Posts

Posted on

AI-AGE Project Presented at Symposium on Early Vascular Aging

On 10 November 2026, the Faculty of Medicine of the University of Montenegro hosted the multidisciplinary symposium “Cardio-Reno-Neuro-Metabolic Syndrome and Early Vascular Aging” in Podgorica, bringing together more than 130 participants, including national and international experts, academic staff, and medical students.

The symposium was organized by the Faculty of Medicine and the Montenegrin Association for Healthy Vascular Aging, with the support of the International Society for Healthy Vascular Aging (ISVH) and the Ulysseus European University Alliance.

The symposium “Cardio-Reno-Neuro-Metabolic Syndrome and Early Vascular Aging,” held at the Faculty of Medicine, University of Montenegro

As part of the scientific programme, Prof. Dr. Nataša Popović, AI-AGE Project Coordinator and Vice-Dean for Science at the Faculty of Medicine, delivered a presentation on biological aging, frailty, and multimorbidity.

Her lecture highlighted the distinction between chronological and biological age, emerging approaches to assessing biological aging, and their potential for the early identification of individuals at increased health risk.

Prof. Popovic gave a presentation on project results, also pbulished in BMJ Open by the AI-AGE team

The presentation also featured findings from research on frailty and multimorbidity in Montenegro, published in BMJ Open. The study identified a significant increase in chronic disease burden and frailty from approximately 55 years of age, highlighting the importance of earlier preventive interventions.

There was more than 130 participants

These findings are closely aligned with the objectives of the AI-AGE project (Artificial Intelligence Supported Identification of Novel Non-invasive Biomarkers of Aging), which focuses on identifying and investigating non-invasive biomarkers of biological aging using artificial intelligence and exploring their associations with frailty and multimorbidity.

Participation in the symposium provided an opportunity to disseminate AI-AGE research activities, exchange scientific knowledge, and highlight the potential of AI-supported approaches for early detection of accelerated biological aging and the promotion of healthy aging.

Further information: Faculty of Medicine, University of Montenegro

Posted on

MSc Thesis Defence: Explainable AI for Type 2 Diabetes Risk Assessment

On October 21, 2026, MSc candidate Sanja Lazić successfully defended her thesis entitled “Interpretable Machine Learning and Deep Learning Models for Type 2 Diabetes Risk Prediction Based on Behavioural and Clinical Indicators” within the Artificial Intelligence Master’s programme at the University of Donja Gorica, Faculty for Information Systems and Technologies, under the mentorship of Prof. Dr. Tomo Popović.

Ms Sanja Lazic during her thesis defence

The research was partially supported by the AI-AGE project, with additional support from NCC HPC Montenegro within the EuroCC3 project. The thesis explores the application of explainable artificial intelligence to health risk assessment, focusing on the development of reliable and interpretable predictive models that use behavioural, clinical, and demographic indicators without requiring laboratory tests. The work contributes to research and capacity building in medical AI, particularly in model interpretability, reliability, and the potential application of AI-based tools in preventive healthcare.

ABSTRACT – This thesis presents the development and systematic evaluation of machine learning and deep learning models for assessing the risk of type 2 diabetes using questionnaire-based health indicators. The study analysed a dataset containing 253,680 records and 21 predictive variables, comparing five approaches: Logistic Regression, Random Forest, XGBoost, LightGBM, and a deep neural network. Model performance was evaluated in terms of predictive discrimination, probability calibration, and interpretability. While the deep neural network achieved the highest ROC-AUC score (0.7728), LightGBM demonstrated the most balanced overall performance. Explainable AI techniques, including TreeSHAP, Integrated Gradients, and DeepLIFT SHAP, were employed to identify factors contributing to individual predictions. A prototype web application was also developed to demonstrate how estimated risk and its contributing factors could be presented to users. The findings highlight the potential of interpretable AI models to support non-invasive health risk assessment and preventive screening, while emphasizing the need for further validation before clinical application.

