Hasil untuk "Medical legislation"

Phi Van Nguyen, Ngoc Huynh Trinh, Duy Minh Lam Nguyen et al.

Quantifying aleatoric uncertainty in medical image segmentation is critical since it is a reflection of the natural variability observed among expert annotators. A conventional approach is to model the segmentation distribution using the generative model, but current methods limit the expression ability of generative models. While current diffusion-based approaches have demonstrated impressive performance in approximating the data distribution, their inherent stochastic sampling process and inability to model exact densities limit their effectiveness in accurately capturing uncertainty. In contrast, our proposed method leverages conditional flow matching, a simulation-free flow-based generative model that learns an exact density, to produce highly accurate segmentation results. By guiding the flow model on the input image and sampling multiple data points, our approach synthesizes segmentation samples whose pixel-wise variance reliably reflects the underlying data distribution. This sampling strategy captures uncertainties in regions with ambiguous boundaries, offering robust quantification that mirrors inter-annotator differences. Experimental results demonstrate that our method not only achieves competitive segmentation accuracy but also generates uncertainty maps that provide deeper insights into the reliability of the segmentation outcomes. The code for this paper is freely available at https://github.com/huynhspm/Data-Uncertainty

Arkadiusz Bryłkowski, Jakub Klikowski

Large language models (LLMs) are among the best methods for processing natural language, partly due to their versatility. At the same time, domain-specific LLMs are more practical in real-life applications. This work introduces a novel natural language dataset created by acquired data from official legislative authorities' websites. The study focuses on formulating three natural language processing (NLP) tasks to evaluate the effectiveness of LLMs on legislative content analysis within the context of the Polish legal system. Key findings highlight the potential of LLMs in automating and enhancing legislative content analysis while emphasizing specific challenges, such as understanding legal context. The research contributes to the advancement of NLP in the legal field, particularly in the Polish language. It has been demonstrated that even commonly accessible data can be practically utilized for legislative content analysis.

Juan Reutter, Sergio Toro, Lucas Valenzuela et al.

This paper combines two significant areas of political science research: measuring individual ideological position and cohesion. Although both approaches help analyze legislative behaviors, no unified model currently integrates these dimensions. To fill this gap, the paper proposes a methodology called B-Call that combines ideological positioning with voting cohesion, treating votes as random variables. The model is empirically validated using roll-call data from the United States, Brazil, and Chile legislatures, which represent diverse legislative dynamics. The analysis aims to capture the complexities of voting and legislative behaviors, resulting in a two-dimensional indicator. This study addresses gaps in current legislative voting models, particularly in contexts with limited party control.

Pooya Mohammadi Kazaj, Giovanni Baj, Yazdan Salimi et al.

While numerous architectures for medical image segmentation have been proposed, achieving competitive performance with state-of-the-art models networks such as nnUNet, still leave room for further innovation. In this work, we introduce nnUZoo, an open source benchmarking framework built upon nnUNet, which incorporates various deep learning architectures, including CNNs, Transformers, and Mamba-based models. Using this framework, we provide a fair comparison to demystify performance claims across different medical image segmentation tasks. Additionally, in an effort to enrich the benchmarking, we explored five new architectures based on Mamba and Transformers, collectively named X2Net, and integrated them into nnUZoo for further evaluation. The proposed models combine the features of conventional U2Net, nnUNet, CNN, Transformer, and Mamba layers and architectures, called X2Net (UNETR2Net (UNETR), SwT2Net (SwinTransformer), SS2D2Net (SwinUMamba), Alt1DM2Net (LightUMamba), and MambaND2Net (MambaND)). We extensively evaluate the performance of different models on six diverse medical image segmentation datasets, including microscopy, ultrasound, CT, MRI, and PET, covering various body parts, organs, and labels. We compare their performance, in terms of dice score and computational efficiency, against their baseline models, U2Net, and nnUNet. CNN models like nnUNet and U2Net demonstrated both speed and accuracy, making them effective choices for medical image segmentation tasks. Transformer-based models, while promising for certain imaging modalities, exhibited high computational costs. Proposed Mamba-based X2Net architecture (SS2D2Net) achieved competitive accuracy with no significantly difference from nnUNet and U2Net, while using fewer parameters. However, they required significantly longer training time, highlighting a trade-off between model efficiency and computational cost.

