Abstract Background In the context of medically futile treatment, clinical decision-making often becomes ethically and existentially fraught, especially when physicians and patients navigate the space between prolonging life and preserving its meaning. Existing shared decision-making (SDM) models often rely heavily on empirical rationality, yet overlook the ontological depth of patient experience. Methods Drawing on Heidegger’s concept of being-in-the-world and Gadamer’s fusion of horizons, we conducted an interpretative phenomenological analysis (IPA) of in-depth interviews with a terminal cervical cancer patient and three attending physicians (specialists in cardiology, cardiac surgery, and gynecologic oncology). These philosophical frameworks guided both the analytic lens and the ethical interpretation of SDM practices in contexts of medical futility. Results Our findings reveal that decisions to continue aggressive treatment, even when medically futile, are not mere irrationalities. Rather, they emerge from divergent value orientations and temporal understandings between patients and physicians. A clinically “correct” decision may be ethically inadequate if it fails to integrate the patient’s lived horizon. Conclusions We propose a hermeneutic framework for SDM that supplements the evidence-based model with three core steps: attunement to the patient’s existential situation, fusion of horizons between patient and physician, and respect for irreducible differences. This approach allows for ethically grounded decisions that honor both medical expertise and the patient’s being-in-the-world. Trial registration Not applicable.
Sajjad Azmand, Sulmaz Ghahramani, Marziyeh Doostfatemeh
et al.
Abstract Background To reduce potential health disparities, it is critical to recognize health determinants among socioeconomically disadvantaged women. Therefore, we aimed to investigate the determinants of self-rated health in socioeconomically disadvantaged women supported by a Relief Foundation (RF). Method This cross-sectional study was conducted on women in Iran who were supported by a RF as an aided institute. We collected demographic and socioeconomic data, as well as information on physical, mental, and social health and self-rated health status. Data analysis was performed by random forest, classification and regression tree (CART) techniques, and gamma regression. Results The mean age of the 556 included disadvantaged women was 42.8 ± 12.4 years, and the mean self-rated health status was 66.5. Physical health was the most important factor affecting self-rated health. In disadvantaged women with physical problem, nonacademic and academic educated had significantly greater health perceptions than illiterate individuals (1.267, 95% CI: 1.106, 1.451) and (1.666, 95% CI: 1.251, 2.217) respectively. Also, anxiety and stress were both significant predictors of self-rated health status in disadvantaged women with physical health problem (0.765, 95% CI: 0.653, 0.896), and (0.872, 95% CI: 0.762, 0.999) respectively. Conclusion The study of disadvantaged women revealed a significant influence of physical health on their overall sense of well-being. The findings suggest that education and anxiety have impacts on self-rated health of both diseased and healthy women. To improve the well-being of disadvantaged women, providing accessible physical and mental health support, along with expanding educational opportunities, would be beneficial.
María del Carmen Hernández Cediel, Ana Casaux Huertas, Francisco Javier Rivas Flores
et al.
Antecedentes: La Consulta de Ética Clínica (CEC) es un servicio proporcionado por una persona o grupo de personas a pacientes, familiares o profesionales ante los problemas éticos que aparecen en el ámbito sanitario. Puede ser dependiente de los Comités de Ética Asistencial (CEAS) o independiente. Objetivo: Conocer la situación actual de la CEC en España. Método: Estudio cuantitativo descriptivo transversal mediante cuestionario online sobre la situación actual de la CEC a nivel nacional.Resultados: Se identificaron 23 CEC establecidas y 4 en proceso de implantación en España. Las fechas de implementación abarcan desde 1986 hasta 2023, siendo el periodo comprendido entre 2020 y 2024 en el que han surgido más CEC. La forma específica más utilizada por los centros para denominar a la CEC es “Consultas realizadas al CEAS” (50%), el 86,4% son dependientes de los CEAS. De media se han registrado 7,5 consultas a la CEC en el 2021 y 7,3 en el 2022, con una desviación estándar de 9,1 y 8,2 respectivamente. Conclusiones: existe una tendencia al alza de la CEC en España, aunque su prevalencia es todavía menor que en países extranjeros. La CEC puede convertirse en un servicio valioso, para dar respuesta a los problemas éticos en el ámbito sanitario, en colaboración con los CEAS. Para potenciar este servicio se requiere unificar terminología y modelos de implementación.
