AI-AGE team presented a paper titled “Interpretable ML for Diabetes and Prediabetes Screening Using Self-Reported Health Indicators” by S. Lazic, S. Cakic, I. Rubezic Lukic, N. Popovic, and T. Popovic at the 30. Annual Conferenc on Information Technology IT 2026. This was part of mentoring activities and efforts related to development of young researchers.
Image source AI-AGE
ABSTRACT – Early identification of type 2 diabetes (T2D) and prediabetes enables timely interventions, yet screening often relies on self-reported data rather than laboratory testing. This work compares lightweight Machine Learning (ML) models: Logistic Regression (LR), Random Forest (RF), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Multilayer Perceptron (MLP) trained on 21 self-reported indicators from the 2015 Behavioral Risk Factor Surveillance System (BRFSS) dataset for three-class classification (no diabetes, prediabetes, diabetes). We propose a screening-oriented evaluation where a probability threshold is selected to achieve a target sensitivity (recall) of 0.80. LightGBM achieves balanced accuracy of 0.52 and precision of 0.33 at the target sensitivity, with 38% of cases flagged. Tree SHapley Additive exPlanations (TreeSHAP) highlight general health status, age category, body mass index (BMI), and hypertension as dominant predictors. A FastAPI web application provides individual risk estimates and instance-level explanations. The pipeline demonstrates feasibility of interpretable, calibrated screening from non-laboratory data.
At the IEEE IT2026 conference in Žabljak, researchers from the University of Donja Gorica presented PollenTrace, an innovative project combining Artificial Intelligence and High Performance Computing (HPC) to enhance honey authenticity verification. Traditional pollen analysis (melissopalynology), while reliable, is time-consuming and dependent on expert knowledge. PollenTrace addresses this limitation by developing a large-scale microscopy dataset and an AI-driven detection pipeline capable of automatically identifying pollen grains in honey samples.
The project is building a dataset of over 33,000 high-resolution microscopy images derived from more than 1,100 biological samples collected across Montenegro, enabling the development of robust and scalable AI models. As a proof of concept, a deep learning model based on YOLOv11 was trained on annotated microscopy images, achieving 84% precision and 88% recall, demonstrating strong potential for automated pollen detection and future large-scale deployment.
HPC resources played a key role in enabling efficient model training and handling of high-resolution image datasets, highlighting the importance of national HPC infrastructure—such as that provided through NCC Montenegro -in supporting advanced AI applications in agri-food systems. This is also cross-project collaboration.
PollenTrace represents a step forward toward digital, scalable, and reproducible food authenticity verification, with strong potential to support laboratories, regulatory bodies, and industry in ensuring product quality and consumer trust. PollenTrace is supported as a PoC project by the Innovation Fund of Montenegro.
The University of Donja Gorica, through the Faculty for Information Systems and Technologies, proudly announces the successful PhD defence of Mr. Stevan Čakić, focused on the application of Artificial Intelligence and High-Performance Computing in precision agriculture.
The research addresses key challenges in modern agriculture, particularly in poultry farming, by leveraging deep learning and computer vision models for real-time monitoring, early disease detection, and improved farm management. The models were developed and trained using HPC resources, enabling efficient experimentation and achieving high prediction accuracy exceeding 92% . A significant contribution of this work lies in the integration of HPC-based model development with deployment on edge devices in real farm environments, demonstrating a complete AI-to-industry pipeline. The research also explores the use of generative AI and synthetic data to reduce dependency on large annotated datasets, accelerating innovation cycles.
mr Stevan Cakic presenting his PhD Thesis on AI/HPC in precision agriculture
Importantly, part of this research was conducted in synergy with the FFplus experiment and in direct collaboration with industry partners, highlighting the role of HPC in enabling real-world, industry-driven AI applications. This achievement further demonstrates the impact of the NCC Montenegro and EuroCC2 & EuroCC4SEE initiatives in supporting advanced research, fostering academia-industry collaboration, and promoting the adoption of HPC technologies in strategic sectors such as agriculture.
We are pleased to announce the upcoming “AI in Action for SMEs” training, organized within the EuroCC4SEE initiative by NCC Montenegro, NCC Serbia, NCC Bosnia and Herzegovina, and NCC Türkiye. This training will take place March 2-3, 2026.
