• Media type: E-Article; Text
  • Title: Addressing the clinical unmet needs in primary Sjögren's Syndrome through the sharing, harmonization and federated analysis of 21 European cohorts
  • Contributor: Pezoulas, Vasileios C. [Author]; Goules, Andreas [Author]; Kalatzis, Fanis [Author]; Chatzis, Luke [Author]; Kourou, Konstantina D. [Author]; Venetsanopoulou, Aliki [Author]; Exarchos, Themis P. [Author]; Gandolfo, Saviana [Author]; Votis, Konstantinos [Author]; Zampeli, Evi [Author]; Burmeister, Jan [Author]; May, Thorsten [Author]; Marcelino Pérez, Manuel [Author]; Lishchuk, Iryna [Author]; Chondrogiannis, Thymios [Author]; Andronikou, Vassiliki [Author]; Varvarigou, Theodora [Author]; Filipovic, Nenad [Author]; Tsiknakis, Manolis [Author]; Baldini, Chiara [Author]; Bombardieri, Michele [Author]; Bootsma, Hendrika [Author]; Bowman, Simon J. [Author]; Shahnawaz Soyfoo, Muhammad [Author]; [...]
  • imprint: Gotenburg : Research Network of Computational and Structural Biotechnology (RNCSB), 2022
  • Published in: Computational and structural biotechnology journal 20 (2022) ; Computational and structural biotechnology journal
  • Issue: published Version
  • Language: English
  • DOI: https://doi.org/10.15488/12907; https://doi.org/10.1016/j.csbj.2022.01.002
  • Keywords: Data harmonization ; Biomarkers ; Data curation ; Lymphoma classification ; Primary Sjögren's syndrome ; Data sharing ; Federated AI
  • Origination:
  • Footnote: Diese Datenquelle enthält auch Bestandsnachweise, die nicht zu einem Volltext führen.
  • Description: For many decades, the clinical unmet needs of primary Sjögren's Syndrome (pSS) have been left unresolved due to the rareness of the disease and the complexity of the underlying pathogenic mechanisms, including the pSS-associated lymphomagenesis process. Here, we present the HarmonicSS cloud-computing exemplar which offers beyond the state-of-the-art data analytics services to address the pSS clinical unmet needs, including the development of lymphoma classification models and the identification of biomarkers for lymphomagenesis. The users of the platform have been able to successfully interlink, curate, and harmonize 21 regional, national, and international European cohorts of 7,551 pSS patients with respect to the ethical and legal issues for data sharing. Federated AI algorithms were trained across the harmonized databases, with reduced execution time complexity, yielding robust lymphoma classification models with 85% accuracy, 81.25% sensitivity, 85.4% specificity along with 5 biomarkers for lymphoma development. To our knowledge, this is the first GDPR compliant platform that provides federated AI services to address the pSS clinical unmet needs. © 2022 The Author(s)
  • Access State: Open Access
  • Rights information: Attribution (CC BY)