Publications

Scientific Publications

This section encompasses all scientific publications generated by the project

RAMA: a risk assessment solution for healthcare organizations

Michail Smyrlis, Evangelos Floros, Ioannis Basdekis, Dumitru-Bogdan Prelipcean, Aristeidis Sotiropoulos, Herve Debar, Apostolis Zarras & George Spanoudakis

Recent cyber-attacks on healthcare institutions emphasise their growing vulnerability to malicious activities due to the sensitive personal health data they handle. To address these risks, we present RAMA, a specialized risk assessment tool tailored for critical sectors like healthcare. RAMA enables both local and global stakeholders to evaluate cyber risk profiles and fosters a culture of continuous improvement in cybersecurity practices. Implemented in four real-world healthcare IT infrastructures, RAMA demonstrates its practical effectiveness in safeguarding sensitive health data and enhancing the sector’s cyber resilience.

Full article

Architectural Design for Enhancing Remote Patient Monitoring in Heart Failure: A Case Study of the RETENTION Project

Ourania Manta, Nikolaos Vasileiou, Olympia Giannakopoulou, Konstantinos Bromis, Ioannis Kouris, Maria Haritou, Lefteris Koumakis, George Spanoudakis,

Irina E. Nicolae, C. Septimiu Nechifor, Miltiadis Kokkonidis, Michalis Vakalelis, Yorgos Goletsis, Maria Roumpi, Dimitrios I Fotiadis, Heraklis Galanis, Panagiotis Dimitrakopoulos, George K. Matsopoulos, Dimitrios D. Koutsouris

This paper introduces the RETENTION Platform, an integrated healthcare data management system meticulously crafted to support personalised interventions, thereby enhancing outcomes for heart failure (HF) patients. Comprising three fundamental components—the Global Insights Cloud (GIC), the Clinical Site Backend (CSB), and Patient Edge (PE)—the platform coordinates a sophisticated array of functions. The GIC facilitates data analysis and machine learning model training, while the CSB enables daily patient check-ups, data gathering, and intervention application. The Patient Edge enables continuous monitoring and feedback collection from patients. The system is deployed using virtual machines (VMs) and Docker containers on a cloud-based infrastructure. Integration and testing procedures are outlined to safeguard system functionality. This paper provides a comprehensive overview of the RETENTION Platform’s architecture and highlights its potential for improving healthcare delivery through personalised interventions.

Full article  

Security shortcomings in healthcare: a preliminary investigation of Data Protection Authorities’ decisions

Nanou Christina, Kampyli Maria, Crociani Maria, and Danilatou Vasiliki

As digital technologies are being more and more deployed to support the healthcare sector, the latter becomes increasingly vulnerable to cybersecurity and privacy risks. The past decades, significant effort has been put into advancing standardization and regulatory frameworks, aiming at protecting healthcare infrastructure and digital applications intended for use in healthcare, along with ongoing research on this field. Motivated by the ongoing research that uses digital applications in the healthcare, which is also conducted in two relevant HORIZON research projects (RETENTION and PHOENI2X), this work aims at providing insights on regulatory compliance challenges faced in this context and exploring respective shortcomings or solutions in practice. To this end, we reviewed decisions of the supervisory authorities within the USA and EU regarding data breaches in the healthcare sector, issued from 1/1/2020 to 31/12/2022, illustrating the most common areas of vulnerabilities and discussing the challenges and the lessons learned.

Full article

Advanced Notebook: A tool for enhanced Management of Machine Learning models and procedures in the Healthcare Domain

Gabriel Danciu, Irina E. Nicolae, Iulia Ilie, C. Septimiu Nechifor

The significant improvements in machine learning today necessitate procedures and frameworks that are simple to configure by data scientists, ML researchers, and non-DevOps engineers, allowing them to rapidly develop ML models and address real-world challenges. This article provides an in-depth analysis of the architectural design of a holistic system that addresses the management of machine learning processes and deployment procedures. The proposed system has been designed to provide seamless configuration options and smooth integration with other solutions by enabling the rapid development of ML models. Its versatility makes it applicable in various scenarios, enhancing its usability across different domains. The effectiveness of the proposed solution has been validated through practical implementation in two distinct machine ML scenarios, both of which were integrated into European Union (EU) projects centered around the healthcare domain. The findings from these specific use cases have been documented and are presented as part of the empirical evidence supporting the viability and success of the solution.

Full article

New ethical challenges facing clinicians in the digital era: the paradigm of a clinical trial using AI-enabled tools for remote heart-failure patient monitoring and management

Christina Nanou, Maria Crociani, Vasiliki Danilatou

Chronic Heart Failure (HF) is a major cause of disability and premature death throughout the world. Although the exploitation of e-health technological advancements might provide promising solutions regarding HF patient management -aimed at reducing mortality and hospitalisation rates and improving the quality of life of HF patients, more research needs to be conducted to validate these potentials. Motivated by a use case of an ongoing H2020 research project (RETENTION, GA965343) that will develop an Artificial Intelligence (AI)-driven platform to support outpatient monitoring and management of HF patients, this paper provides an overview of the ethical challenges associated with the conduction of relevant randomized controlled trials (RCTs), based on a literature review.

Full article (pag.219)

Heart Failure Patient Management and Interventions using Real-world Data – The RETENTION case

1. Roumpi, Y. Goletsis, V. Pezoulas, A. Pardalis, I. Basdekis, D. Koutsouris, D.I. Fotiadis

RETENTION is a European research project aiming to develop an innovative platform for enhanced clinical monitoring and personalized interventions in chronic heart failure (HF) patients. By combining continuous home monitoring with integration of diverse medical, clinical, physiological, behavioural, psychosocial, and real-world data, the RETENTION system supports clinical decision-making and individualized interventions. This platform will undergo validation through a Randomized Clinical Trial involving 450 HF patients across 6 hospitals in 4 EU countries. Each patient will receive devices such as a smartphone, weight scale, smartwatch, blood pressure monitor, oximeter, home temperature and humidity sensors, and a local gateway. The RETENTION platform’s main services include the Patient Edge (PE), Clinical Site Backend (CSB), and Global Insights Cloud (GIC). The PE collects and analyses real-world data, while the CSB ingests patient data and enables local analytics. The GIC hosts intervention models for training and triggers patient management interventions based on local analytics results. The integration of heterogeneous data, including real-world data, is a key feature of RETENTION, enabling extraction of valuable insights from patients’ daily lives. The RETENTION data model is designed to store and process this heterogeneous data, following HL7 standards and FHIR specifications.

Full article

Α HEART FAILURE PATIENT MANAGEMENT AND INTERVENTIONS PLATFORM, USING CONTINUOUS PATIENT MONITORING OUTSIDE HOSPITALS AND REAL-WORLD DATA

1. Costarides, I. Kouris, M. Haritou, G. Matsopoulos*, D. Koutsouris, RETENTION team

Heart failure (HF), a chronic disease and one of the world’s major disease burdens and despite efforts in improving its prevention, diagnosis and treatment, HF represents the leading cause of disability and premature death throughout the world. The prevalence of HF is estimated to be 1-2% of the adult population in developed countries, reaching more than 1 0% among people over 70 years of age.

Full article (pag.68)

Follow Us