large language model
Dotaz
Zobrazit nápovědu
Příchod velkých jazykových modelů (LLMs) založených na neuronových sítích představuje zásadní změnu v akademickém psaní, zejména v lékařských vědách. Tyto modely, např. GPT-4 od OpenAI, Google’s Bard či Claude od Anthropic, umožňují efektivnější zpracování textu díky architektuře transformátorů a mechanismu pozornosti. LLMs jsou schopny generovat koherentní texty, které se těžko rozeznávají od lidských. V medicíně mohou přispět k automatizaci rešerší, extrakci dat a formulaci hypotéz. Současně však vyvstávají etické otázky týkající se kvality a integrity vědeckých publikací a rizika generování zavádějícího obsahu. Článek poskytuje přehled o tom, jak LLMs mění psaní odborných textů, etická dilemata a možnosti detekce generovaného textu. Závěrem se zaměřuje na potenciální budoucnost LLMs v akademickém publikování a jejich dopad na lékařskou komunitu.
The advent of large language models (LLMs) based on neural networks marks a significant shift in academic writing, particularly in medical sciences. These models, including OpenAI's GPT-4, Google's Bard, and Anthropic’s Claude, enable more efficient text processing through transformer architecture and attention mechanisms. LLMs can generate coherent texts that are indistinguishable from human-written content. In medicine, they can contribute to the automation of literature reviews, data extraction, and hypothesis formulation. However, ethical concerns arise regarding the quality and integrity of scientific publications and the risk of generating misleading content. This article provides an overview of how LLMs are changing medical writing, the ethical dilemmas they bring, and the possibilities for detecting AI-generated text. It concludes with a focus on the potential future of LLMs in academic publishing and their impact on the medical community.
- MeSH
- jazyk (prostředek komunikace) MeSH
- lidé MeSH
- neuronové sítě MeSH
- publikování * etika MeSH
- zpracování přirozeného jazyka * MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- přehledy MeSH
Linguistic theory since the Cognitive Revolution has followed one of the premises of that revolution by largely sidelining the issue of emotions and concentrating on those aspects of language that are more strictly cognitive. However, during the last two decades research in cognitive science, especially in neuropsychology, has begun to fill in the gaps left by the exclusion of emotions from cognitive research. This article proposes a model for applying the fruits of this new research in emotion to our understanding of language itself. Building on Karl Pribram's integrated model of emotions and motivations, the presentation it offers a propositional explanation for how the emotions may have contributed to the emergence of symbolic formation and, ultimately, to every aspect of language from lexis to literature.
Artificial Intelligence (AI) has evolved significantly over the past decades, from its early concepts in the 1950s to the present era of deep learning and natural language processing. Advanced large language models (LLMs), such as Chatbot Generative Pre-Trained Transformer (ChatGPT) is trained to generate human-like text responses. This technology has the potential to revolutionize various aspects of gastroenterology, including diagnosis, treatment, education, and decision-making support. The benefits of using LLMs in gastroenterology could include accelerating diagnosis and treatment, providing personalized care, enhancing education and training, assisting in decision-making, and improving communication with patients. However, drawbacks and challenges such as limited AI capability, training on possibly biased data, data errors, security and privacy concerns, and implementation costs must be addressed to ensure the responsible and effective use of this technology. The future of LLMs in gastroenterology relies on the ability to process and analyse large amounts of data, identify patterns, and summarize information and thus assist physicians in creating personalized treatment plans. As AI advances, LLMs will become more accurate and efficient, allowing for faster diagnosis and treatment of gastroenterological conditions. Ensuring effective collaboration between AI developers, healthcare professionals, and regulatory bodies is essential for the responsible and effective use of this technology. By finding the right balance between AI and human expertise and addressing the limitations and risks associated with its use, LLMs can play an increasingly significant role in gastroenterology, contributing to better patient care and supporting doctors in their work.
- MeSH
- deep learning MeSH
- gastroenterologie * MeSH
- lidé MeSH
- umělá inteligence * MeSH
- zpracování přirozeného jazyka * MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
- přehledy MeSH
Over the past decade, neuropsychiatric fluctuations in Parkinson's disease (PD) have been increasingly recognized for their impact on patients' quality of life. Speech, a complex function carrying motor, emotional, and cognitive information, offers potential insights into these fluctuations. While previous studies have focused on acoustic analysis to assess motor speech disorders reliably, the potential of linguistic patterns associated with neuropsychiatric fluctuations in PD remains unexplored. This study analyzed the content of spontaneous speech from 33 PD patients in ON and OFF medication states, using machine learning and large language models (LLMs) to predict medication states and a neuropsychiatric state score. The top-performing model, the LLM Gemma-2 (9B), achieved 98% accuracy in differentiating ON and OFF states and its predicted scores were highly correlated with actual scores (Spearman's ρ = 0.81). These methods could provide a more comprehensive assessment of PD treatment effects, allowing remote neuropsychiatric symptom monitoring via mobile devices.