Lucie-Aimée Kaffee, Pepa Atanasova, Anna Rogers

The rapid adoption of AI across diverse domains has led to the development of organisational guidelines that vary significantly, even within the same sector. This paper examines AI policies in two domains, news organisations and universities, to understand how bottom-up governance approaches shape AI usage and oversight. By analysing these policies, we identify key areas of convergence and divergence in how organisations address risks such as bias, privacy, misinformation, and accountability. We then explore the implications of these findings for international AI legislation, particularly the EU AI Act, highlighting gaps where practical policy insights could inform regulatory refinements. Our analysis reveals that organisational policies often address issues such as AI literacy, disclosure practices, and environmental impact, areas that are underdeveloped in existing international frameworks. We argue that lessons from domain-specific AI policies can contribute to more adaptive and effective AI governance at the global level. This study provides actionable recommendations for policymakers seeking to bridge the gap between local AI practices and international regulations.

Zhang Linlin, Zhang Shimeng

Under the background of medical disputes growing in number, scale and intensity, tracing back legal changes in medical field as a breakthrough point, this paper took a legal perspective to illustrate changes in medical dispute settlements from legislative orientation to legal system improvement. In view of the fact that early legislation in medical field was biased towards identification and punishment of doctors’ responsibility, and later intensive legislation in balancing increasing ''medical trouble'' phenomenon with limited effects and difficulties to abide by the law, this paper proposed to improve doctor-patient dispute settlements system in China referencing from foreign law experience, to reduce investigation of doctors at the judicial level, and to establish a settlement mechanism on doctors' apology at the legislative level, so as to promote a healthy development of doctor-patient relationship.

Olga V. Romanovskaya, Georgy B. Romanovskiy

The article addresses the issues in healthcare delivery and organization of public healthcare in the face of rapid advancements in digital technologies. The purpose of the study is to outline the legal challenges arising during the implementation of concepts such as digital health, e-health, mobile health as well as establishing the legal framework for electronic medical records and telemedicine, and certain types of innovative biomedical activities. The article illustrates the consistent impact of information and communication technologies on the interaction between patients and healthcare providers. It defines the legal framework for telemedicine and its transition to e-health. The study systematizes the particularities of legal regulations concerning both general electronic medical record and those developed by specialized medical organizations. It presents legal challenges related to data compatibility and potential cross-border exchanges. The concept of mobile healthcare is analyzed, with attention given to the risks associated with its development, notably threats to privacy and cybersecurity. The main directions of digital medicine and the challenges faced by modern legal regulations are summarized, including the use of big data, the integration of artificial intelligence, translational bioinformatics, gamification of various stages of medical care, etc. Additionally, the legal challenges arising from the use of big data and introduction of certain digital devices into medical practice are outlined, with special attention given to the brain-computer interface. Comprehensive recommendations for the improvement of healthcare legislation are presented.

Ashish Chouhan, Michael Gertz

With the increase in legislative documents at the EU, the number of new terms and their definitions is increasing as well. As per the Joint Practical Guide of the European Parliament, the Council and the Commission, terms used in legal documents shall be consistent, and identical concepts shall be expressed without departing from their meaning in ordinary, legal, or technical language. Thus, while drafting a new legislative document, having a framework that provides insights about existing definitions and helps define new terms based on a document's context will support such harmonized legal definitions across different regulations and thus avoid ambiguities. In this paper, we present LexDrafter, a framework that assists in drafting Definitions articles for legislative documents using retrieval augmented generation (RAG) and existing term definitions present in different legislative documents. For this, definition elements are built by extracting definitions from existing documents. Using definition elements and RAG, a Definitions article can be suggested on demand for a legislative document that is being drafted. We demonstrate and evaluate the functionality of LexDrafter using a collection of EU documents from the energy domain. The code for LexDrafter framework is available at https://github.com/achouhan93/LexDrafter.

Neil Zhao

The mixing problem is classically encountered in the study of differential equations applied to fluid dynamics. An understanding of fluid movement under constraints is particularly important in the field of medicine as many therapeutics and biologic molecules are dissolved in bodily fluids. Many areas of biomedical research and diagnostics also rely on fluid sampling to obtain accurate measurements of biologic markers. We present in this manuscript the general solution to the mixing problem in the context of studying physiological phenomena based on the movement of fluid acting as a carrier for medically relevant molecules/solutes. We also expanded the general solution to become more compatible with areas of biomedical research and diagnostics that seek to characterize bodily fluids located in areas that are difficult to sample.

