Keynote Speech #1: Towards Ethical and Trustworthy AI in Healthcare: Principles, Dimensions, and Open Challenges
Prof. Dimitrios I. Fotiadis
Abstract: The rapid integration of artificial intelligence (AI) into healthcare settings has intensified the need for principled frameworks that go beyond predictive performance and address the broader ethical, legal, and social dimensions of clinical AI deployment. Despite growing regulatory momentum, including the EU AI Act and GDPR, the operationalization of trustworthiness and ethical compliance in AI remains fragmented and inconsistent across institutions and use cases. This work presents a trustworthiness assessment framework developed within the EU-funded FAITH project as a structured response to this challenge. The framework systematizes trustworthiness across key ethical and technical dimensions including fairness, explainability, privacy, robustness, and accountability, grounding each in established ethical principles such as beneficence, non-maleficence, autonomy, and justice. Complementing the framework, the FAITH ecosystem introduces structured documentation mechanisms for transparent governance of AI assets, alongside dedicated tools for continuous monitoring and real-time trustworthiness evaluation in clinical environments. Together, these components establish a cohesive infrastructure for ethics- and trust-by-design in medical AI. Open challenges including ethical governance across institutions, regulatory alignment with the EU AI Act, and the moral dimensions of human-AI collaboration are discussed, positioning trustworthy and ethical AI as inseparable imperatives in the responsible deployment of clinical intelligence.
Keynote Speech #2: Hybrid Computational Intelligence for Early Autism Detection in Infants
Prof. George Magoulas
Abstract: The search for reliable biomarkers of Autism Spectrum Disorder (ASD) has grown rapidly in recent years, with EEG-based methods emerging as a promising direction. At the same time, longitudinal studies indicate that early behavioural interventions can influence developmental outcomes, and that the enhanced neuroplasticity of infancy offers an opportunity window to apply targeted interventions that may impact the developmental trajectory associated with ASD. However, developing digital biomarkers for reliable early detection remains challenging because there is inherent variability in the ASD manifestation and any practical solution must rely on simple measurements that can be collected during infant checkups. This talk presents work on using infant EEG and hybrid computational intelligence to identify early digital biomarkers of ASD. The proposed framework combines topology-preserving transformations of infant EEG into image-like representations and hyper-connectivity signatures within a hybrid computational intelligence pipeline. The analysis uses infant EEG from the British Autism Study of Infant Siblings cohort, a longitudinal study of infants at elevated likelihood for autism in the UK. Our results show that these representations encode discriminative structure relevant to early ASD screening and together with hybrid computational intelligence methods for learning from the underlying information they could support early autism detection.
Keynote Speaker Short CVs
Prof. Dimitrios I. Fotiadis
Prof. Dimitrios I. Fotiadis (Male), received the Diploma degree in chemical engineering from the National Technical University of Athens, Athens, Greece, and the Ph.D. degree in chemical engineering and materials science from the University of Minnesota, Minneapolis. He is currently a Professor of Biomedical Engineering in the Department of Materials Science and Engineering, University of Ioannina, Ioannina, Greece, where he is also the Director of the Unit of Medical Technology and Intelligent Information Systems, an Affiliated Member of Foundation for Research and Technology Hellas, Biomedical Research Institute and Director MSc in Digital Health. He is member of the board of Michailideion Cardiac Center. He was a Visiting Researcher at the RWTH, Aachen, Germany, and the Massachusetts Institute of Technology, Boston. He has coordinated and participated in more than 250 R&D funded projects (in FP6, FP7, H2020, Horizon Europe and national Projects), being the coordinator (e.g. INSILC, TAXINOMISIS, HOLOBALANCE, CARDIOCARE, DECODE, etc.) and/or Technical coordinator (e.g. SMARTOOL, KARDIATOOL, TO_AITION, etc.). He is the author or coauthor of more than 500 papers in scientific journals, more than 600 papers in peer-reviewed conference proceedings, and more than 50 chapters in books. He is also the author/editor of 30 books. His work has received more than 38,500 citations (h-index=87). He served as Editor in Chief of IEEE Journal of Biomedical and Health Informatics from 2017-2024 and he is IEEE EMBS Fellow, EAMBES Fellow, Fellow of IAMBE, Fellow of AIAA, member of the IEEE Technical Committee of Biomedical Health Informatics, Editor in Chief of IEEE Open Journal of Engineering in Medicine and Biology, Member of the Editorial Board in IEEE Reviews in Biomedical Engineering, member of the Editorial Board of Health Information Science and Systems (HISC), member of the European Academy of Sciences and Arts and member of the National Academy of Artificial Intelligence (NAAI). His research interests include multiscale modelling of human tissues and organs, intelligent wearable/implantable devices for automated diagnosis, processing of big medical data, machine learning, sensor informatics, image informatics, and bioinformatics. He is the recipient of many scientific awards including the one by the Academy of Athens. He is the co-founder of PD Neurotechnology Ltd, UK, Intelligence4Rehab and SYNTHAINA AI.
Prof. George Magoulas
Dr George Magoulas is Professor of Computer Science at Birkbeck’s School of Computing & Mathematical Sciences, and Director of the Birkbeck Knowledge Lab, University of London. The Knowledge Lab pursues research on digital technologies, digital information and artificial intelligence and investigates how developments in these areas are transforming the way people learn, work and communicate. Current applications of his work are in intelligent systems for psychophysiological data modelling and classification (neurodegenerative diseases, ASD), and in intelligent environments (AI in education, learning technologies, autonomous AI systems for services management and systems integration). His group designs and develops innovative learning algorithms, system components that employ machine learning, sometimes combined with knowledge engineering, learner models and intelligent tutors. His work has received best paper awards from the IEEE (2000 ,2008), the European Network on Intelligent Technologies for Smart Adaptive Systems (2001 and 2004), the International Association for Development of the Information Society (2006), the ACM (2009), KES International (2010) and EANN/AIAI (2021). His research has been funded by UK funding agencies- EPSRC, ESRC, AHRC, JISC- and the EU.