Hasil untuk "Medical legislation"

Vlad-Gabriel Vasilescu, Lucian Toma Ciocan, Andreia Cucuruz et al.

<b>Background/Objectives:</b> The main objective of optimizing the composition of dental implants is to improve tissue compatibility for enhanced biological/biochemical performance. In this context, research on the development of new titanium alloys in dental implantology considers the careful selection of alloying elements, both in terms of biocompatibility (their lack of toxicity) and their potential to improve the metallurgical processing capacity (thermal and/or thermomechanical), which through controlled microstructural changes lead to the optimal combination of properties for functionality and durability of the implant. The purpose of the research is to study the influence of alloying elements on the phase composition and physical–mechanical properties of experimental titanium alloys. <b>Methods:</b> Four alloys with original chemical compositions were developed, coded in the experiments as follows: Ti1, Ti2, Ti3, Ti4. The characterization of the alloys was carried out by detailed analysis of the chemical composition, phase structure and by testing the physico-mechanical properties (HV hardness, tensile strength, yield strength, elongation, modulus of elasticity), by standardized modern methods. Characterization methods, such as optical microscopy, SEM, EDS and XRD were performed, followed by tensile tests based on ASTM EB/EBM-22 and EN ISO 6892-1-2009 standards. <b>Results:</b> The research results provide information regarding the relationship between the composition and the physico-mechanical properties (Rm, Rp, HV, A, G, E) of the experimental alloys (Ti1–Ti4). Depending on the value level of the properties, these have been highlighted: compositions in which the alloy can be indicated for conditions of intense stress (Ti3), compositions that describe highly ductile alloys, easy to process and adapt to clinical requirements (Ti4), but also alloys compositions characterized by a balanced combination of strength, plasticity/ductility (Ti1, Ti2). <b>Conclusions:</b> Research for the development of new titanium alloys through the optimization of chemical composition has taken into account the requirements regarding the biological/biomechanical compatibility of biomaterials. Analyzed in comparison with Cp-Ti grade 4 and Ti6A4V, the experimental alloys (Ti1–Ti4) can be characterized as follows: The mechanical strength properties (Rm and Rp) are higher than those of pure commercial titanium (Cp-Ti grade 4) for all compositions Ti1–Ti4, but slightly lower than those of alloy Ti6Al4V. The plasticity–ductility properties have values comparable to those of Cp-Ti grade 4 (Ti4 and Ti2 compositions) and Ti6Al4V (Ti1 composition), with one exception, the Ti3 alloy. All four experimental alloys have a lower modulus of elasticity than Cp-Ti grade 4 (102–104 GPa) and Ti6Al4V (113 GPa), commonly used in dental implants. An in-depth analysis, which will also consider information on corrosion behavior and cellular testing, may support the selection of some of the four experimental alloys studied. The research aims to continue the progress to a higher level of testing, through the realization of dental implants (e.g., fatigue, wear, osteointegration capacity, etc.).

Blake VanBerlo, Alexander Wong, Jesse Hoey et al.

Data augmentation is a central component of joint embedding self-supervised learning (SSL). Approaches that work for natural images may not always be effective in medical imaging tasks. This study systematically investigated the impact of data augmentation and preprocessing strategies in SSL for lung ultrasound. Three data augmentation pipelines were assessed: (1) a baseline pipeline commonly used across imaging domains, (2) a novel semantic-preserving pipeline designed for ultrasound, and (3) a distilled set of the most effective transformations from both pipelines. Pretrained models were evaluated on multiple classification tasks: B-line detection, pleural effusion detection, and COVID-19 classification. Experiments revealed that semantics-preserving data augmentation resulted in the greatest performance for COVID-19 classification - a diagnostic task requiring global image context. Cropping-based methods yielded the greatest performance on the B-line and pleural effusion object classification tasks, which require strong local pattern recognition. Lastly, semantics-preserving ultrasound image preprocessing resulted in increased downstream performance for multiple tasks. Guidance regarding data augmentation and preprocessing strategies was synthesized for practitioners working with SSL in ultrasound.

Xin Wang, Yin Guo, Kaiyu Zhang et al.

