Demetris Gerogiannis
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Demetris Gerogiannis has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Alexandra Siorenta
Immunology Department & National Tissue Typing Center, General Hospital of Athens “G. Gennimatas”, 11527 Athens, Greece
1 shared publication - Aliki G. Iniotaki
Clinic of Nephrology and Renal Transplantation, Medical School of Athens, National and Kapodistrian University, Laiko General Hospital, 11527 Athens, Greece
1 shared publication - Angeliki G. Vittoraki
Immunology Department & National Tissue Typing Center, General Hospital of Athens “G. Gennimatas”, 11527 Athens, Greece
1 shared publication - Asimina Fylaktou
Department of Immunology, National Peripheral Histocompatibility Center, Hippokration General Hospital of Thessaloniki, 54642 Thessaloniki, Greece
1 shared publication - Elsa Papadopoulou
Ionian University, Corfu, Greece
1 shared publication - George Ch Petasis
School of Medicine, Aristotle University of Thessaloniki, 45636 Thessaloniki, Greece
1 shared publication
Latest Publications
- Open Access
- 4 June 2024
- Published by MDPI AG in Preprints.org
An ‘Algorithmic Ethics’ Effectiveness Impact Assessment Framework’ for developers of Artificial Intelligence (AI) systems in healthcare
Algorithmic systems used in healthcare contexts are primarily developed for the benefit of the public. It is therefore essential that these systems are trusted by the individuals for whose benefit they are deployed. Drawing inspiration from the principles embedded in the testing of the safety, efficacy and effectiveness of new medicinal products, concurrent design engineering and pro-fessional certification requirements, the authors propose, for the first time, a preliminary com-petency-based ‘Algorithmic Ethics’ Effectiveness Impact Assessment’ framework for developers of AI systems used in healthcare contexts. They concluded that this set of principles should en-compass the algorithmic systems ‘production lifecycle’, to guarantee the optimized use of the AI technologies, avoiding biases and discrimination while ensuring the best possible outcomes, simultaneously increasing decision-making capacity and the accuracy of the results. As AI is as good as those who program it and the system in which it operates, the robustness and trustworthiness of their ‘creators’ and ‘deployers’, should be fostered by a certification system guaranteeing the latter’s knowledge and understanding of ethical aspects as well as their com-petencies in integrating these aspects in trustworthy AI systems when used in healthcare con-texts.
- 4 June 2024
- Published by MDPI AG in Preprints.org
Open AccessAn ‘Algorithmic Ethics’ Effectiveness Impact Assessment Framework’ for developers of Artificial Intelligence (AI) systems in healthcare
Algorithmic systems used in healthcare contexts are primarily developed for the benefit of the public. It is therefore essential that these systems are trusted by the individuals for whose benefit they are deployed. Drawing inspiration from the principles embedded in the testing of the safety, efficacy and effectiveness of new medicinal products, concurrent design engineering and pro-fessional certification requirements, the authors propose, for the first time, a preliminary com-petency-based ‘Algorithmic Ethics’ Effectiveness Impact Assessment’ framework for developers of AI systems used in healthcare contexts. They concluded that this set of principles should en-compass the algorithmic systems ‘production lifecycle’, to guarantee the optimized use of the AI technologies, avoiding biases and discrimination while ensuring the best possible outcomes, simultaneously increasing decision-making capacity and the accuracy of the results. As AI is as good as those who program it and the system in which it operates, the robustness and trustworthiness of their ‘creators’ and ‘deployers’, should be fostered by a certification system guaranteeing the latter’s knowledge and understanding of ethical aspects as well as their com-petencies in integrating these aspects in trustworthy AI systems when used in healthcare con-texts.
- Open Access
- 29 November 2022
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 11 (23) , 7046
An Approach to Identify HLA Class II Immunogenic Epitopes in the Greek Population through Machine Learning Algorithms
Current pre-transplantation routine matching involves serum anti-HLA antibodies quantification but cannot always preclude unfavorable graft outcomes. Epitope-based matching is proposed as a more precise approach, but to date no epitope-matching algorithm provides a satisfactory predictive tool for transplantation outcomes. In this study, anti-HLA-II loci responses from 1748 patients were analyzed with unsupervised machine learning algorithms, namely principal component analysis (PCA) and antigenic distances, projected as dendrograms. PCA for anti-HLA-DR anti-bodies revealed three main clusters of responses: anti-HLA-DR51 combined with anti-HLA-DRB1*01, anti-HLA-DR52 combined with anti-HLA-DRB1*08 and anti-HLA-DR53 combined with anti-HLA-DRB1*10. The dendrogram for anti-HLA-DR confirmed the pattern and showed further bisection of each cluster. Common epitopes present exclusively in all HLA molecules of each cluster were determined following the HLA epitope registry. Thus, we propose that 19 out of 123 HLA-DR epitopes are those that mainly lead anti-HLA-DR responses in the studied population. Likewise, we identified 22 out of 83 epitopes responsible for anti-HLA-DQ and 13 out of 62 responsible for anti-HLA-DP responses. Interpretation of these results may elucidate mechanisms of interlocus cross-reactivity, providing an alternative way of estimating the significance of each epitope in a population and thus suggesting a novel strategy towards optimal donor selection.
- 29 November 2022
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 11 (23) , 7046
Open AccessAn Approach to Identify HLA Class II Immunogenic Epitopes in the Greek Population through Machine Learning Algorithms
Current pre-transplantation routine matching involves serum anti-HLA antibodies quantification but cannot always preclude unfavorable graft outcomes. Epitope-based matching is proposed as a more precise approach, but to date no epitope-matching algorithm provides a satisfactory predictive tool for transplantation outcomes. In this study, anti-HLA-II loci responses from 1748 patients were analyzed with unsupervised machine learning algorithms, namely principal component analysis (PCA) and antigenic distances, projected as dendrograms. PCA for anti-HLA-DR anti-bodies revealed three main clusters of responses: anti-HLA-DR51 combined with anti-HLA-DRB1*01, anti-HLA-DR52 combined with anti-HLA-DRB1*08 and anti-HLA-DR53 combined with anti-HLA-DRB1*10. The dendrogram for anti-HLA-DR confirmed the pattern and showed further bisection of each cluster. Common epitopes present exclusively in all HLA molecules of each cluster were determined following the HLA epitope registry. Thus, we propose that 19 out of 123 HLA-DR epitopes are those that mainly lead anti-HLA-DR responses in the studied population. Likewise, we identified 22 out of 83 epitopes responsible for anti-HLA-DQ and 13 out of 62 responsible for anti-HLA-DP responses. Interpretation of these results may elucidate mechanisms of interlocus cross-reactivity, providing an alternative way of estimating the significance of each epitope in a population and thus suggesting a novel strategy towards optimal donor selection.