Iskanje po katalogu digitalne knjižnice

Opis: This paper reviews benchmarking methods for evaluating large language models (LLMs) in healthcare settings. It highlights the importance of rigorous benchmarking to ensure LLMs' safety, accuracy, and effectiveness in clinical applications. The review also discusses the challenges of developing standardized benchmarks and metrics tailored to healthcare-specific tasks such as medical text generation, disease diagnosis, and patient management. Ethical considerations, including privacy, data security, and bias, are also addressed, underscoring the need for multidisciplinary collaboration to establish robust benchmarking frameworks that facilitate LLMs' reliable and ethical use in healthcare. Evaluation of LLMs remains challenging due to the lack of standardized healthcare-specific benchmarks and comprehensive datasets. Key concerns include patient safety, data privacy, model bias, and better explainability, all of which impact the overall trustworthiness of LLMs in clinical settings.
Ključne besede: artificial intelligence, benchmarking, chatbots, healthcare, large language models, natural language processing
Objavljeno v DKUM: 12.05.2025; Ogledov: 0; Prenosov: 0
Povezava na datoteko

Opis: Background Micronutrient deficiencies in pregnant women are linked to serious health issues, including conception difficulties, spontaneous abortions, preterm births, low birth weight, birth defects and long-term metabolic disorders. Despite the recognized importance of dietary supplementation during pregnancy, rigorous research and supplementation monitoring remain limited. Objective This study aimed to review the evidence on the impact of dietary supplementation on maternal and infant outcomes and to provide evidence-based recommendations for dietary supplementation during pregnancy. Methods A systematic search, analysis, and synthesis of randomized controlled trials (RCTs) were conducted between October and January 2022. Databases searched included PubMed, CINAHL with Full Text, Google Scholar and CrossRef. The study adhered to PRISMA guidelines and applied inclusion and exclusion criteria to identify relevant studies. A total of 51 RCTs were included and assessed for quality, categorizing articles as moderate or high quality. Results Of the 51 RCTs analyzed, 47 (92.16%) were of moderate quality, and 4 (7.84%) were of high quality. Findings revealed that recommended dietary supplementation doses for pregnant women are often set well below safety thresholds. Evidence supporting the efficacy of certain vitamins and minerals in pregnancy remains inconclusive. The study highlighted a dose–response conundrum, with an emphasis on identifying effective and safe doses. Conclusion Micronutrient deficiencies in pregnant women pose significant risks to maternal and infant health. Current dietary supplementation recommendations require enhancement and alignment with the latest and most robust evidence. This study provides a comprehensive overview of state-of-the-art evidence and underscores the importance of bridging gaps in supplementation guidelines to optimize maternal and infant health outcomes.
Ključne besede: EBN, pregnancy, vitamins, minerals, FDA, infant
Objavljeno v DKUM: 27.01.2025; Ogledov: 0; Prenosov: 11
Celotno besedilo (528,31 KB)
Gradivo ima več datotek! Več...

Opis: Uvod: Pandemija COVID-19 je prinesla nove izzive in spremenila način življenja mnogih ljudi po svetu. Države se niso zavedale, kako hitro se lahko bolezen razširi in kakšne posledice lahko prinese. Prizadela je ljudi vseh starosti, vključno z otroki in mladostniki, ki so to pandemijo doživljali na drugačen način kot njihovi starši. Metode: Uporabili smo opisno metodo pregleda literature. Literaturo smo iskali v petih podatkovnih bazah: PubMed, CINAHL, Cochrane Library in ScienceDirect. Pri poteku iskanja literature smo upoštevali smernice PRISMA. Ustrezne rezultate smo nato razporedili glede na hierarhijo dokazov in jih prikazali s pomočjo evalvacijske in sintezne tabele. Rezultati: V končno analizo smo vključili 11 člankov. V vseh člankih so opisovali negativen vpliv socialne izolacije na mentalno zdravje otrok in mladostnikov po vsem svetu. Najbolj na udaru so bili otroci in mladostniki z že pridruženimi boleznimi ali pa s šibkimi odnosi v družini. Razprava in zaključek: Pandemija COVID-19 je znatno negativno vplivala na dobrobitje otrok in mladostnikov. Slednji so bili izpostavljeni tako nevarnosti okužbe kot nevarnostmi zlorabe v nefunkcionalnih družinah. Za določitev specifičnih posledic bi bilo potrebnih več raziskav.
Ključne besede: koronavirus, psihično zdravje, socialna izolacija, odraščanje
Objavljeno v DKUM: 17.01.2025; Ogledov: 0; Prenosov: 58
Celotno besedilo (1,23 MB)

Opis: Background: Although the internet facilitates access to a wide range of knowledge and evidence, overuse among young people is associated with lower wellbeing and psychosomatic symptoms. The aim of this cross-sectional study is to explore the relationship between internet use, mental wellbeing, and psychosomatic symptoms among university students in Slovenia. Methods: We used correlation matrix plots to identify correlated symptoms and multivariate logistic regression to analyze the relationship between the time spent on the internet or computer and psychosomatic symptoms controlling for gender. Symptoms were measured using the Health Behavior of School Children scale. Results: Out of 464 students, the majority (64.7%, n = 300) were healthcare students and 35.3% (n = 164) were computer science students. Among somatic symptoms, headaches were associated with more time spent on the computer (r = −0.17, p < 0.001) and were significantly more prevalent in computer science students compared to health science students (χ2(1) = 8.52, p = 0.004). Time spent using the internet for spare time activities was associated with lower nervousness (r = 0.15, p = 0.005). Conclusions: Computer science students reported more frequent psychological symptoms compared to health science students and less somatic symptoms.
Ključne besede: psychological symptoms, somatic symptoms, technology use, wellbeing, university students
Objavljeno v DKUM: 27.11.2024; Ogledov: 0; Prenosov: 3
Celotno besedilo (2,43 MB)
Gradivo ima več datotek! Več...

Opis: The publication "Analysis of quantitative research data in nursing research: A guide to SPSS" provides nursing students and nurses with the knowledge and skills to interpret the different statistical methods in their field, which can improve users' skills in collecting, analysing and interpreting results from clinical practice, thus contributing to improving the quality of health care. It provides detailed instructions on how to use IBM SPSS and perform statistical analyses that nurses need to be familiar with as they use and generate data in their daily work with patients. The main aim of patient care is to provide high quality, evidence-based care, so nurses have a duty to keep up to date with the latest research and evidence and apply it to their work. The knowledge gained in this book can also help nurses to better understand and interpret previously published results, and thus critically assess the validity and reliability of the results they will use in clinical practice.
Ključne besede: quantitative analysis, statistics, IBM SPSS, reliability, validity, data analysis
Objavljeno v DKUM: 18.07.2024; Ogledov: 113; Prenosov: 27
Celotno besedilo (18,18 MB)
Gradivo ima več datotek! Več...