Hasil untuk "Medical legislation"

M. Fishbein

Zhongying Deng, Cheng Tang, Ziyan Huang et al.

Foundation models have demonstrated remarkable success across diverse domains and tasks, primarily due to the thrive of large-scale, diverse, and high-quality datasets. However, in the field of medical imaging, the curation and assembling of such medical datasets are highly challenging due to the reliance on clinical expertise and strict ethical and privacy constraints, resulting in a scarcity of large-scale unified medical datasets and hindering the development of powerful medical foundation models. In this work, we present the largest survey to date of medical image datasets, covering over 1,000 open-access datasets with a systematic catalog of their modalities, tasks, anatomies, annotations, limitations, and potential for integration. Our analysis exposes a landscape that is modest in scale, fragmented across narrowly scoped tasks, and unevenly distributed across organs and modalities, which in turn limits the utility of existing medical image datasets for developing versatile and robust medical foundation models. To turn fragmentation into scale, we propose a metadata-driven fusion paradigm (MDFP) that integrates public datasets with shared modalities or tasks, thereby transforming multiple small data silos into larger, more coherent resources. Building on MDFP, we release an interactive discovery portal that enables end-to-end, automated medical image dataset integration, and compile all surveyed datasets into a unified, structured table that clearly summarizes their key characteristics and provides reference links, offering the community an accessible and comprehensive repository. By charting the current terrain and offering a principled path to dataset consolidation, our survey provides a practical roadmap for scaling medical imaging corpora, supporting faster data discovery, more principled dataset creation, and more capable medical foundation models.

Heyuan Huang, Alexandra DeLucia, Vijay Murari Tiyyala et al.

While Large Language Models (LLMs) can generate fluent and convincing responses, they are not necessarily correct. This is especially apparent in the popular decompose-then-verify factuality evaluation pipeline, where LLMs evaluate generations by decomposing the generations into individual, valid claims. Factuality evaluation is especially important for medical answers, since incorrect medical information could seriously harm the patient. However, existing factuality systems are a poor match for the medical domain, as they are typically only evaluated on objective, entity-centric, formulaic texts such as biographies and historical topics. This differs from condition-dependent, conversational, hypothetical, sentence-structure diverse, and subjective medical answers, which makes decomposition into valid facts challenging. We propose MedScore, a new pipeline to decompose medical answers into condition-aware valid facts and verify against in-domain corpora. Our method extracts up to three times more valid facts than existing methods, reducing hallucination and vague references, and retaining condition-dependency in facts. The resulting factuality score substantially varies by decomposition method, verification corpus, and used backbone LLM, highlighting the importance of customizing each step for reliable factuality evaluation by using our generalizable and modularized pipeline for domain adaptation.

Xinyu Chen, Yiran Wang, Gaoyang Pang et al.

Medical Referring Image Segmentation (MRIS) involves segmenting target regions in medical images based on natural language descriptions. While achieving promising results, recent approaches usually involve complex design of multimodal fusion or multi-stage decoders. In this work, we propose NTP-MRISeg, a novel framework that reformulates MRIS as an autoregressive next-token prediction task over a unified multimodal sequence of tokenized image, text, and mask representations. This formulation streamlines model design by eliminating the need for modality-specific fusion and external segmentation models, supports a unified architecture for end-to-end training. It also enables the use of pretrained tokenizers from emerging large-scale multimodal models, enhancing generalization and adaptability. More importantly, to address challenges under this formulation-such as exposure bias, long-tail token distributions, and fine-grained lesion edges-we propose three novel strategies: (1) a Next-k Token Prediction (NkTP) scheme to reduce cumulative prediction errors, (2) Token-level Contrastive Learning (TCL) to enhance boundary sensitivity and mitigate long-tail distribution effects, and (3) a memory-based Hard Error Token (HET) optimization strategy that emphasizes difficult tokens during training. Extensive experiments on the QaTa-COV19 and MosMedData+ datasets demonstrate that NTP-MRISeg achieves new state-of-the-art performance, offering a streamlined and effective alternative to traditional MRIS pipelines.

Lemar Abdi, Francisco Caetano, Amaan Valiuddin et al.