This work presents a novel Bayesian framework for unsupervised domain adaptation (UDA) in medical image segmentation. While prior works have explored this clinically significant task using various strategies of domain alignment, they often lack an explicit and explainable mechanism to ensure that target image features capture meaningful structural information. Besides, these methods are prone to the curse of dimensionality, inevitably leading to challenges in interpretability and computational efficiency. To address these limitations, we propose RemInD, a framework inspired by human adaptation. RemInD learns a domain-agnostic latent manifold, characterized by several anchors, to memorize anatomical variations. By mapping images onto this manifold as weighted anchor averages, our approach ensures realistic and reliable predictions. This design mirrors how humans develop representative components to understand images and then retrieve component combinations from memory to guide segmentation. Notably, model prediction is determined by two explainable factors: a low-dimensional anchor weight vector, and a spatial deformation. This design facilitates computationally efficient and geometry-adherent adaptation by aligning weight vectors between domains on a probability simplex. Experiments on two public datasets, encompassing cardiac and abdominal imaging, demonstrate the superiority of RemInD, which achieves state-of-the-art performance using a single alignment approach, outperforming existing methods that often rely on multiple complex alignment strategies.

Aadarsh Rajiv Patel, Klaus Mueller

Modern legislative frameworks, such as the Affordable Care Act (ACA), often involve complex webs of agencies, mandates, and interdependencies. Government issued charts attempt to depict these structures but are typically static, dense, and difficult to interpret - even for experts. We introduce LegiScout, an interactive visualization system that transforms static policy diagrams into dynamic, force-directed graphs, enhancing comprehension while preserving essential relationships. By integrating data extraction, natural language processing, and computer vision techniques, LegiScout supports deeper exploration of not only the ACA but also a wide range of legislative and regulatory frameworks. Our approach enables stakeholders - policymakers, analysts, and the public - to navigate and understand the complexity inherent in modern law.

Ahmad Chaddad, Jihao Peng, Yihang Wu

The use of deep learning (DL) in medical image analysis has significantly improved the ability to predict lung cancer. In this study, we introduce a novel deep convolutional neural network (CNN) model, named ResNet+, which is based on the established ResNet framework. This model is specifically designed to improve the prediction of lung cancer and diseases using the images. To address the challenge of missing feature information that occurs during the downsampling process in CNNs, we integrate the ResNet-D module, a variant designed to enhance feature extraction capabilities by modifying the downsampling layers, into the traditional ResNet model. Furthermore, a convolutional attention module was incorporated into the bottleneck layers to enhance model generalization by allowing the network to focus on relevant regions of the input images. We evaluated the proposed model using five public datasets, comprising lung cancer (LC2500 $n$=3183, IQ-OTH/NCCD $n$=1336, and LCC $n$=25000 images) and lung disease (ChestXray $n$=5856, and COVIDx-CT $n$=425024 images). To address class imbalance, we used data augmentation techniques to artificially increase the representation of underrepresented classes in the training dataset. The experimental results show that ResNet+ model demonstrated remarkable accuracy/F1, reaching 98.14/98.14\% on the LC25000 dataset and 99.25/99.13\% on the IQ-OTH/NCCD dataset. Furthermore, the ResNet+ model saved computational cost compared to the original ResNet series in predicting lung cancer images. The proposed model outperformed the baseline models on publicly available datasets, achieving better performance metrics. Our codes are publicly available at https://github.com/AIPMLab/Graduation-2024/tree/main/Peng.

Anvar Kurmukov, Bogdan Zavolovich, Aleksandra Dalechina et al.

Image compression is a critical tool in decreasing the cost of storage and improving the speed of transmission over the internet. While deep learning applications for natural images widely adopts the usage of lossy compression techniques, it is not widespread for 3D medical images. Using three CT datasets (17 tasks) and one MRI dataset (3 tasks) we demonstrate that lossy compression up to 20 times have no negative impact on segmentation quality with deep neural networks (DNN). In addition, we demonstrate the ability of DNN models trained on compressed data to predict on uncompressed data and vice versa with no quality deterioration.

Jamil Zaghir, Marco Naguib, Mina Bjelogrlic et al.

Prompt engineering is crucial for harnessing the potential of large language models (LLMs), especially in the medical domain where specialized terminology and phrasing is used. However, the efficacy of prompt engineering in the medical domain remains to be explored. In this work, 114 recent studies (2022-2024) applying prompt engineering in medicine, covering prompt learning (PL), prompt tuning (PT), and prompt design (PD) are reviewed. PD is the most prevalent (78 articles). In 12 papers, PD, PL, and PT terms were used interchangeably. ChatGPT is the most commonly used LLM, with seven papers using it for processing sensitive clinical data. Chain-of-Thought emerges as the most common prompt engineering technique. While PL and PT articles typically provide a baseline for evaluating prompt-based approaches, 64% of PD studies lack non-prompt-related baselines. We provide tables and figures summarizing existing work, and reporting recommendations to guide future research contributions.