Sohrab Namazi Nia, Frank Y. Shih

In medical imaging, accurate diagnosis heavily relies on effective image enhancement techniques, particularly for X-ray images. Existing methods often suffer from various challenges such as sacrificing global image characteristics over local image characteristics or vice versa. In this paper, we present a novel approach, called G-CLAHE (Global-Contrast Limited Adaptive Histogram Equalization), which perfectly suits medical imaging with a focus on X-rays. This method adapts from Global Histogram Equalization (GHE) and Contrast Limited Adaptive Histogram Equalization (CLAHE) to take both advantages and avoid weakness to preserve local and global characteristics. Experimental results show that it can significantly improve current state-of-the-art algorithms to effectively address their limitations and enhance the contrast and quality of X-ray images for diagnostic accuracy.

Joseph Gesnouin, Yannis Tannier, Christophe Gomes Da Silva et al.

This report introduces LLaMandement, a state-of-the-art Large Language Model, fine-tuned by the French government and designed to enhance the efficiency and efficacy of processing parliamentary sessions (including the production of bench memoranda and documents required for interministerial meetings) by generating neutral summaries of legislative proposals. Addressing the administrative challenges of manually processing a growing volume of legislative amendments, LLaMandement stands as a significant legal technological milestone, providing a solution that exceeds the scalability of traditional human efforts while matching the robustness of a specialized legal drafter. We release all our fine-tuned models and training data to the community.

A. I. Dobrieva, P. I. Ananchenkova

Introduction. All over the world, the number of people forced to flee their homes due to conflict, violence, and persecution is now higher than at any time in human history. Migrants, refugees, and other citizens belonging to the category of internally displaced persons have the right to health and medical care in the host country based upon the basic principles of humanitarian law and a number of international legal documents. However, the practice of providing medical care in the host country varies depending on the legislation and resources of the national healthcare system.The purpose of this study was to consider the barriers to the accessibility of medical care for migrants, refugees, and other internally displaced persons.Materials and methods. The research was mainly carried out using a content analysis of scientific literature published by foreign researchers on the accessibility of medical care to internally displaced persons, refugees, persons seeking citizenship, and other categories of migrants.Results. The study showed that it was challenging to collect complete data on the number of people deprived of the right to medical care during the registration procedure in the host country. The health status of asylum seekers depends on environmental and social factors; in addition, they face unique problems related to the healthcare system of the host country. In general, the global situation concerning access to medical care should be considered catastrophic. Despite legislative and programmatic achievements both within the framework of international humanitarian law and within countries, the provision of health services to migrants, refugees, and stateless persons remains a challenging issue. Thus, a huge number of people cannot exercise their rights to health and medical care.

Thomas Hügle, Vincent Grek

Digital transformation has a significant impact on efficiency and quality in hospitals. New solutions can support the management of data overload and the shortage of qualified staff. However, the timely and effective integration of these new digital tools in the healthcare setting poses challenges and requires guidance. The balanced scorecard (BSC) is a managerial method used to translate new strategies into action and measure their impact in an institution, going beyond financial values. This framework enables quicker operational adjustments and enhances awareness of real-time performance from multiple perspectives, including customers, internal procedures, and the learning organization. The aim of this study was to adapt the BSC to the evolving digital healthcare environment, encompassing factors like the recent pandemic, new technologies such as artificial intelligence, legislation, and user preferences. A strategic mapping with identification of corresponding key performance indicators was performed. To achieve this, we employed a qualitative research approach involving retreats, interdisciplinary working groups, and semi-structured interviews with different stakeholders (administrative, clinical, computer scientists) in a rheumatology department. These inputs served as the basis for customizing the BSC according to upcoming or already implemented solutions and to define actionable, cross-level performance indicators for all perspectives. Our defined values include quality of care, patient empowerment, employee satisfaction, sustainability and innovation. We also identified substantial changes in our internal processes, with the electronic medical record (EMR) emerging as a central element for vertical and horizontal digitalization. This includes integrating patient-reported outcomes, disease-specific digital biomarker, prediction algorithms to increase the quality of care as well as advanced language models in order save resources. Gaps in communication and collaboration between medical departments have been identified as a main target for new digital solutions, especially in patients with more than one disorder. From a learning institution's perspective, digital literacy among patients and healthcare professionals emerges as a crucial lever for successful implementation of internal processes. In conclusion, the BSC is a helpful tool for guiding digitalization in hospitals as a horizontally and vertically connected process that affects all stakeholders. Future studies should include empirical analyses and explore correlations between variables and above all input and user experience from patients.

