1. |
2. |
3. Data and data quality in mathematicsKatja Berčič, 2026, samostojni znanstveni sestavek ali poglavje v monografski publikaciji Povzetek: Pure mathematics is often viewed, even by its practitioners, as a discipline in which data play little or no role. Data, when acknowledged at all, are often seen as a byproduct of research rather than a research product in their own right. Yet databases and datasets are increasingly central to the way mathematicians formulate conjectures, test hypotheses, and explore complex structures. Unlike empirical data, data in mathematics often consist of exact values derived from symbolic definitions or computations and commonly describe highly structured objects such as graphs, elliptic curves, or manifolds. This combination of abstraction, precision, and low redundancy poses distinctive challenges for data quality, shifting the focus away from concerns like noise and bias toward correctness, completeness, consistency, and accessibility.
Ključne besede: mathematical knowledge management, digital mathematics libraries and repositories, computer-assisted mathematics, implementation challenges, data quality dimensions, mathematical data
Objavljeno v DiRROS: 06.05.2026; Ogledov: 83; Prenosov: 84
 Celotno besedilo (831,18 KB)
Gradivo ima več datotek! Več... |
4. |
5. Fake news detection through LLM-driven text augmentation across media and languagesAbdul Sittar, Mateja Smiljanić, Alenka Guček, Marko Grobelnik, 2026, izvirni znanstveni članek Povzetek: The proliferation of fake news across social media, headlines, and news articles poses major challenges for automated detection, particularly in multilingual and cross-media settings affected by data imbalance. We propose a fake news detection framework based on LLM-driven, feature-guided text augmentation. The method generates realistic synthetic samples across languages, media types, and text granularities while preserving mean ing and stylistic coherence. Experiments with classical and transformer-based models (Random Forest, Logistic Regression, BERT, XLM-R) across social media, headlines, and multilingual news datasets show consistent improvements in performance. For inherently balanced datasets (e.g., social media), synthetic augmentation yields negligible but stable performance changes. Across imbalanced scenarios, synthetic augmentation substantially improves minority-class recall and F1-score (e.g., fake news recall from 0.57 to 0.86), while preserving majority-class performance, leading to more balanced and reliable classifiers, whereas oversampling significantly degrades results due to overfitting on duplicated language patterns. Overall, a hybrid semantic- and style-based model proves to be the most robust strategy, outperforming oversampling and matching or exceeding baseline performance across datasets
Ključne besede: fake news detection, low-resource languages, data imbalance, synthetic data generation, prompt engineering, style-based features, semantic features
Objavljeno v DiRROS: 28.04.2026; Ogledov: 171; Prenosov: 112
Celotno besedilo (1,16 MB)
Gradivo ima več datotek! Več... |
6. Ethical considerations on the use of big data and artificial intelligence in kidney research from the ERA ethics committeeWim Van Biesen, Jadranka Buturović-Ponikvar, Monica Fontana, Peter Heering, Mehmet S. Sever, Simon Sawhney, Valerie Luyckx, 2025, pregledni znanstveni članek Povzetek: In the current paper, we will focus on requirements to ensure big data can advance the outcomes of our patients suffering from kidney disease. The associated ethical question is whether and how we as a nephrology community can and should encourage the collection of big data of our patients. We identify some ethical reflections on the use of big data, and their importance and relevance. Furthermore, we balance advantages and pitfalls and discuss requirements to make legitimate and ethical use of big data possible. The collection, organization, and curation of data come upfront in the pipeline before any analyses. Great care must therefore be taken to ensure quality of the data at this stage, to avoid the ‘garbage in garbage out’ problem and suboptimal patient care as a consequence of such analyses. Access to the data should be organized so that correct and efficient use of data is possible. This means that data must be stored safely, so that only those entitled to do so can access them. At the same time, those who are entitled to access the data should be able to do so in an efficient way, so as not to hinder relevant research. Analysis of observational data is itself prone to many errors and biases. Each of these biases can finally result in provision of low-quality medical care. Secure platforms should therefore also ensure correct methodology is used to interpret the available data. This requires close collaboration of a skilled workforce of experts in medical research and data scientists. Only then will our patients be able to benefit fully from the potential of AI and big data.
