The rapid advancements in big data and artificial intelligence have posed challenges to the traditional model of specific informed consent. This paper examines the practices and governance framework of the UK "Our Future Health" project, which operates under a broad consent model. The project has garnered a relatively high level of public trust, largely due to its well-established broad informed consent procedures, transparent information disclosure, extensive public engagement, and robust governance structures and institutional framework. However, the paper also scrutinizes the controversies it has faced, such as potential misleading publicity, inequalities in the recruitment process, inadequate risk disclosure, and deficiencies in the withdrawal mechanism. Drawing on China's national context, the paper suggests establishing and clarifying the basis for the legality of broad informed consent, refining the broad informed consent process, strengthening data governance system, improving transparency, and encouraging public participation.
Mehdi Mirzaei-Alavijeh, Shakila Valadbeygi, Hassan Gharibnavaz
et al.
Abstract Background Research ethics is crucial for protecting participants’ rights in medical studies. Although several studies have explored general awareness and attitudes toward research ethics among medical students, few have systematically examined the behavioral determinants of adherence to Research Ethical Codes (REC) using established theoretical models. This study addresses this gap by identifying the determinants of REC adherence among students at Kermanshah University of Medical Sciences (KUMS), applying the Theory of Planned Behavior (TPB) as a conceptual framework. Methods A descriptive-analytical study was conducted in 2024 among KUMS students. A cluster sampling approach was used, with structured questionnaires distributed to gather data on demographics and TPB constructs. Data were analyzed using SPSS, employing Pearson correlation and linear regression analyses. Results The study included 271 participants with a mean age of 23.99 years. The adherence level to ethical codes was 69.1%. The adjusted R² value was 0.352, indicating that 35.2% of the variance in adherence to REC behavior was explained by the model. Notably, attitude (B = 0.694, p < 0.001) and intention (B = 0.857, p = 0.002) were significant predictors. The highest adherence was for confidentiality (mean score = 4.04), while the lowest was for obtaining ethical approval before data collection (mean score = 2.68). Conclusions The findings indicate a 69.1% adherence to ethical research codes, with attitude and intention identified as key predictors of ethical behavior. These results emphasize the importance of targeted educational strategies to strengthen students’ commitment to ethical research practices.
Medical image denoising is considered among the most challenging vision tasks. Despite the real-world implications, existing denoising methods have notable drawbacks as they often generate visual artifacts when applied to heterogeneous medical images. This study addresses the limitation of the contemporary denoising methods with an artificial intelligence (AI)-driven two-stage learning strategy. The proposed method learns to estimate the residual noise from the noisy images. Later, it incorporates a novel noise attention mechanism to correlate estimated residual noise with noisy inputs to perform denoising in a course-to-refine manner. This study also proposes to leverage a multi-modal learning strategy to generalize the denoising among medical image modalities and multiple noise patterns for widespread applications. The practicability of the proposed method has been evaluated with dense experiments. The experimental results demonstrated that the proposed method achieved state-of-the-art performance by significantly outperforming the existing medical image denoising methods in quantitative and qualitative comparisons. Overall, it illustrates a performance gain of 7.64 in Peak Signal-to-Noise Ratio (PSNR), 0.1021 in Structural Similarity Index (SSIM), 0.80 in DeltaE ($ΔE$), 0.1855 in Visual Information Fidelity Pixel-wise (VIFP), and 18.54 in Mean Squared Error (MSE) metrics.
Felix Buendía, Joaquín Gayoso-Cabada, José-Luis Sierra
In this paper, we describe an approach to transforming the huge amount of medical knowledge available in existing online medical collections into standardized learning packages ready to be integrated into the most popular e-learning platforms. The core of our approach is a tool called Clavy, which makes it possible to retrieve pieces of content in medical collections, to transform this content into meaningful learning units, and to export it in the form of standardized learning packages. In addition to describing the approach, we demonstrate its feasibility by applying it to the generation of IMS content packages from MedPix, a popular online database of medical cases in the domain of radiology.
Nikita Malik, Pratinav Seth, Neeraj Kumar Singh
et al.