In medical imaging, unsupervised out-of-distribution (OOD) detection offers an attractive approach for identifying pathological cases with extremely low incidence rates. In contrast to supervised methods, OOD-based approaches function without labels and are inherently robust to data imbalances. Current generative approaches often rely on likelihood estimation or reconstruction error, but these methods can be computationally expensive, unreliable, and require retraining if the inlier data changes. These limitations hinder their ability to distinguish nominal from anomalous inputs efficiently, consistently, and robustly. We propose a reconstruction-free OOD detection method that leverages the forward diffusion trajectories of a Stein score-based denoising diffusion model (SBDDM). By capturing trajectory curvature via the estimated Stein score, our approach enables accurate anomaly scoring with only five diffusion steps. A single SBDDM pre-trained on a large, semantically aligned medical dataset generalizes effectively across multiple Near-OOD and Far-OOD benchmarks, achieving state-of-the-art performance while drastically reducing computational cost during inference. Compared to existing methods, SBDDM achieves a relative improvement of up to 10.43% and 18.10% for Near-OOD and Far-OOD detection, making it a practical building block for real-time, reliable computer-aided diagnosis.

Yuwen Chen, Zafer Yildiz, Qihang Li et al.

Manual annotation of volumetric medical images, such as magnetic resonance imaging (MRI) and computed tomography (CT), is a labor-intensive and time-consuming process. Recent advancements in foundation models for video object segmentation, such as Segment Anything Model 2 (SAM 2), offer a potential opportunity to significantly speed up the annotation process by manually annotating one or a few slices and then propagating target masks across the entire volume. However, the performance of SAM 2 in this context varies. Our experiments show that relying on a single memory bank and attention module is prone to error propagation, particularly at boundary regions where the target is present in the previous slice but absent in the current one. To address this problem, we propose Short-Long Memory SAM 2 (SLM-SAM 2), a novel architecture that integrates distinct short-term and long-term memory banks with separate attention modules to improve segmentation accuracy. We evaluate SLM-SAM 2 on four public datasets covering organs, bones, and muscles across MRI, CT, and ultrasound videos. We show that the proposed method markedly outperforms the default SAM 2, achieving an average Dice Similarity Coefficient improvement of 0.14 and 0.10 in the scenarios when 5 volumes and 1 volume are available for the initial adaptation, respectively. SLM-SAM 2 also exhibits stronger resistance to over-propagation, reducing the time required to correct propagated masks by 60.575% per volume compared to SAM 2, making a notable step toward more accurate automated annotation of medical images for segmentation model development.

Stević Ivana, Vajagić Maja, Knežević Bojana et al.

Obesity is a chronic, complex, relapsing disease impacting healthcare systems and the economy worldwide. We aim to analyze the utilization trends of antiobesity drugs, and their reimbursement status on drug lists of health insurance funds (HIF) in selected European countries. The DDD/1000 inhabitants/day methodology is used for utilization trend analysis, where data from official national utilization reports were used. For the reimbursement status analysis of 5 antiobesity drugs (orlistat, semaglutide, liraglutide, naltrexone/bupropion, setmelanotide), the websites of national health insurance funds (HIF) of 22 European countries were screened. Trend analysis revealed fluctuation for almost all antiobesity drugs (the highest decrease seen for orlistat in Serbia, and the highest increase for liraglutide in Croatia). Novel antiobesity drugs show an increasing utilization trend in almost all the countries. In two out of three European countries, 437 antiobesity drugs are not covered by the HIF. Slovenia and Denmark reimburse most of the antiobesity drugs. The Netherlands is the only country where the cost of setmelanotide is paid by the HIF. Our results emphasize the importance of prioritizing the introduction and implementation of new strategies and reimbursement scheme models in global and national antiobesity policies.