Anatolii A. Khoroshev

The article examines the problem of mortality among Soviet prisoners of war in Finland in the period between 1939 and 1944. Memoirs of former prisoners of war and documents from the State Archives of the Russian Federation were used as the main sources. The fonds dedicated to the repatriation of Soviet citizens (F-9526) contains information about war crimes against Soviet soldiers in Finnish captivity. The first part of the article examines the issue of the number of Soviet prisoners of war in the territory of Finland from 1941 to 1944. An analysis of historiography and a complex of historical sources revealed that during the initial period of the conflict some of the prisoners of war were not recorded. The status of Soviet prisoners of war in Finnish camps depended on compliance with Finnish legislation, since none of the international agreements, such as the Fourth Hague Convention and the Geneva Convention of 1929, were ratified by the Soviet Union in full. This resulted in a harsh system of punishments against Soviet prisoners of war and also to difficulties in providing them with the necessary medical care, food, etc. In the period between 1941 and 1944, the number of Soviet prisoners of war in the Finnish territory was significantly higher than during the Winter War, for which the Finnish side was not ready. During the first months of the Continuation War, the camp and administrative organization of prisoners of war had to be expanded at an accelerated pace, and the resulting confusion indicates a lack of preparation and indifference to the problem of prisoners of war, since it was not a priority of the offensive war. The final part of the article highlights a set of factors that influenced the high mortality rate of Soviet prisoners of war in Finnish camps in the initial period of the Soviet-Finnish war of 1941–44. Among them were malnutrition, unacceptable living conditions, backbreaking toil, harsh climate, lack of attention to the health of prisoners of war, and the policy of the leadership of a particular camp.

Mosabbir Bhuiyan, MD Abdullah Al Nasim, Sarwar Saif et al.

Medical imaging plays an important role in the medical sector in identifying diseases. X-ray, computed tomography (CT) scans, and magnetic resonance imaging (MRI) are a few examples of medical imaging. Most of the time, these imaging techniques are utilized to examine and diagnose diseases. Medical professionals identify the problem after analyzing the images. However, manual identification can be challenging because the human eye is not always able to recognize complex patterns in an image. Because of this, it is difficult for any professional to recognize a disease with rapidity and accuracy. In recent years, medical professionals have started adopting Computer-Aided Diagnosis (CAD) systems to evaluate medical images. This system can analyze the image and detect the disease very precisely and quickly. However, this system has certain drawbacks in that it needs to be processed before analysis. Medical research is already entered a new era of research which is called Artificial Intelligence (AI). AI can automatically find complex patterns from an image and identify diseases. Methods for medical imaging that uses AI techniques will be covered in this chapter.

Lucas A. Polson, Roberto Fedrigo, Chenguang Li et al.

There is a need for open-source libraries in emission tomography that (i) use modern and popular backend code to encourage community contributions and (ii) offer support for the multitude of reconstruction techniques available in recent literature, such as those that employ artificial intelligence. The purpose of this research was to create and evaluate a GPU-accelerated, open-source, and user-friendly image reconstruction library, designed to serve as a central platform for the development, validation, and deployment of various tomographic reconstruction algorithms. PyTomography was developed using Python and inherits the GPU-accelerated functionality of PyTorch and parallelproj for fast computations. Its flexible and modular design decouples system matrices, likelihoods, and reconstruction algorithms, simplifying the process of integrating new imaging modalities using various python tools. Example use cases demonstrate the software capabilities in parallel hole SPECT and listmode PET imaging. Overall, we have developed and publicly share PyTomography, a highly optimized and user-friendly software for medical image reconstruction, with a class hierarchy that fosters the development of novel imaging applications.

Sourav Mondal, A. Gandhi, Rebecca Pachuau

Radio-isotopes produced via proton induced reaction holds special significance regarding nuclear medicine, astrophysical p-process, theragnostic and diagnostic processes. $^{76}$Br, $^{80m}$Br and $^{61}$Cu are positron emitter and they are useful in the functional studies via Positron Emission Tomography (PET), whereas $^{77}$Br bears the potential for the application in Single Photon Emission Computed Tomography (SPECT) which involves electron capture process. PET and SPECT have been in high application in medical physics, diagnostics, therapy and nuclear medicine. $^{99m}$Tc and $^{64}$Cu are two popular radionuclide which play important role in nuclear medicine, currently being used in bio-medical physics, bone scan, modern imaging, blood pool leveling, oncology and diagnosis of copper related diseases. This paper focus on the generation of recommended nuclear reaction cross sections for the production of some useful medical radio-isotopes using the experimental datasets obtained from EXFOR database and simulated datasets from nuclear reaction model codes TALYS-1.95 and EMPIRE-3.1.1. 95\% confidence interval has been implemented to ensure confidence and precision.