Deep learning has driven significant advances in medical image analysis, yet its adoption in clinical practice remains constrained by the large size and lack of transparency in modern models. Advances in interpretability techniques such as DL-Backtrace, Layer-wise Relevance Propagation, and Integrated Gradients make it possible to assess the contribution of individual components within neural networks trained on medical imaging tasks. In this work, we introduce an interpretability-guided pruning framework that reduces model complexity while preserving both predictive performance and transparency. By selectively retaining only the most relevant parts of each layer, our method enables targeted compression that maintains clinically meaningful representations. Experiments across multiple medical image classification benchmarks demonstrate that this approach achieves high compression rates with minimal loss in accuracy, paving the way for lightweight, interpretable models suited for real-world deployment in healthcare settings.
El siguiente trabajo pone en discusión avances terapéuticos que implican modificaciones en cuerpos humanos mediante inteligencia artificial (IA). Una de las preguntas principales incluye ensayos clínicos, sujetos de investigación y autonomía. Se analizarán aspectos ético-comunicacionales en el vínculo entre investigador/a y sujeto de investigación, así como aspectos de la relación médico-paciente en la implementación de IA para tratamientos terapéuticos. ¿Debe el profesional de la salud transparentar su aplicación a los pacientes?
A su vez, se analizará el recorte específico de ensayos clínicos en personas privadas de la libertad, tomando como analogía el caso de ficción La naranja mecánica para reflexionar sobre la decisión autónoma en circunstancias extremas desde una perspectiva bioética a la vez que intentaremos responder a la pregunta, ¿es la modificación artificial del ser una forma ética de resolver problemas sociales?
Medical philosophy. Medical ethics, Business ethics
The current mainstream multi-modal medical image-to-image translation methods face a contradiction. Supervised methods with outstanding performance rely on pixel-wise aligned training data to constrain the model optimization. However, obtaining pixel-wise aligned multi-modal medical image datasets is challenging. Unsupervised methods can be trained without paired data, but their reliability cannot be guaranteed. At present, there is no ideal multi-modal medical image-to-image translation method that can generate reliable translation results without the need for pixel-wise aligned data. This work aims to develop a novel medical image-to-image translation model that is independent of pixel-wise aligned data (MITIA), enabling reliable multi-modal medical image-to-image translation under the condition of misaligned training data. The proposed MITIA model utilizes a prior extraction network composed of a multi-modal medical image registration module and a multi-modal misalignment error detection module to extract pixel-level prior information from training data with misalignment errors to the largest extent. The extracted prior information is then used to construct a regularization term to constrain the optimization of the unsupervised cycle-consistent GAN model, restricting its solution space and thereby improving the performance and reliability of the generator. We trained the MITIA model using six datasets containing different misalignment errors and two well-aligned datasets. Subsequently, we compared the proposed method with six other state-of-the-art image-to-image translation methods. The results of both quantitative analysis and qualitative visual inspection indicate that MITIA achieves superior performance compared to the competing state-of-the-art methods, both on misaligned data and aligned data.
Medical image representations can be learned through medical vision-language contrastive learning (mVLCL) where medical imaging reports are used as weak supervision through image-text alignment. These learned image representations can be transferred to and benefit various downstream medical vision tasks such as disease classification and segmentation. Recent mVLCL methods attempt to align image sub-regions and the report keywords as local-matchings. However, these methods aggregate all local-matchings via simple pooling operations while ignoring the inherent relations between them. These methods therefore fail to reason between local-matchings that are semantically related, e.g., local-matchings that correspond to the disease word and the location word (semantic-relations), and also fail to differentiate such clinically important local-matchings from others that correspond to less meaningful words, e.g., conjunction words (importance-relations). Hence, we propose a mVLCL method that models the inter-matching relations between local-matchings via a relation-enhanced contrastive learning framework (RECLF). In RECLF, we introduce a semantic-relation reasoning module (SRM) and an importance-relation reasoning module (IRM) to enable more fine-grained report supervision for image representation learning. We evaluated our method using six public benchmark datasets on four downstream tasks, including segmentation, zero-shot classification, linear classification, and cross-modal retrieval. Our results demonstrated the superiority of our RECLF over the state-of-the-art mVLCL methods with consistent improvements across single-modal and cross-modal tasks. These results suggest that our RECLF, by modelling the inter-matching relations, can learn improved medical image representations with better generalization capabilities.
