1. Variational oblique predictive clustering treesViktor Andonovikj, Sašo Džeroski, Biljana Mileva Boshkoska, Pavle Boškoski, 2026, original scientific article Abstract: Oblique predictive clustering trees (SPYCTs) are semi-supervised multi-target prediction models mainly used for structured output prediction (SOP) problems. They are computationally efficient and when combined in ensembles they achieve state-of-the-art results. However, one major issue is that it is challenging to interpret an ensemble of SPYCTs without the use of a model-agnostic method. We propose variational oblique predictive clustering trees, which address this challenge. The parameters of each split node are treated as random variables, described with a probability distribution, and they are learned through the Variational Bayes method. We evaluate the model on several benchmark datasets of different sizes. The experimental analyses show that a single variational oblique predictive clustering tree (VSPYCT) achieves competitive, and sometimes better predictive performance than the ensemble of standard SPYCTs. We also present a method for extracting feature importance scores from the model. Finally, we present a method to visually interpret the model’s decision making process through analysis of the relative feature importance in each split node.
Keywords: machine learning, predictive clustering, interpretable models, structured output prediction, uncertainty quantification
Published in DiRROS: 17.02.2026; Views: 146; Downloads: 52
 Full text (2,20 MB)
This document has many files! More... |
2. Data in diabetic foot care : from current state to a management framework for implementationIztok Štotl, 2025, review article Abstract: Background/Objectives: The healthcare data sector is experiencing unprecedented growth, fueled by advances in genomics, medical imaging, and wearable devices. The convergence of universal data standards now provides the common ground needed to translate this data into medical advances. However, a significant implementation gap persists, preventing effective deployment in routine clinical practice, particularly in specialized areas like diabetic foot care. Methods: This paper examines the opportunities presented by modern data methodologies to bridge this gap, contextualized within diabetic foot care, where the paramount goals are patient well-being, tissue preservation, and amputation prevention. Results: The analysis indicates that the synergy of interoperable data and advanced management tools is poised to fundamentally transform healthcare delivery. Interdisciplinary collaboration is identified as the foundational element enabling the timely, coordinated, and evidence-based interventions necessary to achieve critical clinical objectives. Conclusions: The pivotal challenge has shifted from technological capability to effective implementation. Leveraging modern data methodologies is essential for translating potential into tangible improvements in diabetic foot outcomes. In this context, collaborative data management must be recognized as a critical treatment modality itself. Here, “data is tissue”; it must be managed with the same urgency and care to enable success.
Keywords: diabetes, diabetic foot, electronic health record, governance, prediction models, digital practice guidelines, guidelines definition language, diabetes registries, fair, quality of care
Published in DiRROS: 17.12.2025; Views: 390; Downloads: 144
Full text (732,61 KB)
This document has many files! More... |
3. Breast cancer risk based on adapted IBIS prediction model in Slovenian women aged 40-49 years : coul it be better?Tjaša Oblak, Vesna Zadnik, Mateja Krajc, Katarina Lokar, Janez Žgajnar, 2020, original scientific article Keywords: breast surgery, IBIS, prediction models, risk factors
Published in DiRROS: 12.07.2024; Views: 966; Downloads: 357
Full text (286,49 KB) |
4. Impact of climate change on landslides in Slovenia in the mid-21st centuryMateja Jemec Auflič, Gašper Bokal, Špela Kumelj, Anže Medved, Mojca Dolinar, Jernej Jež, 2021, original scientific article Abstract: Slovenia is affected by extreme and intense rainfall that triggers numerous landslides every year, resulting in significant human impact and damage to infrastructure. Previous studies on landslides have shown how rainfall patterns can influence landslide occurrence, while in this paper, we present one of the first study in Slovenia to examine the impact of climate change on landslides in the mid-21st century. To do this, we used the Representative Concentration Pathway (RCP) 4.5 climate scenario and future climatology simulated by six climate models that differed from each other as much as possible while representing measured values of past climate variables as closely as possible. Based on baseline period (1981-2010) we showed the number of days with exceedance of rainfall thresholds and the area where landslides may occur more frequently in the projection period (2041-2070). We found that extreme rainfall events are likely to occur more frequent in the future, which may lead to a higher frequency of landslides in some areas.
Keywords: climate change, landslides, models, hazard, prediction
Published in DiRROS: 09.03.2022; Views: 2534; Downloads: 774
Full text (4,78 MB) |
