MicroRNAs (miRNAs) are key post-transcriptional regulators implicated in neuroinflammatory and neurodegenerative processes underlying multiple sclerosis (MS). This study aimed to identify candidate miRNAs associated with MS and investigate their involvement in disease-related molecular pathways. An integrated in silico workflow was used to identify MS-associated genes, predict regulatory miRNAs, and characterize enriched pathways. Candidate miRNAs were validated in serum EV-enriched fractions from treated and untreated MS patients and healthy controls using quantitative polymerase chain reaction (qPCR). In silico analysis prioritized four miRNAs (miR-204-5p, miR-17-5p, miR-21-5p, and miR-106a-5p) for validation. Their predicted target genes were enriched in pathways related to immune regulation and central nervous system function, including Th17 cell differentiation, MAPK signaling, cytokine signaling, and axon guidance. qPCR revealed significant differences in miR-21-5p and miR-106a-5p expression between MS patients and healthy controls, while miR-204-5p differed between untreated MS patients and healthy controls. Among the four miRNAs evaluated, miR-21-5p was significantly associated with MS status and showed moderate discrimination between MS patients and healthy controls (AUC = 0.7204). These findings identify serum EV-enriched miRNAs as candidate biomarkers of MS, although validation in larger and longitudinal cohorts is required.

AttractAdria is a Horizon Europe initiative that strengthens research and innovation ecosystems in the Adriatic region by improving research careers and capacity in personalised preventive healthcare. Its ecosystem-based approach combines institutional reform, research-support hubs, mentorship, training, mobility and academia-industry collaboration. Transferable skills are developed alongside competencies in biomarkers, genomics, glycomics, digital health, artificial intelligence, and clinical and translational research. By linking widening-region institutions with international partners, healthcare providers, industry, policymakers and funders, the project aims to improve career development, talent circulation and the region's ability to translate multidisciplinary research into responsible preventive-health innovation.

CardioPharmaGENET COST Action network aims to advance personalized medicine in cardiovascular care by leveraging pharmacogenomics (PGx) to optimize drug therapies. In cardiovascular medicine, this approach is especially critical, given the significant patient variability in drug responses to therapies. The main goal is to establish a pan-European network that addresses several key challenges that hinder the widespread adoption of PGx in cardiovascular care. These challenges include the lack of a centralized knowledge hub for clinicians and policymakers, insufficient integration of PGx into clinical practice, and inconsistent policy frameworks across Europe. The project also seeks to utilize AI and machine learning to streamline the analysis of large-scale genomic data and enhance clinical decision-making. The network includes five working groups (WG) to tackle these issues: WG1 evaluates the current landscape of cardiovascular PGx, identifying key gaps in research, clinical integration, and available resources; WG2 develops optimized guidelines for applying PGx in cardiovascular therapies, focusing on patient stratification based on genetic and demographic profiles; WG3 focuses on advancing digital and AI tools to improve PGx data analysis and implementation in clinical settings; WG4 analyzes regulatory frameworks across Europe, proposing policy changes to facilitate seamless integration of PGx into healthcare systems; WG5 handles communication, dissemination, and stakeholder engagement, ensuring that findings and guidelines are accessible to all stakeholders, including clinicians, researchers, and policymakers. By addressing these challenges, the network will help bridge the gap between PGx research and clinical practice, improving cardiovascular patient outcomes and promoting equitable healthcare access across Europe. This manuscript represents the COST Association-approved Memorandum of Understanding of COST Action CA24165 CardioPharmaGENET.

Despite widespread discussion of digital transformation, many organizations struggle to assess their digital capability and define improvement priorities. We developed a transparent self-assessment tool, implemented as a Streamlit web application, based on 25 items grouped into five dimensions. Dimension averages are combined into a weighted overall score (1-5 scale) using explicit and visible scoring rules. The tool was evaluated through a single organizational case study (XL Labs) and a pilot expert review (N = 3), providing preliminary, non-generalizable evidence. In the case study, the organization achieved a score of 3.41 / 5.00, corresponding to the Intermediate maturity category, which remained stable under one-at-a-time sensitivity analysis (±0. 20 per dimension).

BACKGROUND AND OBJECTIVE Peripheral artery disease (PAD) is a progressive vascular condition affecting >237 million individuals worldwide. Accurate diagnosis and patient-specific treatment planning are critical but are often hindered by limited access to advanced imaging tools and real-time analytical support. This study presents DECODE, an open-source, cloud-based platform that integrates artificial intelligence, interactive 3D visualization, and computational modeling to improve the noninvasive management of PAD. METHODS The DECODE platform was designed as a modular backend (Django) and frontend (React) architecture that combines deep learning-based segmentation, real-time volume rendering, and finite element simulations. Peripheral artery and intima-media thickness segmentation were implemented via convolutional neural networks, including extended U-Net and nnU-Net architectures. Centreline extraction algorithms provide quantitative vascular geometry analysis. Balloon angioplasty simulations were conducted via nonlinear finite element models calibrated with experimental data. Usability was evaluated via the System Usability Scale (SUS), and user acceptance was assessed via the Technology Acceptance Model (TAM). RESULTS Peripheral artery segmentation achieved an average Dice coefficient of 0.91 and a 95th percentile Hausdorff distance 1.0 mm across 22 computed tomography dataset. Intima-media segmentation evaluated on 300 intravascular optical coherence tomography images demonstrated Dice scores 0.992 for the lumen boundaries and 0.980 for the intima boundaries, with corresponding Hausdorff distances of 0.056 mm and 0.101 mm, respectively. Finite element simulations successfully reproduced the mechanical interactions between balloon and artery models in both idealized and subject-specific geometries, identifying pressure and stress distributions relevant to treatment outcomes. The platform received an average SUS score 87.5, indicating excellent usability, and an overall TAM score 4.21 out of 5, reflecting high user acceptance. CONCLUSIONS DECODE provides an automated, cloud-integrated solution for PAD diagnosis and intervention planning, combining deep learning, computational modeling, and high-fidelity visualization. The platform enables precise vascular analysis, real-time procedural simulation, and interactive clinical decision support. By streamlining image processing, enhancing segmentation accuracy, and enabling in-silico trials, DECODE offers a scalable infrastructure for personalized vascular care and sets a new benchmark in digital health technologies for PAD.

BackgroundDialysis is a very complex treatment that is received by around 3 million people annually. Around 10% of the death cases in the presence of the dialysis machine were due to the technical errors of dialysis devices. One of the ways to maintain dialysis devices is by using machine learning and predictive maintenance in order to reduce the risk of patient's death, costs of repairs and provide a higher quality treatment.ObjectivePrediction of dialysis machine performance status and errors using regression models.MethodThe methodology includes seven steps: data collection, processing, model selection, training, evaluation, fine-tuning, and prediction. After preprocessing 1034 measurements, twelve machine learning models were trained to predict dialysis machine performance, and temperature and conductivity error values.ResultsEach model was trained 100 times on different splits of the dataset (80% training, 10% testing, 10% evaluation). Logistic regression achieved the highest accuracy in predicting dialysis machine performance. For temperature predictions, Lasso regression had the lowest MSE on training data (0.0058), while Linear regression showed the highest R² (0.59). For conductivity predictions, Lasso regression provided the lowest MSE (0.134), with Decision tree achieving the highest R² (0.2036). SVM attained the lowest MSE on testing dataset, with 0.0055 for temperature and 0.1369 for conductivity.ConclusionThe results of this study demonstrate that clinical engineering (CE) and health technology management (HTM) departments in healthcare institutions can benefit from proposed automated systems for advanced management of dialysis machines.