- Publikační typ
- časopisecké články MeSH
BACKGROUND AND PURPOSE: Pediatric radiotherapy patients and their parents are usually aware of their need for radiotherapy early on, but they meet with a radiation oncologist later in their treatment. Consequently, they search for information online, often encountering unreliable sources. Large language models (LLMs) have the potential to serve as an educational pretreatment tool, providing reliable answers to their questions. We aimed to evaluate the responses provided by generative pre-trained transformers (GPT), the most popular subgroup of LLMs, to questions about pediatric radiation oncology. MATERIALS AND METHODS: We collected pretreatment questions regarding radiotherapy from patients and parents. Responses were generated using GPT-3.5, GPT-4, and fine-tuned GPT-3.5, with fine-tuning based on pediatric radiotherapy guides from various institutions. Additionally, a radiation oncologist prepared answers to these questions. Finally, a multi-institutional group of nine pediatric radiotherapy experts conducted a blind review of responses, assessing reliability, concision, and comprehensibility. RESULTS: The radiation oncologist and GPT-4 provided the highest-quality responses, though GPT-4's answers were often excessively verbose. While fine-tuned GPT-3.5 generally outperformed basic GPT-3.5, it often provided overly simplistic answers. Inadequate responses were rare, occurring in 4% of GPT-generated responses across all models, primarily due to GPT-3.5 generating excessively long responses. CONCLUSIONS: LLMs can be valuable tools for educating patients and their families before treatment in pediatric radiation oncology. Among them, only GPT-4 provides information of a quality comparable to that of a radiation oncologist, although it still occasionally generates poor-quality responses. GPT-3.5 models should be used cautiously, as they are more likely to produce inadequate answers to patient questions.
- Publikační typ
- časopisecké články MeSH
- MeSH
- kognice MeSH
- komunikace MeSH
- lékařská etika MeSH
- lidé MeSH
- teoretické modely MeSH
- umělá inteligence MeSH
- využití lékařské informatiky * MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- úvodníky MeSH
The current interest in systems biology is to gain a better understanding of how the complex dynamic behaviour of the cell emerges from mutual interactions of molecular species. When solving such a nontrivial goal, biological data have to be necessarily integrated with mathematical modelling and computer analysis. Since the key aspect of biological modelling is based on unifying several kinds of data captured in terms of large-scale biological networks, scalable and automatized methods are necessary to obtain novel predictions and understanding. In this review, we provide a brief description of the tool DiVinE adapted for automatized analysis of biological systems dynamics. The tool employs high-performance computing techniques to enable analysis of large models.
The Ten-Item Internet Gaming Disorder Test (IGDT-10) is a short screening instrument developed to assess Internet gaming disorder (IGD) as proposed in the Diagnostic and Statistical Manual of MentalDisorders, fifth edition (DSM-5), adopting a concise, clear, and consistent item-wording. According to initial studies conducted in 2014, the instrument showed promising psychometric characteristics. The present study tested the psychometric properties, including language and gender invariance, in a large international sample of online gamers. In this study, data were collected from 7,193 participants comprising Hungarian (n = 3,924), Iranian (n = 791), English-speaking (n = 754), French-speaking (n = 421), Norwegian (n = 195), Czech (n = 496), and Peruvian (n = 612) online gamers via gaming-related websites and gaming-related social-networking-site groups. A unidimensional factor structure provided a good fit to the data in all language-based samples. In addition, results indicated both language and gender invariance on the level of scalar invariance. Criterion and construct validity of the IGDT-10 was supported by its strong association with the Problematic Online Gaming Questionnaire and moderate association with weekly gaming time, psychopathological symptoms, and impulsivity. The proportions of each sample that met the cut-off score on the IGDT-10 varied between 1.61% and 4.48% in the individual samples, except for the Peruvian sample (13.44%). The IGDT-10 shows robust psychometric properties and appears suitable for conducting cross-cultural and gender comparisons across seven languages. (PsycINFO Database Record (c) 2019 APA, all rights reserved).