Andrea Colombo

Knowledge Graphs (KGs) have been used to organize large datasets into structured, interconnected information, enhancing data analytics across various fields. In the legislative context, one potential natural application of KGs is modeling the intricate set of interconnections that link laws and their articles with each other and the broader legislative context. At the same time, the rise of large language models (LLMs) such as GPT has opened new opportunities in legal applications, such as text generation and document drafting. Despite their potential, the use of LLMs in legislative contexts is critical since it requires the absence of hallucinations and reliance on up-to-date information, as new laws are published on a daily basis. This work investigates how Legislative Knowledge Graphs and LLMs can synergize and support legislative processes. We address three key questions: the benefits of using KGs for legislative systems, how LLM can support legislative activities by ensuring an accurate output, and how we can allow non-technical users to use such technologies in their activities. To this aim, we develop Legis AI Platform, an interactive platform focused on Italian legislation that enhances the possibility of conducting legislative analysis and that aims to support lawmaking activities.

Denis Saveliev, Ruslan Kuchakov

We present the comprehensive Russian primary and secondary legislation corpus covering 1991 to 2023. The corpus collects all 281,413 texts (176,523,268 tokens) of non-secret federal regulations and acts, along with their metadata. The corpus has two versions the original text with minimal preprocessing and a version prepared for linguistic analysis with morphosyntactic markup.

Anna Reithmeir, Veronika Spieker, Vasiliki Sideri-Lampretsa et al.

Image registration is fundamental in medical imaging applications, such as disease progression analysis or radiation therapy planning. The primary objective of image registration is to precisely capture the deformation between two or more images, typically achieved by minimizing an optimization problem. Due to its inherent ill-posedness, regularization is a key component in driving the solution toward anatomically meaningful deformations. A wide range of regularization methods has been proposed for both conventional and deep learning-based registration. However, the appropriate application of regularization techniques often depends on the specific registration problem, and no one-fits-all method exists. Despite its importance, regularization is often overlooked or addressed with default approaches, assuming existing methods are sufficient. A comprehensive and structured review remains missing. This review addresses this gap by introducing a novel taxonomy that systematically categorizes the diverse range of proposed regularization methods. It highlights the emerging field of learned regularization, which leverages data-driven techniques to automatically derive deformation properties from the data. Moreover, this review examines the transfer of regularization methods from conventional to learning-based registration, identifies open challenges, and outlines future research directions. By emphasizing the critical role of regularization in image registration, we hope to inspire the research community to reconsider regularization strategies in modern registration algorithms and to explore this rapidly evolving field further.

Sergey V. Vinogradov, Yulia G. Eshchenko

The authors examine the history of the establishment of the system of sanitary inspection and medical care for workers of the Caspian-Volga fisheries. There is considered the fishing legislation of the XIX - early XX century. It is stated that, despite the approved rules, fishery workers actually had no qualified medical care, the provision of which was entrusted to the owners of the fishing business. The authors come to the conclusion that the supervision of the sanitary condition of the fisheries was not effective due to a number of reasons: unresolved personnel problems, the large territorial expanses of sanitary areas with a lack of vehicles for sanitary doctors, the difficulties of bureaucratic interaction between the Department of Fisheries and Seal Fisheries, regional authorities and owners of the fishing business, etc. The shortcomings of the sanitary and medical services for fisheries, as well as the specific geographical location and natural and climatic conditions of the Astrakhan province contributed to the wide spread of various epidemic diseases. Due to the lack of the public free healthcare system and qualified medical personnel, there emerged infectious diseases, which led to high mortality among fishery workers.