Anna Romanova

The significant part of the operational context for autonomous company management systems is the regulatory and legal environment in which corporations operate. In order to create a dedicated operational context for autonomous artificial intelligence systems, the wording of local regulatory documents can be simultaneously presented in two versions: for use by people and for use by autonomous systems. In this case, the artificial intelligence system will get a well-defined operational context that allows such a system to perform functions within the required standards. Local regulations that provide basis for the joint work of individuals and autonomous artificial intelligence systems can form the grounds for the relevant legislation governing the development and implementation of autonomous systems.

Olena Martynyuk, Svitlana Busel, Anna Nemchenko

At the contemporary stage of development of the global healthcare industry, improving the quality of medical care is the main goal and the main criterion for assessing its effectiveness. Therefore, ensuring the high quality of medical care and medical services is the responsibility of healthcare authorities, managers of healthcare facilities of any form of ownership and all medical professionals. An important mechanism for achieving this in the modern world is standardisation as a key tool for quality management. The purpose of this article is to study the existing international healthcare standards, analyse the state of standardisation in the healthcare sector as a basic element of providing quality medical and pharmaceutical care to the population, and to identify opportunities for implementing the best standards in the practice of the healthcare system in Ukraine. The findings of the study show that international service quality standards are the most important frameworks developed and maintained by international organisations to ensure consistency, reliability and security across industries. All these standards are aimed at increasing customer satisfaction, operational efficiency and international competitiveness. Keeping these standards up-to-date and compliant is essential to meet customer expectations and regulatory requirements in today's ever-changing globalised world. By systematising scientific research, the authors have established that the transformation of the healthcare system in Ukraine will be successful if the most significant domestic achievements in the healthcare sector are rationally combined with the world's best practices and international standards, the principles of healthcare contained in international human rights instruments, and the principles and norms that define the content and scope of human rights in the healthcare sector that Ukraine must implement. Moreover, it is essential to establish the world's best practices in the field of treatment of major diseases, principles of medical services, and training of staff, which will help to achieve the necessary improvement in the quality of medical care in the context of the development of the medical system of Ukraine. It is determined that in the process of adaptation of national legislation to the regulations of the European Union, all ISO 9000 standards were adopted in Ukraine as national standards and their implementation in everyday activities, including in the healthcare sector, was organised. Considering all of the abovementioned, the System of Implementation of International Quality Standards for Healthcare Services is proposed. The standards are divided into international, national, sectoral, regional and local standards by the scope of influence. According to the Donabedian triad, the objects of influence are: resources, processes and outcomes of healthcare. The types of standards are grouped by object, and the mechanisms of influence on the quality of standardisation are defined: Licensing of healthcare facilities, Accreditation of healthcare facilities, Certification of healthcare professionals. The ways of implementing international standards can be defined as direct, indirect, doctrinal and institutional, so the regulatory and legal mechanisms will operate through laws that have already been ratified in Ukraine. For example, the Law of Ukraine ‘On the State Programme for Adaptation of Ukrainian Legislation to the Legislation of the European Union’ allows for the formation of action chains for the implementation and reform of the Ukrainian healthcare system.

Pablo Ros-Arlanzón, Angel Perez-Sempere

Abstract BackgroundWith the rapid advancement of artificial intelligence (AI) in various fields, evaluating its application in specialized medical contexts becomes crucial. ChatGPT, a large language model developed by OpenAI, has shown potential in diverse applications, including medicine. ObjectiveThis study aims to compare the performance of ChatGPT with that of attending neurologists in a real neurology specialist examination conducted in the Valencian Community, Spain, assessing the AI’s capabilities and limitations in medical knowledge. MethodsWe conducted a comparative analysis using the 2022 neurology specialist examination results from 120 neurologists and responses generated by ChatGPT versions 3.5 and 4. The examination consisted of 80 multiple-choice questions, with a focus on clinical neurology and health legislation. Questions were classified according to Bloom’s Taxonomy. Statistical analysis of performance, including the κ coefficient for response consistency, was performed. ResultsHuman participants exhibited a median score of 5.91 (IQR: 4.93-6.76), with 32 neurologists failing to pass. ChatGPT-3.5 ranked 116th out of 122, answering 54.5% of questions correctly (score 3.94). ChatGPT-4 showed marked improvement, ranking 17th with 81.8% of correct answers (score 7.57), surpassing several human specialists. No significant variations were observed in the performance on lower-order questions versus higher-order questions. Additionally, ChatGPT-4 demonstrated increased interrater reliability, as reflected by a higher κ coefficient of 0.73, compared to ChatGPT-3.5’s coefficient of 0.69. ConclusionsThis study underscores the evolving capabilities of AI in medical knowledge assessment, particularly in specialized fields. ChatGPT-4’s performance, outperforming the median score of human participants in a rigorous neurology examination, represents a significant milestone in AI development, suggesting its potential as an effective tool in specialized medical education and assessment.

