Authors:
Jakob Lehmann
1
;
Gesa Wimberg
1
;
Serge Autexier
1
;
Alberto Acebes
2
;
Christos Kalloniatis
3
;
Costas Lamprinoudakis
4
;
Thrasyvoulos Giannakopoulos
4
;
Andreas Menegatos
4
;
Agni Delvinioti
5
;
Giulio Pagliari
5
;
Nicoletta di Giorgi
5
;
Jarno Raid
6
;
Danae Lekka
7
;
Aristodemos Pnevmatikakis
7
;
Sofoklis Kyriazakos
7
;
Konstantina Kostopoulou
7
and
Monique Tabak
8
Affiliations:
1
Deutsches Forschungszentrum für Künstliche Intelligenz (DFKI), Enrique-Schmidt-Str. 5, 28359 Bremen, Germany
;
2
Atos IT Solutions and Services Iberia, S.L. Calle de Albarracín, 25. 28037 Madrid, Spain
;
3
Department of Cultural Technology and Communication, University of the Aegean, University Hill, 81100 Mytilene, Greece
;
4
Department of Digital Systems, University of Piraeus, 150 Androutsou St., Piraeus 18532, Greece
;
5
Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Largo Agostino Gemelli, 8, 00168 Rome, Italy
;
6
Tartu Ülikooli Kliinikum, Ludvig Puusepa 8, 50406 Tartu, Estonia
;
7
Innovation Sprint, Clos Chapelle-aux-Champs 30, Bte. 1.30.30 1200 Brussels, Belgium
;
8
University of Twente, Drienerlolaan 5, 7522 NB Enschede, Netherlands
Keyword(s):
Federated Learning, Interpretable Machine Learning, Chronic Obstructive Pulmonary Disease, Personalized Care, Real-World Data.
Abstract:
Federated learning is becoming more and more popular, also in healthcare applications. The platform, developed within a multidisciplinary consortium, is enabling privacy-preserving training of machine learning models generating predictions for patients with chronic obstructive pulmonary disease and comorbidities. Moreover, data synchronization and monitoring is made possible using the HL7 FHIR standard. The platform provides two front ends; a patient facing smartphone app and a healthcare professional facing dashboard that is used inside three different hospitals in Italy, Estonia and the Netherlands. The overall architecture and implementation into practice is shown in this paper.