating time series and metadata (A2) appears to perform more poorly overall., This research was partly funded by the VITALISE (VIrtual healTh And weLlbeing Living Lab InfraStructurE) project, funded by the Horizon 2020 Framework Program of the European Union for Research Innovation (grant agreement 101007990). Ane Alberdi is part of the Intelligent Systems for Industrial Systems research group of Mondragon Unibertsitatea (IT1676-22), supported by the Department of Education, Universities and Research of the Basque Country.
eBiltegia. Repositorio Institucional de Mondragon Unibertsitatea
Publicación

Comparative assessment of synthetic time series generation approaches in healthcare: leveraging patient metadata for accurate data synthesis

Archivo Digital UPM
Publicación Artículo científico (JournalArticle)

Innovation through the Quintuple Helix in living labs: lessons learned for a transformation from lab to ecosystem

  • Merino Barbancho, Beatriz|||0000-0001-5070-4178
  • Abril Jiménez, Patricia|||0000-0002-2805-5025
  • Mallo de la Calle, Irene|||0009-0003-3807-5307
  • Lombroni, Ivana
  • Cea, Gloria
  • López Nebreda, Cristina
  • Cabrera, Mari­a Fernanda
  • Fico, Giuseppe|||0000-0003-1551-4613
  • Arredondo Waldmeyer, María Teresa|||0000-0003-3113-3976