Ključne besede: artificial intelligence, big data, machine learning, observational trial
Objavljeno v DiRROS: 22.04.2026; Ogledov: 108; Prenosov: 88
Celotno besedilo (705,70 KB)
Gradivo ima več datotek! Več... |
7. Online screening tool for precipitation stable isotopes records : hybrid distance / density based outlier filtering approach via interactive web applicationIstván Gábor Hatvani, Dániel Erdélyi, Polona Vreča, Sonja Lojen, Klara Žagar, Jan Gačnik, Zoltán Kern, 2026, izvirni znanstveni članek Povzetek: The ratio between the heavy and light stable isotopes in precipitation is an effective tool for addressing questions in e.g., hydrology, climatology, biogeochemistry etc., but only if spatiotemporally sufficient data is available from precipitation monitoring networks. However, when data from multiple sources are gathered into large databases these can contain errors severely impacting research outcomes. The most common practices for stable isotopic database filtering apply static thresholds, not accounting for the spatially dynamically changing nature of the variable. We propose a distance-based outlier detection approach in the form of an online tool. The IsoQC App is developed to identify likely-outliers or inconsistent data points by deriving adjustable elevation-corrected average isotope values for nearby stations within an adjustable search radius (0 < R ≤ 500 km). The IsoQC is showcased on the records of the precipitation stable isotope network of Slovenia and its vicinity. It enables an objective and reproducible analysis of spatial and temporal patterns of nearby precipitation stable isotopic records by employing thresholds for dissimilarity between regional averages and individual station records in a dynamic graphical user interface. The interactive nature of the application allows users to explore spatial and temporal variations in precipitation isotope compositions, identify anomalous data points, and empirically assess regional isotope patterns in real time. The developed IsoQC tool is freely available at https://sapps.geochem.hu/isoqc/
Ključne besede: isotope composition, datasets, spatiotemporal data, web application
Objavljeno v DiRROS: 21.04.2026; Ogledov: 201; Prenosov: 115
Celotno besedilo (12,94 MB)
Gradivo ima več datotek! Več... |
8. Machine learning-assisted diagnosis classification of primary immune dysregulation using IDDA2.1 phenotype profilingMalte Schwitzkowski, Sai Pavan Kumar Veeranki, Benedikt N. Seidel, Gerhard Kindle, Stephan Rusch, Diether Kramer, Markus G. Seidel, 2026, izvirni znanstveni članek Povzetek: Background Immune dysregulation, including autoimmunity, autoinflammation, allergy, and malignancy predisposition, adds significant disease burden in primary immune disorders (PID) and inborn errors of immunity (IEIs). Objective We evaluated whether the 5-graded immune deficiency and dysregulation activity (IDDA2.1) score, encompassing 21 organ involvement and disease burden parameters, supports diagnosis across a wide spectrum of IEIs. Methods From April 2022 to November 2024, collaborators from 84 centers collected 1,043 IDDA score datasets from 825 patients across 89 IEIs (17 disorders with ≥10 patients each; range, 1-196 per IEI), including 177 scores from 141 treated patients. Supervised machine learning models ( k -nearest neighbors, support vector machine, logistic regression, random forest) classified patients into disease groups and ranked corresponding predictive features, while unsupervised uniform manifold approximation and projection (UMAP) visualized disease-specific clustering. Results Feature analysis reflected clinicians’ recognition of IEI patterns and confirmed internal IDDA score consistency. Phenotype profiles in treated patients remained informative, inversely reflecting anticipated treatment-dependent phenotype amelioration. UMAP effectively distinguished IEIs by IDDA2.1 profiles. Genetic disorder prediction achieved 73% overall accuracy, 70% for the correct monogenic IEI, and 93% within the top 3 predictions; classification reached 43% for IEI–International Union of Immunological Society categories and 59% for 12 “cardinal” IEIs (25 genes). Conclusions Random forest feature importance analysis can inform targeted clinical screening for key disease manifestations. The top 3 prediction approach demonstrates diagnostic potential, but improved accuracy will require larger, globally shared datasets. Small sample sizes for rare diseases highlight the necessity of broader collaboration to enhance AI-assisted clinical decision-making in the future.
