Addressing the clinical unmet needs in primary Sjögren’s Syndrome through the sharing, harmonization and federated analysis of 21 European cohorts

• Published in: Computational and structural biotechnology journal Vol. 20; pp. 471 - 484
• Main Authors: Pezoulas, Vasileios C., Goules, Andreas, Kalatzis, Fanis, Chatzis, Luke, Kourou, Konstantina D., Venetsanopoulou, Aliki, Exarchos, Themis P., Gandolfo, Saviana, Votis, Konstantinos, Zampeli, Evi, Burmeister, Jan, May, Thorsten, Marcelino Pérez, Manuel, Lishchuk, Iryna, Chondrogiannis, Thymios, Andronikou, Vassiliki, Varvarigou, Theodora, Filipovic, Nenad, Tsiknakis, Manolis, Baldini, Chiara, Bombardieri, Michele, Bootsma, Hendrika, Bowman, Simon J., Soyfoo, Muhammad Shahnawaz, Parisis, Dorian, Delporte, Christine, Devauchelle-Pensec, Valérie, Pers, Jacques-Olivier, Dörner, Thomas, Bartoloni, Elena, Gerli, Roberto, Giacomelli, Roberto, Jonsson, Roland, Ng, Wan-Fai, Priori, Roberta, Ramos-Casals, Manuel, Sivils, Kathy, Skopouli, Fotini, Torsten, Witte, A. G. van Roon, Joel, Xavier, Mariette, De Vita, Salvatore, Tzioufas, Athanasios G., Fotiadis, Dimitrios I.
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.01.2022; Research Network of Computational and Structural Biotechnology; Elsevier
• Subjects: Biomarkers; Data curation; Data harmonization; Data sharing; Federated AI; Lymphoma classification; Primary Sjögren’s syndrome; Data sharing; Data curation; Biomarkers; Data harmonization; Federated AI; Primary Sjögren’s syndrome; Lymphoma classification
• ISSN: 2001-0370; 2001-0370
• DOI: 10.1016/j.csbj.2022.01.002

[Display omitted] •Data sharing can address open issues and clinical unmet needs in rare diseases.•Data curation enhanced the cohort data quality in primary Sjögrens Syndrome (pSS).•Semantic analysis yielded 7,156 harmonized patients across 21 cohorts in pSS.•Federated tree ensembles yield explainable AI models for lymphoma development.•Salivary gland swelling & cryoglobulinemia increase the risk for lymphomagenesis. 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.