Click on image for more info and registration
The 1.5-day online training is designed for SMEs, start-ups, technical leads, and researchers interested in practical adoption of Artificial Intelligence supported by High-Performance Computing (HPC).
The programme focuses on applied AI methods with live demonstrations and real-world use cases.
Day 1 covers Time Series Forecasting with AI & Machine Learning and Explainable AI (XAI), including HPC-enabled demonstrations and practical insights for business and healthcare applications. NCC Montenegro will actively contribute to the time-series and HPC session, presenting practical approaches relevant for SMEs.
Day 2 is dedicated to Applied Data Anonymization Techniques, addressing data protection challenges and practical anonymization approaches essential for responsible AI deployment
Invitation to Participants from Montenegro
As a co-organizer, NCC Montenegro will also present during the programme. We invite companies, researchers, and innovators from Montenegro to register and participate in this regional training.
This is an opportunity to:
Learn from hands-on AI & HPC demonstrations
Connect with regional NCC experts
Strengthen AI adoption capacity within your organization
Participation is free, and registration is open via the event page.
We look forward to strong participation from Montenegro.
We are pleased to announce that the research team from the Faculty of Science and Mathematics has published a scientific paper titled “Data augmentation for fuselage panel inspection via 3D point cloud segmentation” in the Journal of Electronic Imaging. The paper presents advanced data augmentation methods to improve fuselage panel inspection using 3D point cloud segmentation, contributing to more accurate and reliable AI-based inspection systems. The research was enabled by access to the Leonardo HPC supercomputing resources, granted through the EuroCC2 project, which allowed the team to process large datasets and develop high-performance models efficiently. More info at: https://doi.org/10.1117/1.JEI.35.3.031202
From 25 to 28 February, in Žabljak, within the framework of the traditional IT Conference – one of the most significant scientific and professional conferences in the field of engineering and information sciences, held with IEEE support (triple IEEE concept in engineering) – the EUROCC4SEE Conference will be organized, with both in-person and online participation of partners.
EuroCC 2 & EuroCC4SEE at IEEE IT2026 in Zabljak
The conference will gather members of the EUROCC4SEE team, representatives of National Competence Centres (NCCs), as well as representatives of companies, the business community, and the public sector from the region and beyond. According to current registrations, more than 200 participants are expected, confirming the strong regional and international character of the event.
As part of the conference, a training session and workshop will be organized in line with the strategic tourism development priorities of all EUROCC4SEE countries, entitled: “Application of HPC and AI to Enhance the Tourism Offer”, aiming to present the possibilities of applying High Performance Computing (HPC) and Artificial Intelligence in improving tourism services, data analytics, and the development of innovative digital solutions.
The conference program will also include presentations of research papers, proof-of-concept projects, and HPC success stories demonstrating the practical application of HPC infrastructure in science, industry, and the development of new technologies.
Special focus will be placed on two central panels:
Application of HPC in Science and Industry – Real Examples and Success Stories, bringing together representatives of academia, industry, and the public sector to exchange experiences and present concrete examples of HPC solution implementation;
Regional Cooperation and EuroCC Experience – EUROCC4SEE: What Have We Learned and Where Do We Go Next? Lessons Learned and Regional Experiences, focused on analyzing project results achieved so far, sharing regional experiences, and defining future directions for the development of the HPC ecosystem in Southeast Europe.
In order to strengthen cooperation with industry and institutions, B2B Meetings and Collaborative Initiatives Toward EUROCC3 will also be organized, enabling direct meetings with business partners, public sector representatives, and potential HPC resource users.
The EUROCC4SEE conference represents an important platform for knowledge exchange, enhancement of regional cooperation, and strengthening the application of HPC technologies in science, industry, and public policies, confirming the strategic importance of digital infrastructure and innovation ecosystem development in the region.
Podgorica, 13 February 2026 – The Faculty of Medicine at the University of Montenegro hosted a regional symposium dedicated to the application of High-Performance Computing (HPC) and Artificial Intelligence (AI) in healthcare and medical research.