Ključne besede: inborn error of immunity, IEI, primary immune regulatory disorder, PIRD, phenotype-driven disease classification, interoperable patient data, immune deficiency and dysregulation activity (IDDA) score, artificial intelligence, AI, unsupervised and supervised machine learning, ML, primary immune disorder, PID
Objavljeno v DiRROS: 08.04.2026; Ogledov: 179; Prenosov: 135
Celotno besedilo (2,83 MB)
Gradivo ima več datotek! Več... |
9. Erratum : Better growth outcomes in GH-deficient children treated younger than 2 years of ageTilman R. Rohrer, Primož Kotnik, Bradley S Miller, Nicky Kelepouris, Anne Helene Olsen, Alberto Pietropoli, Michel Polak, Jo Blair, 2025, drugi znanstveni članki Ključne besede: growth factors, development/foetal nutrition, pituitary, paediatric endocrinology, growth hormone therapy, growth hormone deficiency, multiple pituitary hormone deficiency, clinical outcomes, real-world data, corrigendum
Objavljeno v DiRROS: 31.03.2026; Ogledov: 239; Prenosov: 133
Celotno besedilo (220,33 KB)
Gradivo ima več datotek! Več... |
10. Better growth outcomes in GH-deficient children treated younger than 2 years of ageTilman R. Rohrer, Primož Kotnik, Bradley S Miller, Nicky Kelepouris, Anne Helene Olsen, Alberto Pietropoli, Michel Polak, Jo Blair, 2025, izvirni znanstveni članek Povzetek: Background: Limited data are available on the growth response to growth hormone (GH) treatment in very young children with GH deficiency (GHD). In the present analysis, we compared clinical outcomes after GH treatment in children with GHD aged <2 and ≥2 years at the start of GH treatment. Methods: We analysed pooled data from two observational studies of paediatric patients who received Norditropin® treatment: NordiNet® IOS (NCT00960128) and the ANSWER Program (NCT01009905). Patients with GHD, who remained pre-pubertal after 1 year of treatment, were grouped by age at treatment start (<2 years; ≥2 years). The primary effectiveness outcome was change in height standard deviation score (SDS) after 1 and 10 years. We also investigated the frequency of non-serious adverse drug reactions (ADRs), serious ADRs and serious adverse events (SAEs). Results: In total, 507 and 7,486 children initiated treatment at <2 and ≥2 years of age, respectively. Height SDS (mean change (SD) from baseline) improved after 1 year of treatment in both groups and was greater in children initiating treatment at <2 years than in those initiating treatment at ≥2 years (1.4 (1.2) and 0.75 (0.5), respectively); these findings were sustained after 10 years of treatment (3.2 (1.7) and 2.2 (1.3), respectively). SAEs were more frequent in children initiating treatment at <2 years vs ≥ 2 years (3.3 vs 0.67%, respectively). Conclusions: Children aged <2 years at GH treatment initiation had better height outcomes, but more SAEs, after 1 and 10 years of GH treatment compared to children starting GH at age ≥2 years.
Ključne besede: growth factors, development/foetal nutrition, pituitary, paediatric endocrinology, growth hormone therapy, growth hormone deficiency, multiple pituitary hormone deficiency, clinical outcomes, real-world data
Objavljeno v DiRROS: 31.03.2026; Ogledov: 221; Prenosov: 141
Celotno besedilo (782,51 KB)
Gradivo ima več datotek! Več... |