Ange Lou, Shuyue Guan, Murray Loew

Segmenting medical images accurately and reliably is important for disease diagnosis and treatment. It is a challenging task because of the wide variety of objects' sizes, shapes, and scanning modalities. Recently, many convolutional neural networks (CNN) have been designed for segmentation tasks and achieved great success. Few studies, however, have fully considered the sizes of objects, and thus most demonstrate poor performance for small objects segmentation. This can have a significant impact on the early detection of diseases. This paper proposes a Context Axial Reverse Attention Network (CaraNet) to improve the segmentation performance on small objects compared with several recent state-of-the-art models. CaraNet applies axial reserve attention (ARA) and channel-wise feature pyramid (CFP) module to dig feature information of small medical object. And we evaluate our model by six different measurement metrics. We test our CaraNet on brain tumor (BraTS 2018) and polyp (Kvasir-SEG, CVC-ColonDB, CVC-ClinicDB, CVC-300, and ETIS-LaribPolypDB) segmentation datasets. Our CaraNet achieves the top-rank mean Dice segmentation accuracy, and results show a distinct advantage of CaraNet in the segmentation of small medical objects.

Andrew M. Bean, Karolina Korgul, Felix Krones et al.

Large language models (LLMs) have made rapid improvement on medical benchmarks, but their unreliability remains a persistent challenge for safe real-world uses. To design for the use LLMs as a category, rather than for specific models, requires developing an understanding of shared strengths and weaknesses which appear across models. To address this challenge, we benchmark a range of top LLMs and identify consistent patterns across models. We test $16$ well-known LLMs on $874$ newly collected questions from Polish medical licensing exams. For each question, we score each model on the top-1 accuracy and the distribution of probabilities assigned. We then compare these results with factors such as question difficulty for humans, question length, and the scores of the other models. LLM accuracies were positively correlated pairwise ($0.39$ to $0.58$). Model performance was also correlated with human performance ($0.09$ to $0.13$), but negatively correlated to the difference between the question-level accuracy of top-scoring and bottom-scoring humans ($-0.09$ to $-0.14$). The top output probability and question length were positive and negative predictors of accuracy respectively (p$< 0.05$). The top scoring LLM, GPT-4o Turbo, scored $84\%$, with Claude Opus, Gemini 1.5 Pro and Llama 3/3.1 between $74\%$ and $79\%$. We found evidence of similarities between models in which questions they answer correctly, as well as similarities with human test takers. Larger models typically performed better, but differences in training, architecture, and data were also highly impactful. Model accuracy was positively correlated with confidence, but negatively correlated with question length. We find similar results with older models, and argue that these patterns are likely to persist across future models using similar training methods.

F. Lobbezoo, G. Aarab

In addition, national and global health care planning, politics, and legislation should be aligned with new medical curricula across all levels of study undergraduate, graduate, and

Skylar E. Stolte, Kyle Volle, Aprinda Indahlastari et al.

Model calibration measures the agreement between the predicted probability estimates and the true correctness likelihood. Proper model calibration is vital for high-risk applications. Unfortunately, modern deep neural networks are poorly calibrated, compromising trustworthiness and reliability. Medical image segmentation particularly suffers from this due to the natural uncertainty of tissue boundaries. This is exasperated by their loss functions, which favor overconfidence in the majority classes. We address these challenges with DOMINO, a domain-aware model calibration method that leverages the semantic confusability and hierarchical similarity between class labels. Our experiments demonstrate that our DOMINO-calibrated deep neural networks outperform non-calibrated models and state-of-the-art morphometric methods in head image segmentation. Our results show that our method can consistently achieve better calibration, higher accuracy, and faster inference times than these methods, especially on rarer classes. This performance is attributed to our domain-aware regularization to inform semantic model calibration. These findings show the importance of semantic ties between class labels in building confidence in deep learning models. The framework has the potential to improve the trustworthiness and reliability of generic medical image segmentation models. The code for this article is available at: https://github.com/lab-smile/DOMINO.