The event was organized by NCC Montenegro, in collaboration with the Faculty for Information Systems and Technologies (UDG) and the Faculty of Medicine (UoM), within the framework of the EuroCC2 and EuroCC4SEE projects, with additional support from the AI-AGE research project.
Bringing together approximately 20 participants from healthcare institutions, academia, innovative companies, and regional partners from Bosnia and Herzegovina, the symposium aimed to strengthen collaboration and advance the adoption of AI and HPC technologies in the health sector.
From Vision to Implementation
The programme combined strategic presentations, regional cooperation sessions, and technical demonstrations, creating a comprehensive overview of the current state of HPC and AI in healthcare.
NCC Montenegro presented Montenegro’s role as a national reference point for HPC, High-Performance Data Analytics (HPDA), and AI development. The presentation traced the entire pipeline—from clinical and biomedical data collection to AI model development and HPC-accelerated deployment.
A central message of the event was clear: HPC in healthcare is not merely about computational speed. It enables rigorous validation, reproducibility, and scalable deployment of AI models in real clinical environments.
Use cases discussed during the symposium included radiology, digital pathology, cardiology, genomics, ICU monitoring, and public health forecasting
AI-AGE: Advancing Research on Ageing
A dedicated session focused on the AI-AGE project, which explores retinal fundus imaging as a potential biomarker for accelerated biological ageing.
The interdisciplinary team presented research results based on UK Biobank data and datasets collected in Montenegro. Findings indicate that the complexity of retinal microvascular networks may decline more rapidly in patients with chronic diseases, highlighting potential applications in early diagnosis and monitoring.
Speakers emphasized the importance of careful model validation, addressing training bias, and ensuring responsible clinical deployment. The discussion also highlighted the potential of EuroHPC resources to further strengthen research capacity and computational scalability
Technical Showcase: AI Solutions Already in Practice
One of the most dynamic parts of the symposium was the Technical Showcase, where companies from Montenegro and Bosnia and Herzegovina presented concrete AI and HPC-enabled healthcare solutions.
Among the showcased innovations were:
AI-powered colon cancer detection in digital pathology using deep learning on high-resolution histopathology slides
AI-driven IoT platforms supporting clinical decision-making and patient management
AI systems for Alzheimer’s disease care, including predictive digital twins and multimodal reasoning tools
HPC-supported computational simulations accelerating pharmaceutical drug development
A particularly valuable component of the session was the sharing of experiences from companies that successfully applied for and received EuroHPC computing resources. These examples demonstrated how access to supercomputing infrastructure directly enhances model development, testing, and product readiness.
Strengthening Regional Cooperation
The symposium also included a regional twinning workshop between NCC Montenegro and NCC Bosnia and Herzegovina.
The session focused on joint strategies for stakeholder engagement, cross-border resource sharing, and knowledge transfer. The discussion confirmed that the twinning model is an effective mechanism for strengthening the South-East European HPC ecosystem and facilitating access to European supercomputing infrastructure.
Such cooperation is particularly important as the region prepares for the next phase of European HPC initiatives and increasing alignment with the EU AI Act and broader digital strategies.
Addressing Systemic Challenges
The event concluded with an interactive panel discussion titled “Orchestrating the Ecosystem.” Participants addressed key challenges facing AI adoption in healthcare, including:
The healthcare data gap and fragmentation
Regulatory complexity, particularly in the context of the EU AI Act
The need for stronger partnerships between industry, academia, and healthcare institutions
While AI model architectures continue to mature rapidly, participants agreed that the primary bottlenecks lie in data heterogeneity, evaluation standards, and deployment constraints rather than algorithmic limitations.
Healthcare representatives acknowledged the growing importance of HPC and AI in medical research but emphasized the need to improve institutional readiness for strategic and sustainable adoption.
A Strategic Step Forward
The symposium concluded with a shared commitment to:
Position AI and HPC as strategic priorities in healthcare innovation
Continue expanding infrastructure and access to HPC resources
Invest in skills development and capacity building
Strengthen regional collaboration across South-East Europe
The event marked an important step in connecting research excellence, industrial innovation, and clinical practice—demonstrating that HPC-enabled AI in healthcare is no longer a future concept, but an emerging regional reality.