Fatmi Andriati, Aidul Fitriciada Azhari, Wardah Yuspin

Abstract: Reproductive health rights are a crucial aspect of healthcare, particularly for women, with direct impacts on a country's social and economic development. In Indonesia, reproductive health issues are a primary focus for improving the quality of life. The Indonesian government issued Minister of Health Regulation No. 35 of 2014 to regulate Reproductive Health Service Standards, but its implementation in the field remains challenging. This research aims to explore the implementation of Minister of Health Regulation No. 35 of 2014 in healthcare practices in Indonesia, identify barriers to be addressed, and examine the role of legal perspectives and normative aspects in enhancing the protection of women's reproductive health rights. This research uses a qualitative approach with normative juridical and empirical approaches. Legal analysis involves the study of legal documents, while empirical analysis includes interviews with stakeholders in the field of reproductive health. The research results show that Minister of Health Regulation No. 35 of 2014 regulates various aspects of reproductive health, but its implementation varies. Education and training for medical personnel need improvement, communication with patients must be enhanced, patient rights protection needs strengthening, and public education on women's reproductive health rights should be intensified. Legal perspectives provide a strong foundation for safeguarding reproductive health rights, while normative aspects help transform the culture of reproductive healthcare. In conclusion, the implementation of Minister of Health Regulation No. 35 of 2014 still requires improvement in various aspects. Enhancements in education, communication, patient rights protection, and public education are essential. Legal perspectives and normative aspects play a role in enhancing the protection of women's reproductive health rights and the effectiveness of reproductive healthcare services in Indonesia. This research provides recommendations for improving reproductive health services and legal understanding in the context of reproductive health in Indonesia. Abstrak : Hak kesehatan reproduksi merupakan aspek kesehatan penting, terutama bagi perempuan, dengan dampak langsung pada perkembangan sosial dan ekonomi suatu negara. Di Indonesia, masalah kesehatan reproduksi menjadi fokus utama dalam meningkatkan kualitas hidup masyarakat. Meskipun Pemerintah Indonesia telah mengeluarkan Peraturan Menteri Kesehatan RI Nomor 35 Tahun 2014 untuk mengatur Standar Pelayanan Kesehatan Reproduksi, implementasinya di lapangan masih menghadapi sejumlah hambatan yang menghambat perlindungan hak-hak kesehatan reproduksi perempuan. Penelitian ini bertujuan untuk mengeksplorasi implementasi Peraturan Menteri Kesehatan RI Nomor 35 Tahun 2014 dalam praktik pelayanan kesehatan di Indonesia, mengidentifikasi hambatan yang perlu diatasi, serta mengkaji peran perspektif hukum dan aspek normatif dalam meningkatkan perlindungan hak-hak kesehatan reproduksi perempuan. Penelitian ini menggunakan pendekatan kualitatif dengan pendekatan yuridis normatif dan empiris. Analisis hukum mencakup studi dokumen hukum, sementara analisis empiris melibatkan wawancara dengan pemangku kepentingan di bidang kesehatan reproduksi. Hasil penelitian menunjukan Peraturan Menteri Kesehatan RI Nomor 35 Tahun 2014 mengatur berbagai aspek kesehatan reproduksi, tetapi implementasinya bervariasi. Pendidikan dan pelatihan bagi tenaga medis perlu ditingkatkan, komunikasi dengan pasien harus lebih baik, perlindungan hak-hak pasien perlu ditingkatkan, dan edukasi masyarakat tentang hak-hak kesehatan reproduksi perempuan harus lebih intensif. Perspektif hukum memberikan landasan yang kuat bagi perlindungan hak-hak kesehatan reproduksi, sementara aspek normatif membantu mengubah budaya pelayanan kesehatan reproduksi. Kesimpulanya implementasi Peraturan Menteri Kesehatan RI Nomor 35 Tahun 2014 masih perlu perbaikan dalam berbagai aspek. Peningkatan pendidikan, komunikasi, perlindungan hak-hak pasien, dan edukasi masyarakat penting. Perspektif hukum dan aspek normatif berperan dalam meningkatkan perlindungan hak-hak kesehatan reproduksi perempuan dan efektivitas pelayanan kesehatan reproduksi di Indonesia. Penelitian ini memberikan rekomendasi untuk perbaikan layanan kesehatan reproduksi dan pemahaman hukum dalam konteks kesehatan reproduksi di Indonesia.

Mohammad Reza Hosseinzadeh Taher, Michael B. Gotway, Jianming Liang

Human anatomy is the foundation of medical imaging and boasts one striking characteristic: its hierarchy in nature, exhibiting two intrinsic properties: (1) locality: each anatomical structure is morphologically distinct from the others; and (2) compositionality: each anatomical structure is an integrated part of a larger whole. We envision a foundation model for medical imaging that is consciously and purposefully developed upon this foundation to gain the capability of "understanding" human anatomy and to possess the fundamental properties of medical imaging. As our first step in realizing this vision towards foundation models in medical imaging, we devise a novel self-supervised learning (SSL) strategy that exploits the hierarchical nature of human anatomy. Our extensive experiments demonstrate that the SSL pretrained model, derived from our training strategy, not only outperforms state-of-the-art (SOTA) fully/self-supervised baselines but also enhances annotation efficiency, offering potential few-shot segmentation capabilities with performance improvements ranging from 9% to 30% for segmentation tasks compared to SSL baselines. This performance is attributed to the significance of anatomy comprehension via our learning strategy, which encapsulates the intrinsic attributes of anatomical structures-locality and compositionality-within the embedding space, yet overlooked in existing SSL methods. All code and pretrained models are available at https://github.com/JLiangLab/Eden.

