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

Vasileios C. Pezoulas; Andreas Goules; Fanis Kalatzis; Luke Chatzis; Konstantina D. Kourou; Aliki Venetsanopoulou; Themis P. Exarchos; Saviana Gandolfo; Konstantinos Votis; Evi Zampeli; Jan Burmeister; Thorsten May; Manuel Marcelino Pérez; Iryna Lishchuk; Thymios Chondrogiannis; Vassiliki Andronikou; Theodora Varvarigou; Nenad Filipovic; Manolis Tsiknakis; Chiara Baldini; Michele Bombardieri; Hendrika Bootsma; Simon J. Bowman; Muhammad Shahnawaz Soyfoo; Dorian Parisis; Christine Delporte; Valérie Devauchelle-Pensec; Jacques Olivier Pers; Thomas Dörner; Elena Bartoloni; Roberto Gerli; Roberto Giacomelli; Roland Jonsson; Wan Fai Ng; Roberta Priori; Manuel Ramos-Casals; Kathy Sivils; Fotini Skopouli; Witte Torsten; Joel A. G. van Roon; Mariette Xavier; Salvatore De Vita; Athanasios G. Tzioufas; Dimitrios I. Fotiadis

doi:10.1016/j.csbj.2022.01.002

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

Vasileios C. Pezoulas
, Andreas Goules
, Fanis Kalatzis
, Luke Chatzis
, Konstantina D. Kourou
, Aliki Venetsanopoulou
, Themis P. Exarchos
, Saviana Gandolfo
, Konstantinos Votis
, Evi Zampeli
, Jan Burmeister
, Thorsten May
, Manuel Marcelino Pérez
, Iryna Lishchuk
, Thymios Chondrogiannis
, Vassiliki Andronikou
, Theodora Varvarigou
, Nenad Filipovic
, Manolis Tsiknakis
, Chiara Baldini

Michele Bombardieri, Hendrika Bootsma, Simon J. Bowman, Muhammad Shahnawaz Soyfoo, Dorian Parisis, Christine Delporte, Valérie Devauchelle-Pensec, Jacques Olivier Pers, Thomas Dörner, Elena Bartoloni, Roberto Gerli, Roberto Giacomelli, Roland Jonsson, Wan Fai Ng, Roberta Priori, Manuel Ramos-Casals, Kathy Sivils, Fotini Skopouli, Witte Torsten, Joel A. G. van Roon, Mariette Xavier, Salvatore De Vita, Athanasios G. Tzioufas, Dimitrios I. Fotiadis

University of Ioannina
National and Kapodistrian University of Athens
Ionian University
University of Udine
Center for Research and Technology - Hellas
Institute for Systemic Autoimmune and Neurological Diseases
Fraunhofer Institute for Computer Graphics Research
Atos
Leibniz University Hannover
Institute of Communication and Computer Systems
University of Kragujevac
Hellenic Mediterranean University
University of Pisa
Queen Mary University of London
University of Groningen
University Hospitals Birmingham NHS Foundation Trust
Université libre de Bruxelles
Université de Bretagne Occidentale
Charité – Universitätsmedizin Berlin
University of Perugia
University of L'Aquila
University of Bergen
Newcastle University
University of Rome La Sapienza
August Pi i Sunyer Biomedical Research Institute
Oklahoma Medical Research Foundation
Euroclinic Hospital
Hannover Medical School
Utrecht University
Assistance publique – Hôpitaux de Paris
Foundation for Research and Technology-Hellas

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

Abstract

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.

Original language	English
Pages (from-to)	471-484
Number of pages	14
Journal	Computational and Structural Biotechnology Journal
Volume	20
DOIs	https://doi.org/10.1016/j.csbj.2022.01.002
Publication status	Published - Jan 2022
Externally published	Yes

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Biomarkers
Data curation
Data harmonization
Data sharing
Federated AI
Lymphoma classification
Primary Sjögren's syndrome

Access to Document

10.1016/j.csbj.2022.01.002

Cite this

Pezoulas, V. C., Goules, A., Kalatzis, F., Chatzis, L., Kourou, K. D., Venetsanopoulou, A., Exarchos, T. P., Gandolfo, S., Votis, K., Zampeli, E., Burmeister, J., May, T., Marcelino Pérez, M., Lishchuk, I., Chondrogiannis, T., Andronikou, V., Varvarigou, T., Filipovic, N., Tsiknakis, M., ... Fotiadis, D. I. (2022). Addressing the clinical unmet needs in primary Sjögren's Syndrome through the sharing, harmonization and federated analysis of 21 European cohorts. Computational and Structural Biotechnology Journal, 20, 471-484. https://doi.org/10.1016/j.csbj.2022.01.002