- MeSH
- Diagnostický a statistický manuál mentálních poruch MeSH
- dospělí MeSH
- faktorová analýza statistická MeSH
- impulzivní chování MeSH
- internet * MeSH
- jazyk (prostředek komunikace) MeSH
- lidé středního věku MeSH
- lidé MeSH
- mladý dospělý MeSH
- návykové chování diagnóza MeSH
- průzkumy a dotazníky MeSH
- psychometrie MeSH
- reprodukovatelnost výsledků MeSH
- srovnání kultur MeSH
- videohry * MeSH
- výzkumný projekt MeSH
- Check Tag
- dospělí MeSH
- lidé středního věku MeSH
- lidé MeSH
- mladý dospělý MeSH
- mužské pohlaví MeSH
- ženské pohlaví MeSH
- Publikační typ
- časopisecké články MeSH
- validační studie MeSH
- Geografické názvy
- Austrálie MeSH
- Česká republika MeSH
- Írán MeSH
- Itálie MeSH
- Kanada MeSH
- Korejská republika MeSH
- Maďarsko MeSH
- Norsko MeSH
- Peru MeSH
- Slovenská republika MeSH
- Slovinsko MeSH
- Spojené království MeSH
- Spojené státy americké MeSH
The HEXACO Personality Inventory-Revised (HEXACO-PI-R) has become one of the most heavily applied measurement tools for the assessment of basic personality traits. Correspondingly, the inventory has been translated to many languages for use in cross-cultural research. However, formal tests examining whether the different language versions of the HEXACO-PI-R provide equivalent measures of the 6 personality dimensions are missing. We provide a large-scale test of measurement invariance of the 100-item version of the HEXACO-PI-R across 16 languages spoken in European and Asian countries (N = 30,484). Multigroup exploratory structural equation modeling and confirmatory factor analyses revealed consistent support for configural and metric invariance, thus implying that the factor structure of the HEXACO dimensions as well as the meaning of the latent HEXACO factors is comparable across languages. However, analyses did not show overall support for scalar invariance; that is, equivalence of facet intercepts. A complementary alignment analysis supported this pattern, but also revealed substantial heterogeneity in the level of (non)invariance across facets and factors. Overall, results imply that the HEXACO-PI-R provides largely comparable measurement of the HEXACO dimensions, although the lack of scalar invariance highlights the necessity for future research clarifying the interpretation of mean-level trait differences across countries.
- MeSH
- dospělí MeSH
- lidé MeSH
- osobnostní dotazník normy MeSH
- psychometrie normy MeSH
- srovnání kultur MeSH
- Check Tag
- dospělí MeSH
- lidé MeSH
- mužské pohlaví MeSH
- ženské pohlaví MeSH
- Publikační typ
- časopisecké články MeSH
Tento přehledový článek se zaměřuje na základní principy technologií umělé inteligence (AI), možnosti jejich využití v medicíně a na příklady aplikací, které již byly začleněny do klinické praxe. Diskutuje také klíčové výzvy včetně etických otázek, jako je ochrana soukromí pacientů, algoritmická bias a problém transparentnosti modelů AI. Článek zdůrazňuje nutnost integrace AI do medicíny způsobem, který zajistí bezpečnost a důvěryhodnost, a současně vyzdvihuje význam vzdělávání zdravotnických profesionálů v oblasti AI. Umělá inteligence nabízí potenciál ke zlepšení přesnosti diagnostiky, efektivity péče a podpory při klinickém rozhodování, přičemž optimálních výsledků lze dosáhnout spoluprací mezi lékaři a systémy AI.
This review article focuses on the fundamental principles of artificial intelligence (AI) technologies, their utilisation in medicine, and examples of applications that have already been incorporated into clinical practice. It also discusses key challenges, including ethical issues such as patient data privacy, algorithmic bias, and the transparency problem of AI models. The article emphasizes the necessity of integrating AI into medicine in a manner that ensures safety and trustworthiness, while underscoring the importance of educating healthcare professionals about AI. Artificial intelligence offers the potential to enhance diagnostic accuracy, the efficiency of care, and support for clinical decision-making, with optimal outcomes being achieved through collaboration between physicians and AI systems.
- MeSH
- algoritmy MeSH
- lékařství * MeSH
- lidé MeSH
- nefrologie MeSH
- umělá inteligence * etika MeSH
- velké jazykové modely MeSH
- zabezpečení počítačových systémů MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- přehledy MeSH