Anna Reithmeir, Julia A. Schnabel, Veronika A. Zimmer

Medical image registration aims at identifying the spatial deformation between images of the same anatomical region and is fundamental to image-based diagnostics and therapy. To date, the majority of the deep learning-based registration methods employ regularizers that enforce global spatial smoothness, e.g., the diffusion regularizer. However, such regularizers are not tailored to the data and might not be capable of reflecting the complex underlying deformation. In contrast, physics-inspired regularizers promote physically plausible deformations. One such regularizer is the linear elastic regularizer which models the deformation of elastic material. These regularizers are driven by parameters that define the material's physical properties. For biological tissue, a wide range of estimations of such parameters can be found in the literature and it remains an open challenge to identify suitable parameter values for successful registration. To overcome this problem and to incorporate physical properties into learning-based registration, we propose to use a hypernetwork that learns the effect of the physical parameters of a physics-inspired regularizer on the resulting spatial deformation field. In particular, we adapt the HyperMorph framework to learn the effect of the two elasticity parameters of the linear elastic regularizer. Our approach enables the efficient discovery of suitable, data-specific physical parameters at test time.

K. Kidd, G. Sequeira, T. Paglisotti et al.

OBJECTIVES Numerous U.S. state legislatures have proposed bills to ban gender-affirming medical interventions for minors. Parents and caregivers play a critical role in advocating for and supporting their transgender and gender-diverse youth (TGDY). We aimed to understand parent and caregiver perspectives about this potential legislation and perceived effects on their TGDY's mental health. METHODS We developed and launched a social-media based, anonymous online survey in February 2020 to assess parent and caregiver perspectives on proposed laws to ban gender-affirming medical interventions for minors. Participants were asked to respond to two open-ended questions about these laws; responses were coded to identify key themes. RESULTS We analyzed responses from 273 participants from 43 states. Most identified as white (86.4%) female (90.0%) mothers (93.8%), and 83.6% of their TGDY had received gender-affirming medical interventions before age 18 years. The most salient theme, which appeared in the majority of responses, described parent and caregiver fears that these laws would lead to worsening mental health and suicide for their TGDY. Additional themes included a fear that their TGDY would face increased discrimination, lose access to gender-affirming medical interventions, and lose autonomy over medical decision-making due to government overreach. CONCLUSIONS In this convenience sample, parents and caregivers overwhelmingly expressed fear that the proposed legislation will lead to worsening mental health and increased suicidal ideation for their TGDY. They implored lawmakers to hear their stories and to leave critical decisions about gender-affirming medical interventions to families and their medical providers.

Simon Erridge, Ross Coomber, Mikael H Sodergren

Abstract Background In the UK, legislation and regulations governing medical cannabis and over the counter cannabidiol (CBD) wellness products have rapidly evolved since 2018. This study aimed to assess the public awareness of the availability, regulations, and barriers to access medical cannabis and over the counter CBD wellness products. Methods A cross-sectional survey study was performed through YouGov® using quota sampling methodology between March 22nd and March 31st 2021. Responses were matched and statistically weighted to UK adult population demographics, including those without internet access, and analysed according to percentage of respondents. Statistical significance was defined by p-value < 0.050. Results Ten thousand six hundred eighty-four participants completed the survey. 5,494 (51.4%) respondents believed that medical cannabis is legal in the UK. 684 (6.4%) participants consumed CBD for wellness reasons, 286 (2.7%) were prescribed CBD for a medical reason and 222 (2.1%) consumed CBD for another reason. 10,076 (94.3%) respondents were unaware of April 2021 regulations meaning that all over the counter CBD wellness products in the UK must conform to European Novel Foods Regulations. The most frequently reported main barriers to accessing medical cannabis were its association with recreational cannabis (n = 2,686; 25.1%), being unsure if it was legal (n = 2,276; 21.3%) and being unsure what medical conditions its can be used for (n = 1,863; 17.4%). Conclusion A large proportion of respondents are unaware of the legislation and regulations surrounding medical cannabis and over the counter CBD wellness products. Lack of knowledge may present a barrier to safe access to either product.