@article{7d21b49c9b594e67b87e21962a763a1b,

title = "Addressing the clinical unmet needs in primary Sj{\"o}gren's Syndrome through the sharing, harmonization and federated analysis of 21 European cohorts",

abstract = "For many decades, the clinical unmet needs of primary Sj{\"o}gren'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.",

keywords = "Biomarkers, Data curation, Data harmonization, Data sharing, Federated AI, Lymphoma classification, Primary Sj{\"o}gren's syndrome",

author = "Pezoulas, \{Vasileios C.\} and Andreas Goules and Fanis Kalatzis and Luke Chatzis and Kourou, \{Konstantina D.\} and Aliki Venetsanopoulou and Exarchos, \{Themis P.\} and Saviana Gandolfo and Konstantinos Votis and Evi Zampeli and Jan Burmeister and Thorsten May and \{Marcelino P{\'e}rez\}, Manuel and Iryna Lishchuk and Thymios Chondrogiannis and Vassiliki Andronikou and Theodora Varvarigou and Nenad Filipovic and Manolis Tsiknakis and Chiara Baldini and Michele Bombardieri and Hendrika Bootsma and Bowman, \{Simon J.\} and \{Shahnawaz Soyfoo\}, Muhammad and Dorian Parisis and Christine Delporte and Val{\'e}rie Devauchelle-Pensec and Pers, \{Jacques Olivier\} and Thomas D{\"o}rner and Elena Bartoloni and Roberto Gerli and Roberto Giacomelli and Roland Jonsson and Ng, \{Wan Fai\} and Roberta Priori and Manuel Ramos-Casals and Kathy Sivils and Fotini Skopouli and Witte Torsten and \{A. G. van Roon\}, Joel and Mariette Xavier and \{De Vita\}, Salvatore and Tzioufas, \{Athanasios G.\} and Fotiadis, \{Dimitrios I.\}",

note = "Publisher Copyright: {\textcopyright} 2022 The Author(s)",

year = "2022",

month = jan,

doi = "10.1016/j.csbj.2022.01.002",

language = "English",

volume = "20",

pages = "471--484",

journal = "Computational and Structural Biotechnology Journal",

issn = "2001-0370",

publisher = "Elsevier B.V.",

}

Pezoulas, VC, Goules, A, Kalatzis, F, Chatzis, L, Kourou, KD, Venetsanopoulou, A, Exarchos, TP, Gandolfo, S, Votis, K, Zampeli, E, Burmeister, J, May, T, Marcelino Pérez, M, Lishchuk, I, Chondrogiannis, T, Andronikou, V, Varvarigou, T, Filipovic, N, Tsiknakis, M, Baldini, C, Bombardieri, M, Bootsma, H, Bowman, SJ, Shahnawaz Soyfoo, M, Parisis, D, Delporte, C, Devauchelle-Pensec, V, Pers, JO, Dörner, T, Bartoloni, E, Gerli, R, Giacomelli, R, Jonsson, R, Ng, WF, Priori, R, Ramos-Casals, M, Sivils, K, Skopouli, F, Torsten, W, A. G. van Roon, J, Xavier, M, De Vita, S, Tzioufas, AG & Fotiadis, DI 2022, 'Addressing the clinical unmet needs in primary Sjögren's Syndrome through the sharing, harmonization and federated analysis of 21 European cohorts', Computational and Structural Biotechnology Journal, vol. 20, pp. 471-484. https://doi.org/10.1016/j.csbj.2022.01.002

TY - JOUR

T1 - Addressing the clinical unmet needs in primary Sjögren's Syndrome through the sharing, harmonization and federated analysis of 21 European cohorts

AU - Pezoulas, Vasileios C.

AU - Goules, Andreas

AU - Kalatzis, Fanis

AU - Chatzis, Luke

AU - Kourou, Konstantina D.

AU - Venetsanopoulou, Aliki

AU - Exarchos, Themis P.

AU - Gandolfo, Saviana

AU - Votis, Konstantinos

AU - Zampeli, Evi

AU - Burmeister, Jan

AU - May, Thorsten

AU - Marcelino Pérez, Manuel

AU - Lishchuk, Iryna

AU - Chondrogiannis, Thymios

AU - Andronikou, Vassiliki

AU - Varvarigou, Theodora

AU - Filipovic, Nenad

AU - Tsiknakis, Manolis

AU - Baldini, Chiara

AU - Bombardieri, Michele

AU - Bootsma, Hendrika

AU - Bowman, Simon J.

AU - Shahnawaz Soyfoo, Muhammad

AU - Parisis, Dorian

AU - Delporte, Christine

AU - Devauchelle-Pensec, Valérie

AU - Pers, Jacques Olivier

AU - Dörner, Thomas

AU - Bartoloni, Elena

AU - Gerli, Roberto

AU - Giacomelli, Roberto

AU - Jonsson, Roland

AU - Ng, Wan Fai

AU - Priori, Roberta

AU - Ramos-Casals, Manuel

AU - Sivils, Kathy

AU - Skopouli, Fotini

AU - Torsten, Witte

AU - A. G. van Roon, Joel

AU - Xavier, Mariette

AU - De Vita, Salvatore

AU - Tzioufas, Athanasios G.

AU - Fotiadis, Dimitrios I.

PY - 2022/1

Y1 - 2022/1

N2 - 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.

AB - 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.

KW - Biomarkers

KW - Data curation

KW - Data harmonization

KW - Data sharing

KW - Federated AI

KW - Lymphoma classification

KW - Primary Sjögren's syndrome

UR - https://www.scopus.com/pages/publications/85122610206

U2 - 10.1016/j.csbj.2022.01.002

DO - 10.1016/j.csbj.2022.01.002

M3 - Article

AN - SCOPUS:85122610206

SN - 2001-0370

VL - 20

SP - 471

EP - 484

JO - Computational and Structural Biotechnology Journal

JF - Computational and Structural Biotechnology Journal

ER -

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

Abstract

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this