Posted on

Keynote on Adapting Higher Education for the AI Era at ICAII 2026

Rethinking education, engineering skills, and human responsibility in the age of artificial intelligence

Prof. Dr. Tomo Popović from the University of Donja Gorica delivered a keynote presentation at the 2026 IEEE 4th International Conference on Artificial Intelligence Innovation (ICAII 2026), held on October 16–18, 2026, in Beijing, China.

His keynote, “Before the Prompt, After the Answer: Adapting Higher Education for the AI Era,” explored how artificial intelligence is reshaping higher education and challenging universities to reconsider what students need to learn in a world where information and AI-generated answers are increasingly accessible.

The presentation emphasized that general education, critical thinking, cultural awareness, and communication skills are becoming more important, not less, in the AI era. Rather than replacing these foundations, AI makes them essential for asking meaningful questions, interpreting results, and applying knowledge responsibly.

From an engineering perspective, the talk highlighted a shift in the role of engineers and IT professionals toward two critical activities: what happens before the prompt, including understanding needs and defining problems, and what happens after the answer, including verification, validation, and responsibility for outcomes.

The keynote advocated a more integrative approach to university education, connecting technical expertise with knowledge from healthcare, business, law, culture, and other disciplines. This perspective also resonates with the interdisciplinary mission of the AI-AGE project, where the responsible application of AI depends on both technological capabilities and domain-specific knowledge.

In addition to his keynote participation, Prof. Dr. Milica Vukotić from the University of Donja Gorica served as a Conference General Co-Chair, while Prof. Popović served as a Conference Program Chair, contributing to the international scientific and organizational activities of ICAII 2026.

More information: ICAII 2026 Conference | Keynote Speakers | Conference Committees

Posted on

Prof. Nataša Popović Presented at Regional Congress of Physiologists in Osijek

The AI-AGE project was presented at the 4th Regional Congress of Physiological Societies and 6th Congress of the Croatian Physiological Society, held on 14–16 October 2026 in Osijek, Croatia. The congress brought together researchers and experts from across the region to exchange scientific findings and discuss advances in physiology, biomedical research, and emerging technologies.

Prof. Dr. Nataša Popović, from the Faculty of Medicine, University of Montenegro, delivered an invited lecture entitled “The Retina as a Window to Systemic Physiology: Translating Physiological Signals into Digital Biomarkers.” The presentation highlighted the AI-AGE project and its research results, focusing on the use of artificial intelligence and retinal imaging to identify potential non-invasive biomarkers of systemic health. Particular attention was given to recent findings exploring the potential of deep learning for detecting disease-associated patterns in retinal images.

Participation in the congress also provided an excellent opportunity for networking and exchanging experiences with colleagues from Croatia, Bosnia and Herzegovina, Serbia, Hungary, and other countries. These discussions helped strengthen regional scientific connections and explore opportunities for future collaboration in AI-supported biomedical research.

The event contributed to the dissemination of AI-AGE results and increased the project’s visibility within the regional scientific community. For more information, visit the official congress website and the Congress Programme and Book of Abstracts.

Posted on

AI-AGE Strengthens Regional Research Collaboration in AI and Healthcare

Meetings in Sarajevo and Osijek open new opportunities for cooperation in biomedical research, digital health, and AI applications.

As part of its efforts to strengthen regional scientific cooperation, the AI-AGE project continued networking with research institutions and experts from Bosnia and Herzegovina and Croatia, exploring opportunities for collaboration in artificial intelligence (AI), high-performance computing (HPC), and biomedical research.

On 14 October 2026, representatives of the University of Donja Gorica and HPC Montenegro (NCC Montenegro) visited the Verlab Research Institute in Sarajevo, where they met with representatives of NCC Bosnia and Herzegovina. The discussions focused on ongoing cooperation, sharing research expertise and computational resources, and exploring joint initiatives in healthcare and medical research.