Toni Hains

On 16 March 2010, the Senate passed historic legislation allowing nurse practitioners (NPs) and midwives limited access to the Medical Benefits Schedule (MBS) and the Pharmaceutical Benefits Schedule (PBS). The Hon Nicola Roxon MP was celebrated as the Minister for Health and Aging who showed courage and conviction for the nursing profession by facilitating this legislation. How will the current Minister for Health and Aging, the Hon Greg Hunt MP, be remembered by the nursing profession?

Susanna Sternberg-Lewerin, Sofia Boqvist, Simen Foyn Nørstebø et al.

In the Nordic countries, antimicrobial use in animals and the prevalence of antimicrobial resistance are among the lowest in Europe. The network “Nordic Vets Against AMR” organized a meeting in 2021, with key actors including representatives from universities, veterinary authorities and veterinary organizations in Finland, Norway and Sweden. This paper reflects the most important discussions on education, research, policy and future perspectives, including the experiences of these countries. It concludes that Nordic veterinarians are well placed to lead the way in the fight against antimicrobial resistance and that the sharing of experiences can support colleagues in other countries. Veterinary education must go hand in hand with research activities and continuously updated guidelines and legislation. There is also a need for postgraduate training on antimicrobial resistance and prudent antimicrobial use. The veterinary profession must, by any means necessary, protect the efficiency of antimicrobials for the sake of animal health, animal welfare and productivity, as well as public health. While restrictive use of antimicrobials is crucial, the ability of veterinarians to use this medical tool is also important for the sake of animal welfare and global food security.

Julia Hatamyar

This paper studies the effects of legislation mandating the provision of workplace breastfeeding amenities on the labor force participation of women in the United States. Using both the American Community Survey and the Panel Study of Income Dynamics, in a staggered difference-in-differences framework, I find evidence that workplace breastfeeding legislation significantly increases the likelihood of female labor force participation (FLFP) across both datasets and multiple specifications, by at least 1.5 percentage points. The timing and magnitude of the post-law increases in FLFP differ across the two datasets. I bolster the analyses using the CDC's Infant Feeding Practices Survey and the Childhood and Adoption Supplement to the PSID, which further suggest an influence of the laws on breastfeeding women. Heterogeneity analysis indicates the presence of substantial treatment effect heterogeneity across subgroups, but the findings are specific to the separate datasets. Across both datasets, the legislation appears to be more effective in states where average pre-law FLFP was comparatively low. I also find evidence of a negative spillover effect, whereby women without children and women with older children may have reduced their LFP in response to the legislation.

Chen Liu, Matthew Amodio, Liangbo L. Shen et al.

Segmenting medical images is critical to facilitating both patient diagnoses and quantitative research. A major limiting factor is the lack of labeled data, as obtaining expert annotations for each new set of imaging data and task can be labor intensive and inconsistent among annotators. We present CUTS, an unsupervised deep learning framework for medical image segmentation. CUTS operates in two stages. For each image, it produces an embedding map via intra-image contrastive learning and local patch reconstruction. Then, these embeddings are partitioned at dynamic granularity levels that correspond to the data topology. CUTS yields a series of coarse-to-fine-grained segmentations that highlight features at various granularities. We applied CUTS to retinal fundus images and two types of brain MRI images to delineate structures and patterns at different scales. When evaluated against predefined anatomical masks, CUTS improved the dice coefficient and Hausdorff distance by at least 10% compared to existing unsupervised methods. Finally, CUTS showed performance on par with Segment Anything Models (SAM, MedSAM, SAM-Med2D) pre-trained on gigantic labeled datasets.