Saikat Roy, Gregor Koehler, Michael Baumgartner
et al.
Owing to success in the data-rich domain of natural images, Transformers have recently become popular in medical image segmentation. However, the pairing of Transformers with convolutional blocks in varying architectural permutations leaves their relative effectiveness to open interpretation. We introduce Transformer Ablations that replace the Transformer blocks with plain linear operators to quantify this effectiveness. With experiments on 8 models on 2 medical image segmentation tasks, we explore -- 1) the replaceable nature of Transformer-learnt representations, 2) Transformer capacity alone cannot prevent representational replaceability and works in tandem with effective design, 3) The mere existence of explicit feature hierarchies in transformer blocks is more beneficial than accompanying self-attention modules, 4) Major spatial downsampling before Transformer modules should be used with caution.
Christos Matsoukas, Johan Fredin Haslum, Moein Sorkhei
et al.
Convolutional Neural Networks (CNNs) have reigned for a decade as the de facto approach to automated medical image diagnosis, pushing the state-of-the-art in classification, detection and segmentation tasks. Over the last years, vision transformers (ViTs) have appeared as a competitive alternative to CNNs, yielding impressive levels of performance in the natural image domain, while possessing several interesting properties that could prove beneficial for medical imaging tasks. In this work, we explore the benefits and drawbacks of transformer-based models for medical image classification. We conduct a series of experiments on several standard 2D medical image benchmark datasets and tasks. Our findings show that, while CNNs perform better if trained from scratch, off-the-shelf vision transformers can perform on par with CNNs when pretrained on ImageNet, both in a supervised and self-supervised setting, rendering them as a viable alternative to CNNs.
Andrey Reshetnikov, Nadezhda Prisyazhnaya, Florian Steger
et al.
The coronavirus pandemic has raised serious questions about the need to properly inform residents of large cities about the rules of hygiene, behavior in self-isolation, and maintaining health. This study aimed to identify in more detail the sources of information and to assess the levels of awareness and knowledge of the inhabitants of a typical metropolis about coronavirus infection to further search for ways to improve health information during pandemics. This research has a questionnaire survey design. Data from 478 adult Muscovites were collected on 20–25 March 2020 by the Institute of Social Sciences of Sechenov University. The aim of this study was to study the level of awareness in preventing the spread of infection and peculiarities in the perceptions of residents of the city of Moscow toward the large-scale social changes associated with the COVID-19 pandemic as well as their impact on the way of life, social relations, lifestyle, and ideas about the future of the population. This article presents the results of a medical and sociological survey of residents of Moscow implemented at the beginning of the spread of coronavirus infection in the country, which showed the awareness of residents of Moscow regarding the problem of the spread of coronavirus and the prevention of infection as well as a high level of anxiety and the pessimistic expectations of respondents regarding the consequences of the COVID-19 pandemic for the state, society, and people. At the same time, the fears of the survey participants involved both immediate risks of the disease and a wide range of socioeconomic problems from near and distant perspectives.