Iryna Zhyvylo

According to the Ministry of Health of Ukraine, 80% of patients with rare diseases in Ukraine die within 5 years due to the lack of systematic diagnosis and qualified treatment. This is more than, for example, 50% in France. As Russia’s military incursion continues to disrupt basic health services, major efforts are needed to restore and strengthen health services, including access to medicines and medical equipment. Under these circumstances, the heroic work of doctors, both on the territory of our country and abroad, who, despite the challenges faced by the community of rare diseases in Ukraine, did not stop for a moment their work to support and help the community of patients with rare diseases and the mobilization of political advocacy and legislation at the national level. Currently, humanitarian organizations and the international community are making maximum efforts to generally protect the most vulnerable segment of the population, which is affected by the conflict, cannot leave and does not have access to humanitarian aid. The current situation should not undermine the reality that the needs of people living with a rare disease are real, enormous and unmet. The creation of legal, economic and administrative mechanisms for the realization of the constitutional rights of the population of Ukraine suffering from rare (orphan) diseases, preservation and strengthening of their health, extension of the period of active longevity and length of their lives is one of the main tasks of the state. So, the article proposes a structured complex political program document aimed at solving the issues of patients suffering from rare (orphan) diseases. During the development and formation of this state policy, the best practices of developed European countries were used. An overview of the state and problems of national regulatory and organizational support in the field of access to treatment for patients with rare (orphan) diseases was also conducted. Scientific achievements of domestic and foreign researchers, statistical data of state authorities, international organizations and own author’s research were taken into account.

Luiza Beattrys Pereira dos Santos Lima, Marcus Pinto Aguiar

O paradigma de resolução de conflitos sanitários representado pela prestação judicial encontra-se em crise e não consegue responder aos litígios inerentes de forma qualitativa e quantitativamente adequada. Diante disso, este artigo buscou responder à questão: a mediação sanitária pode ser um instrumento adequado de acesso à justiça para o tratamento de conflitos relativos ao direito à saúde pública no Brasil? Analisaram-se aspectos teóricos (e jurídicos) do direito à saúde, enquanto direito humano e fundamental, e os contornos da crise da judicialização do direito à saúde, enquanto relevante para a quebra de paradigmas, para, por fim, investigar se a mediação sanitária pode ser ferramenta adequada de acesso à justiça, com suas respectivas implicações. Foi utilizada como procedimento metodológico a pesquisa documental, de caráter exploratório e de natureza qualitativa. Quanto às técnicas de pesquisa, de documentação direta e indireta, utilizaram-se notadamente a bibliográfica e a documental. O objeto de pesquisa possui relevância jurídica, social e econômica, haja vista que a crise dos direitos sociais representa uma crise de direitos humanos, afetando diretamente a dignidade da vida humana. A mediação sanitária revelou-se como uma ferramenta adequada de acesso à justiça nos conflitos jurídico-sanitários, pois transforma os antagonismos em pontos de convergência e colaboração, prevenindo e tratando os litígios de maneira dialógica, consensual e democrática.

I.B. Ventskivska, L.M. Deshko, O.S. Lotiuk et al.

