Iskanje po repozitoriju

A+ | A- | | SLO | ENG

Povzetek: European Artificial Intelligence Act (EU AI Act) was adopted by the EU Parliament in 2024 as part of the EU’s legislative process. In this article, the author proposes solutions based on AI tools and methodological approaches applied to Digitised and Born-Digital Archival Records from the point of view of computational approaches to analyze Digital collections. Computational Research methods include a wide range of approaches, including text and Data Mining, Data Visualization, Digital Data Analysis, and the use of Language Models in large numbers of Big Data. The application of Artificial Intelligence (AI) and its subsets, such as Data Mining, Machine Learning and Natural Language Processing, has expanded the scope of computational Research methods in Digital Archives, from the creator of Records to the Information Digital Specialist (Digital Archivist) and all the way to the end user. Digital collections such as eArchives have been increasingly recognised as an essential source for Multidisciplinary Research in recent decades.
Ključne besede: EU AI Act, artificial intelligence, AI, digital archives, big data, act machine learning, language models, data mining, cybersecurity, digital archives, AI systems, digital archivist
Objavljeno v DiRROS: 05.08.2026; Ogledov: 91; Prenosov: 50
Celotno besedilo (949,01 KB)
Gradivo ima več datotek! Več...

Povzetek: Background: Large language models (LLMs) are increasingly applied in medicine; however, their accuracy in guideline-driven, high-stakes specialties, such as metabolic and bariatric surgery (MBS), remains uncertain. This study evaluates the performance of ChatGPT-4o, Gemini 2.0 Flash, and DeepSeek-V3 in generating guideline-concordant responses to MBS clinical questions. Methods: Thirty standardized, guideline-based MBS questions were presented to each model. Responses were randomized in order, anonymized (blinded as Model A/B/C), and evaluated by 93 MBS experts using a validated 0–3 scale (0 = inaccurate; 3 = fully guideline-concordant). A repeated-measures ANOVA with Bonferroni correction tested model differences; reliability was assessed with Cronbach’s α and intraclass correlation coefficients (ICC). Results: DeepSeek-V3 achieved the highest mean score (2.44 ± 0.40), followed by ChatGPT-4o (1.79 ± 0.46) and Gemini 2.0 Flash (1.63 ± 0.47) (p < 0.001). Fully guideline-concordant ratings (score = 3) were most frequent for DeepSeek (80%) vs. ChatGPT (0%) and Gemini (3.3%). Internal consistency was excellent (α > 0.90), and inter-rater reliability was strong (ICC > 0.88). When mapped against the QUEST evaluation framework, the study addressed Quality and Understanding but did not fully capture Expression, Safety, or Trust dimensions. Conclusions: DeepSeek-V3 outperformed ChatGPT-4o and Gemini 2.0 Flash in generating guideline-concordant responses in MBS. These results highlight the need for ongoing, domain-focused validation before clinical use.
Ključne besede: large language models, metabolic and bariatric surgery, artificial intelligence evaluation, ChatGPT, DeepSeek-V3, Gemini
Objavljeno v DiRROS: 01.07.2026; Ogledov: 186; Prenosov: 132
Celotno besedilo (1,01 MB)
Gradivo ima več datotek! Več...

Povzetek: The exponential growth of scientific literature challenges traditional synthesis methods, limiting our ability to derive broad insights into complex environmental processes. Large language models (LLMs) may help address this challenge by supporting the extraction of structured knowledge from unstructured text. To evaluate and demonstrate this potential in soil science, we developed a multi-module, LLM-assisted knowledge-extraction workflow built on a recently published meta-data-analysis of management–biota interactions as a contextual framework, using an iteratively refined prompt chain to extract directional relationships between agricultural management practices and soil fauna from scientific abstracts. Benchmarking against manually curated datasets showed high precision and recall, while expert-guided iterative development indicated that the information content of abstracts was likely a major practical constraint on extraction performance. To assess interpretative soundness, we applied the workflow in two use cases: an illustrative comparison with the well-established literature on reduced and no-tillage effects on soil fauna, and a knowledge-gap application on biochar and crop-residue retention. The workflow indicated predominantly beneficial reported patterns for crop residue retention, particularly for earthworms and nematodes, whereas biochar showed a more heterogeneous and context-dependent pattern. Overall, results show that LLM-assisted workflows can support rapid, large-scale evidence mapping of soil fauna responses to management practices when formal quantitative syntheses are unavailable. The proposed framework is best understood as a complementary tool for organising and screening dispersed ecological evidence, and not as a substitute for full-text synthesis, effect-size-based meta-analysis, or decision-grade inference. The complete workflow is publicly available and broadly transferable across environmental research domains.
Ključne besede: text mining, knowledge extraction, artificial intelligence, soil biota, biochar, crop residues
Objavljeno v DiRROS: 23.06.2026; Ogledov: 189; Prenosov: 157
Celotno besedilo (4,24 MB)
Gradivo ima več datotek! Več...

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: 243; Prenosov: 249
Celotno besedilo (705,70 KB)
Gradivo ima več datotek! Več...

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: 376; Prenosov: 334
Celotno besedilo (2,83 MB)
Gradivo ima več datotek! Več...