Meetings with Verlab institute team

Of particular relevance to AI-AGE, Verlab representatives expressed their willingness to support research activities in Montenegro by facilitating connections with healthcare institutions and industry partners and exploring access to relevant biomedical datasets. Such cooperation could support further research into AI-based analysis of aging biomarkers and age-related health conditions.

Meeting with prof. Alisa Elezovic from UNSA

During the Sarajevo visit, the team also met with Prof. Dr. Alisa Elezović from the University of Sarajevo, coordinator of the Erasmus+ AHEDIS (Advancing Higher Education through Digital Innovation and Smart Technologies) project. Both the University of Donja Gorica and Verlab Research Institute are partners in AHEDIS, providing an additional framework for exchanging expertise and developing interdisciplinary cooperation in digital healthcare and biomedical education.

Meeting with prof. Mirza Žižak from UNIZG during the conference in Osijek

Regional networking continued during a visit to Osijek, Croatia, where AI-AGE representatives met with Assoc. Prof. Dr. Mirza Žižak from the University of Zagreb School of Medicine, another AHEDIS project partner. The meeting provided an opportunity to exchange research interests and explore possibilities for future cooperation in biomedical research and digital health.

These interactions also build upon the established collaboration between NCC Montenegro and NCC Bosnia and Herzegovina, currently continuing through the EuroCC 3 project.

By connecting researchers, healthcare experts, and complementary European projects, AI-AGE aims to strengthen its regional research network and create opportunities for future joint activities in AI-driven biomedical research and healthy aging.

Related links:

Posted on

AI-AGE Research on Retinal AI for Colorectal Cancer Published

We are pleased to announce the publication of a new AI-AGE research paper in Current Medical Imaging: “Deep Learning Discrimination of Colorectal Cancer using Retinal Fundus Photographs: UK Biobank Case-Control Study,” by Ivan Jovovic, Tomo Popovic, Isidora Rubezic Lukic, Dejan Babic, and Natasa Popovic.

The study investigates whether deep learning analysis of retinal fundus photographs can distinguish individuals with colorectal cancer (CRC) from those without CRC. Using 1,600 retinal images from the UK Biobank and an EfficientNet-B3 deep learning model, the study achieved an AUROC of 0.945 on an independent participant-level test set.

Click on image to open

The findings support the hypothesis that retinal images may contain measurable signatures associated with systemic diseases beyond ophthalmology. At the same time, the study shows that retinal AI should not currently be considered a stand-alone diagnostic tool for colorectal cancer. Its potential value is primarily as a future non-invasive triage or risk-enrichment approach, subject to further validation in longitudinal and clinically representative populations.

This publication represents an important output of the AI-AGE project and directly contributes to its research objectives related to the use of artificial intelligence and retinal imaging for identifying novel non-invasive biomarkers associated with aging and age-related diseases.

The article was published online on 11 September 2026 in Current Medical Imaging and is currently available as an Early View article [link].

Posted on

AI-AGE Team at the Eastern European Machine Learning Summer School (EEML 2026)

Cetinje, 27 July – 1 August 2026 – Members of the AI-AGE project team took part in the Eastern European Machine Learning Summer School (EEML 2026), one of the largest AI and machine learning gatherings in the region, held in Cetinje with around 300 participants from across the EU.

AI-AGE team members were involved on several levels. They participated in the EEML training programme, strengthening their skills in machine learning and AI methods relevant to the project’s biomedical research. They also contributed as volunteers in the organisation of the school and its activities. In addition, through cross-project collaboration with NCC HPC Montenegro, they provided help and support to participants, including discussions on the use of high-performance computing (HPC) for AI and machine learning.

This participation reflects the close cooperation between AI-AGE and NCC HPC Montenegro, and their shared goal of building AI and HPC capacity in Montenegro and the wider region through both training and hands-on support.

More about the school: www.eeml.eu.