Objective: to identify the standards of the European Court of Human Rights on the introduction of mandatory vaccination of medical personnel from COVID-19 in conditions of pandemic. The analysis has been carried out on the Decisions of the European Court of Human Rights as for vaccination matters, which formed the legal position of the Court on its implementation by the State. These decisions were divided into groups according to the conditions in which the European Council launched mandatory vaccination: the situation, which is being ordinary, one (standard vaccination against diseases well known to medical science, where vaccines have been tested and investigated thoroughly). Another one is extraordinary situation within society and state, as well as in the world, for example, COVID-19 pandemic. The standards of the European Court of Human Rights for the introduction of mandatory vaccination of medical personnel against COVID-19 in conditions of pandemic have been identified: these measures must be provided by the State legislation which is to meet quality rule of law criteria; to pursue legitimate goal (protection of the population from COVID-19); to be necessary in democratic society. Mandatory vaccination of healthcare professionals against COVID-19 should be used if the goal of protecting the population from COVID-19 cannot be achieved in other ways. Mandatory vaccination of medical personnel against COVID-19 is not the same as forced vaccination. The medical employee chooses whether to be vaccinated against COVID-19 or not according to his own views, values, no matter how irrational, unreasonable, shortsighted they may be in the opinion of the state and other people. The state does not have the right to use forced vaccination, but may apply the following: a range of measures to clarify, persuade, encourage mandatory vaccination of medical personnel against COVID-19, which may be direct or indirect, but not violent; sanctions for refusal from mandatory vaccination of medical personnel from COVID-19 who have no contraindications (suspension from medical activities, fines, etc.). Conclusions. The data obtained in this way allow us to develop further proposals for improving legal regulation of vaccination in Member States of the Council of Europe and increase the effectiveness of ensuring the rights of medical personnel, reduce tensions within society.

Yu Tian, Fengbei Liu, Guansong Pang et al.

Unsupervised anomaly detection (UAD) methods are trained with normal (or healthy) images only, but during testing, they are able to classify normal and abnormal (or disease) images. UAD is an important medical image analysis (MIA) method to be applied in disease screening problems because the training sets available for those problems usually contain only normal images. However, the exclusive reliance on normal images may result in the learning of ineffective low-dimensional image representations that are not sensitive enough to detect and segment unseen abnormal lesions of varying size, appearance, and shape. Pre-training UAD methods with self-supervised learning, based on computer vision techniques, can mitigate this challenge, but they are sub-optimal because they do not explore domain knowledge for designing the pretext tasks, and their contrastive learning losses do not try to cluster the normal training images, which may result in a sparse distribution of normal images that is ineffective for anomaly detection. In this paper, we propose a new self-supervised pre-training method for MIA UAD applications, named Pseudo Multi-class Strong Augmentation via Contrastive Learning (PMSACL). PMSACL consists of a novel optimisation method that contrasts a normal image class from multiple pseudo classes of synthesised abnormal images, with each class enforced to form a dense cluster in the feature space. In the experiments, we show that our PMSACL pre-training improves the accuracy of SOTA UAD methods on many MIA benchmarks using colonoscopy, fundus screening and Covid-19 Chest X-ray datasets. The code is made publicly available via https://github.com/tianyu0207/PMSACL.

Adrian Galdran, Gustavo Carneiro, Miguel A. González Ballester

Highly imbalanced datasets are ubiquitous in medical image classification problems. In such problems, it is often the case that rare classes associated to less prevalent diseases are severely under-represented in labeled databases, typically resulting in poor performance of machine learning algorithms due to overfitting in the learning process. In this paper, we propose a novel mechanism for sampling training data based on the popular MixUp regularization technique, which we refer to as Balanced-MixUp. In short, Balanced-MixUp simultaneously performs regular (i.e., instance-based) and balanced (i.e., class-based) sampling of the training data. The resulting two sets of samples are then mixed-up to create a more balanced training distribution from which a neural network can effectively learn without incurring in heavily under-fitting the minority classes. We experiment with a highly imbalanced dataset of retinal images (55K samples, 5 classes) and a long-tail dataset of gastro-intestinal video frames (10K images, 23 classes), using two CNNs of varying representation capabilities. Experimental results demonstrate that applying Balanced-MixUp outperforms other conventional sampling schemes and loss functions specifically designed to deal with imbalanced data. Code is released at https://github.com/agaldran/balanced_mixup .

Tuomas Granlund, Juha Vedenpää, Vlad Stirbu et al.

The medical device products at the European Union market must be safe and effective. To ensure this, medical device manufacturers must comply to the new regulatory requirements brought by the Medical Device Regulation (MDR) and the In Vitro Diagnostic Medical Device Regulation (IVDR). In general, the new regulations increase regulatory requirements and oversight, especially for medical software, and this is also true for requirements related to cybersecurity, which are now explicitly addressed in the legislation. The significant legislation changes currently underway, combined with increased cybersecurity requirements, create unique challenges for manufacturers to comply with the regulatory framework. In this paper, we review the new cybersecurity requirements in the light of currently available guidance documents, and pinpoint four core concepts around which cybersecurity compliance can be built. We argue that these core concepts form a foundations for cybersecurity compliance in the European Union regulatory framework.