Sola Sacra Providentia, Muhammad Rustamaji, Jadmiko Anom Husodo

Abstract: The increase in COVID-19 cases and the limited availability of personal protective equipment cause residents to be prone to contracting COVID-19 and lose some of their rights as consumers of education programs. This study analyzes the legal protection of resident’s rights fulfilment during a pandemic in Indonesia.  This normative study using the statute approach is prescriptive and applied in nature. The data sources used are primary, secondary, legal and non-legal materials collected using literature study and confirmation techniques. The legal materials were analyzed using a syllogistic method of deductive mindset. The findings conclude that the resident's right fulfilment is not optimal at present. To achieve legal protection ideals, Indonesian universities as educational service providers must provide all forms of PPE and the reserves during the education period. Setting resident’s status as workers in teaching hospitals can result in the implications of providing incentives and determining working hours. Keywords: Legal Protection, Resident’s Rights, Pandemic   Abstrak: Penelitian ini bertujuan untuk menganalisis perlindungan hukum di Indonesia dalam pemenuhan hak residen selama masa pandemi. Residen harus melaksanakan tugas belajar mengajar dan peningkatan kasus positif COVID-19 tidak berbanding lurus dengan ketersediaan alat pelindung diri. Residen rawan terjangkit COVID-19 dan terlanggarnya beberapa hak sebagai konsumen dari program pendidikan. Metode penelitian yang digunakan adalah normatif, dengan pendekatan  undang-undang. Sifat penelitian bersifat preskriptif dan terapan. Sumber penelitian berupa bahan hukum primer, sekunder, dan non-hukum, dengan teknik studi kepustakaan serta melakukan konfirmasi. Teknik analisis bahan hukum dengan metode silogisme melalui pola pikir deduktif. Dapat disimpulkan bahwa kondisi kekinian berkenaan pemenuhan hak residen adalah belum optimal. Dari segi idealitas perlindungan hukum, Indonesia yang saat ini menganut masih university-based, universitas sebagai penyedia jasa pendidikan harus menyediakan segala bentuk APD dan cadangannya dalam penggunaan harian selama masa pendidikan. Penetapan status residen sebagai pekerja di RS Pendidikan, dapat berimplikasi terhadap pemberian insentif dan penetapan jam kerja. Kata Kunci: Hak Mahasiswa Peserta Program Pendidikan Dokter Spesialis, Masa Pandemi, Perlindungan Hukum

Shangbin Feng, Zhaoxuan Tan, Zilong Chen et al.

Modeling the ideological perspectives of political actors is an essential task in computational political science with applications in many downstream tasks. Existing approaches are generally limited to textual data and voting records, while they neglect the rich social context and valuable expert knowledge for holistic evaluation. In this paper, we propose a representation learning framework of political actors that jointly leverages social context and expert knowledge. Specifically, we retrieve and extract factual statements about legislators to leverage social context information. We then construct a heterogeneous information network to incorporate social context and use relational graph neural networks to learn legislator representations. Finally, we train our model with three objectives to align representation learning with expert knowledge, model ideological stance consistency, and simulate the echo chamber phenomenon. Extensive experiments demonstrate that our learned representations successfully advance the state-of-the-art in three downstream tasks. Further analysis proves the correlation between learned legislator representations and various socio-political factors, as well as bearing out the necessity of social context and expert knowledge in modeling political actors.

Josh Grace, Foaad Khosmood

In US State government legislatures, most of the activity occurs in committees made up of lawmakers discussing bills. When analyzing, classifying or summarizing these committee proceedings, some important features become broadly interesting. In this paper, we engineer four useful features, two applying to lawmakers (engagement and absence), and two to non-lawmakers (stance and affiliation). We propose a system to automatically track the affiliation of organizations in public comments and whether the organizational representative supports or opposes the bill. The model tracking affiliation achieves an F1 of 0.872 while the support determination has an F1 of 0.979. Additionally, a metric to compute legislator engagement and absenteeism is also proposed and as proof-of-concept, a list of the most and least engaged legislators over one full California legislative session is presented.