Abstract Background Respecting patients’ confidentiality is an ethical and legal responsibility for health professionals and the cornerstone of care excellence. This study aims to assess health professionals’ knowledge, attitudes, and associated factors towards patients’ confidentiality in a resource-limited setting. Methods Institutional based cross-sectional study was conducted among 423 health professionals. Stratified sampling methods were used to select the participants, and a structured self-administer questionnaire was used for data collection. The data was entered using Epi-data version 4.6 and analyzed using SPSS, version 25. Bi-variable and multivariable binary logistic regression analyses were used to measure the association between the dependent and independent variables. Odds ratio with 95% confidence intervals and P value was calculated to determine the strength of association and to evaluate statistical significance. Result Out of 410 participants, about 59.8% with [95% CI (54.8–68.8%)] and 49.5% with [95% CI (44.5–54.5%)] had good knowledge and favorable attitude towards patents confidentiality respectively. Being male (AOR = 1.63, 95% CI [1.03–2.59]), taking training on medical ethics (AOR = 1.73, 95% CI = [1.11–2.70]), facing ethical dilemmas (AOR = 3.07, 95% CI [1.07–8.79]) were significantly associated factors for health professional knowledge towards patients’ confidentiality. Likewise, taking training on medical ethics (AOR = 2.30, 95% CI [1.42–3.72]), having direct contact with the patients (AOR = 3.06, 95% CI [1.12–8.34]), visiting more patient (AOR = 4.38, 95% CI [2.46–7.80]), and facing ethical dilemma (AOR = 3.56, 95% CI [1.23–10.26]) were significant factors associated with attitude of health professionals towards patient confidentiality. Conclusion The findings of this study revealed that health professionals have a limited attitude towards patient confidentiality but have relatively good knowledge. Providing a continuing medical ethics training package for health workers before joining the hospital and in between the working time could be recommended to enhance health professionals’ knowledge and attitude towards patient confidentiality.
Vanilla Oliveira Alencar, Isabel Regiane Cardoso do Nascimento, Igo Borges dos Santos
et al.
Resumo O objetivo deste artigo é apresentar como crianças hospitalizadas compreendem o conceito de morte, além de suscitar reflexões sobre o tema do óbito na infância. Realizaram-se entrevistas semiestruturadas com crianças de 7 a 12 anos, utilizando-se a contação de história como recurso lúdico para coleta de dados. Os principais resultados apontaram que as crianças estruturam o conceito da morte de forma multidimensional, englobando fatores biológicos, espirituais, socioculturais e emocionais. Inseridas no contexto de hospitalização, elas se aproximam da temática da morte, sensibilizando-se. Assim, demonstram a necessidade de escuta e acolhimento dos sentimentos que emergem quando enfrentam a perda de ente querido ou até mesmo a possibilidade do fim da própria vida.
The idea of using computers to read medical scans was introduced as early as 1966. However, limits to machine learning technology meant progress was slow initially. The Alexnet breakthrough in 2012 sparked new interest in the topic, which resulted in the release of 100s of medical AI solutions on the market. In spite of success for some diseases and modalities, many challenges remain. Research typically focuses on the development of specific applications or techniques, clinical evaluation, or meta analysis of clinical studies or techniques through surveys or challenges. However, limited attention has been given to the development process of improving real world performance. In this tutorial, we address the latter and discuss some techniques to conduct the development process in order to make this as efficient as possible.
How should we think of the preferences of citizens? Whereas self-optimal policy is relatively straightforward to produce, socially optimal policy often requires a more detailed examination. In this paper, we identify an issue that has received far too little attention in welfarist modelling of public policy, which we name the "hidden assumptions" problem. Hidden assumptions can be deceptive because they are not expressed explicitly and the social planner (e.g. a policy maker, a regulator, a legislator) may not give them the critical attention they need. We argue that ethical expertise has a direct role to play in public discourse because it is hard to adopt a position on major issues like public health policy or healthcare prioritisation without making contentious assumptions about population ethics. We then postulate that ethicists are best situated to critically evaluate these hidden assumptions, and can therefore play a vital role in public policy debates.
Trusting the predictions of deep learning models in safety critical settings such as the medical domain is still not a viable option. Distentangled uncertainty quantification in the field of medical imaging has received little attention. In this paper, we study disentangled uncertainties in image to image translation tasks in the medical domain. We compare multiple uncertainty quantification methods, namely Ensembles, Flipout, Dropout, and DropConnect, while using CycleGAN to convert T1-weighted brain MRI scans to T2-weighted brain MRI scans. We further evaluate uncertainty behavior in the presence of out of distribution data (Brain CT and RGB Face Images), showing that epistemic uncertainty can be used to detect out of distribution inputs, which should increase reliability of model outputs.