Posted on

AI-AGE at the President’s High-Level Discussion on Artificial Intelligence

Cetinje, 28 July 2026 – A member of the AI-AGE project team took part in a high-level meeting on artificial intelligence hosted by the President of Montenegro and the President’s Cabinet. Our representative was among a group of around ten AI experts from Montenegro invited to this important discussion, alongside the President of the Montenegrin Academy of Sciences and Arts (CANU), representatives of universities, the diaspora, the Montenegrin AI Association (MAIA), and industry.

The discussion focused on directions for the development of artificial intelligence in Montenegro, including the need for data centres and high-performance computing (HPC) infrastructure, and the role of research and education in building national AI capacity. These themes are closely aligned with the mission of AI-AGE, which brings together expertise in AI, HPC and biomedical research to develop non-invasive biomarkers of aging and to strengthen research and educational capacity in the country.

Being invited to this meeting was an important opportunity for AI-AGE to contribute to the national conversation on AI at the highest level of public administration. As part of the discussion, our representative proposed that domain experts — including professionals from the medical field — be included in the strategic dialogue on artificial intelligence in Montenegro, ensuring that AI development is guided by real needs in healthcare and other application areas. The team looks forward to taking part in the further steps that follow from this discussion.

More about the meeting: the President of Montenegro’s Instagram and the post on X.

Posted on

AI-AGE Team Member Participated in Oxford Machine Learning School 2026

Oxford, 14–18 July 2026 – A member of the AI-AGE project team participated in the Oxford Machine Learning School 2026 (OxML), attending the MLx Representation Learning & Generative AI module. The intensive programme brought together more than 150 participants and lecturers from leading academic and industrial research environments, including Oxford, Cambridge, Imperial College London and Google DeepMind.

Participation in the Oxford Machine Learning School 2026 (OxML)

Over four days, the programme covered advanced topics in modern machine learning, ranging from frontier models for vision and language to multimodal representation learning, generative AI and agentic systems. Particular value came from the strong theoretical foundations underlying these methods, complemented by discussions and exchange with researchers from across Europe and beyond.

This was also an opportunity to network with researchers from all over the World

Participation in OxML contributes directly to the capacity-building objectives of the AI-AGE project, strengthening expertise in advanced AI and machine learning methods relevant to the project’s research activities. Such training is particularly important for developing the methodological knowledge required to apply state-of-the-art AI approaches to biomedical data, representation learning and the identification of non-invasive biomarkers of aging.

Dr Stevan Cakic

Participation was co-financed through the 2026 Call for Co-financing Scientific Research Activities provided by the Ministry of Education, science and Innovation.

Posted on

MSc Thesis Defence: Machine Learning and AI Model Development for Medical Applications

On June 29, 2026, MSc candidate Anesa Abazović successfully defended her thesis entitled “Machine Learning and AI Model Development for Medical Applications” within the Artificial Intelligence Master’s programme at the University of Donja Gorica. Through its support for the programme, mentoring activities, and development of competencies in artificial intelligence and high-performance computing, NCC Montenegro contributes to preparing young researchers to apply advanced AI methods in medicine and other socially relevant domains. The thesis investigates the application of machine learning and deep learning to medical image analysis and clinical data classification, while also considering the technical, ethical, and practical challenges of integrating AI systems into healthcare.

Ms Anesa Abazovic during her MSc defence

ABSTRACT – This thesis explores the potential of machine learning (ML) and deep learning (DL) models in the detection of ovarian cancer and the prediction of pneumonia. In the first part, a YOLO model was used to identify tumor lesions in medical images, while in the second part, XGBoost, Random Forest, and neural network models were applied for the classification of clinical data. Model performance was evaluated using metrics such as precision, recall, accuracy, specificity, F1-score, ROC-AUC, MCC, mAP50, and mAP50-95. The experimental analysis demonstrated that AI models can achieve promising performance in both clinical scenarios, with certain limitations that require further validation. In addition to technical aspects, ethical considerations were also examined, including model interpretability, data privacy, and the integration of AI systems into healthcare information systems. It is concluded that AI can provide significant support to modern diagnostics, with the need for further improvements and clinical validation.

Proudly powered by WordPress