Jurisprudence. Philosophy and theory of law, Medical philosophy. Medical ethics
This study aims to grasp the current status and future directions of chronic disease prevention research for people with disabilities. Using data from CNKI, Wanfang Database, and the Web of Science Core Collection, bibliometric analysis and visualization tools such as VOSviewer were employed to generate keyword clustering maps and other analytic outputs. Results reveal a significant gap in publication volume between domestic and international research, with the latter's content expanding beyond disease treatment to increasingly incorporate health humanities. Future chronic disease prevention for people with disabilities in China should move beyond cross-sectional studies and adopt a holistic, life-course health perspective. Emphasis should be placed on enhancing intrinsic motivation among disabled individuals to foster proactive health behaviors. Furthermore, tailored health guidelines for people with disabilities should be developed to improve practicality, highlighting the integration of health humanities from a human-centered perspective.
The clinical penetration of brain-computer interface (BCI) technology has touched the metaphysical foundation of human existence, giving rise to the philosophical framework centered on the triad of "transformations of subjectivity-deconstruction of consciousness-evolution of existence". At the subjectivity level, BCI promotes the transformation of medical subject from "biological individual" to "techno-biological composite subject"; In the dimension of consciousness, neural decoding technology can translate consciousness from "subjective experience" to "digital accessibility". From the perspective of existence, the embodied technology drives the evolution of physical existence to "digital embodiment", and constructs a new medical paradigm of human–machine symbiosis. This study ultimately proposes a three-dimensional governance framework of "bioethics–neurorights-symbiotic ethics", which provides interdisciplinary theoretical support for the clinical regulation and philosophical interpretation of BCI technology.
In medical data analysis, extracting deep insights from complex, multi-modal datasets is essential for improving patient care, increasing diagnostic accuracy, and optimizing healthcare operations. However, there is currently a lack of high-quality datasets specifically designed to evaluate the ability of large multi-modal models (LMMs) to discover medical insights. In this paper, we introduce MedInsightBench, the first benchmark that comprises 332 carefully curated medical cases, each annotated with thoughtfully designed insights. This benchmark is intended to evaluate the ability of LMMs and agent frameworks to analyze multi-modal medical image data, including posing relevant questions, interpreting complex findings, and synthesizing actionable insights and recommendations. Our analysis indicates that existing LMMs exhibit limited performance on MedInsightBench, which is primarily attributed to their challenges in extracting multi-step, deep insights and the absence of medical expertise. Therefore, we propose MedInsightAgent, an automated agent framework for medical data analysis, composed of three modules: Visual Root Finder, Analytical Insight Agent, and Follow-up Question Composer. Experiments on MedInsightBench highlight pervasive challenges and demonstrate that MedInsightAgent can improve the performance of general LMMs in medical data insight discovery.
Large language models (LLMs), particularly those with reasoning capabilities, have rapidly advanced in recent years, demonstrating significant potential across a wide range of applications. However, their deployment in healthcare, especially in disease reasoning tasks, is hindered by the challenge of acquiring expert-level cognitive data. In this paper, we introduce Citrus, a medical language model that bridges the gap between clinical expertise and AI reasoning by emulating the cognitive processes of medical experts. The model is trained on a large corpus of simulated expert disease reasoning data, synthesized using a novel approach that accurately captures the decision-making pathways of clinicians. This approach enables Citrus to better simulate the complex reasoning processes involved in diagnosing and treating medical conditions. To further address the lack of publicly available datasets for medical reasoning tasks, we release the last-stage training data, including a custom-built medical diagnostic dialogue dataset. This open-source contribution aims to support further research and development in the field. Evaluations using authoritative benchmarks such as MedQA, covering tasks in medical reasoning and language understanding, show that Citrus achieves superior performance compared to other models of similar size. These results highlight Citrus potential to significantly enhance medical decision support systems, providing a more accurate and efficient tool for clinical decision-making.
Ramon Cases Solé, Giorgia Sebastiani, David Varillas-Delgado
et al.
El objetivo del presente artículo es realizar una aproximación a la situación de la osteopatía pediátrica en España y proponer la creación de una mesa de diálogo inter y multidisciplinar que permita avanzar en su regulación y ordenación profesional. Actualmente no existe un estándar académico que regule este tipo de formación en nuestro país. La ausencia de regulación predispone a que haya una gran variedad de perfiles profesionales, con formaciones académicas dispares, practicando la osteopatía. Este hecho puede tener implicaciones sobre la seguridad y calidad de la atención que reciben los/las pacientes/usuarios/as, principalmente los grupos vulnerables y dependientes de la población, como son los/las menores de edad. La creación de una mesa de diálogo también permitiría clarificar la práctica profesional de la osteopatía pediátrica y cuál es su bien interno para con la sociedad española. El papel de la bioética puede ser importante a la hora de integrar diferentes voces.
Medical philosophy. Medical ethics, Business ethics
Carlos Alberto Román Collazo, Jonathan Brenner, Diego Andrade Campoverde
El uso de la Inteligencia artificial (IA) en la Medicina de laboratorio (ML) ha provocado un salto cualitativo en el diagnóstico de enfermedades que aquejan al ser humano. El desarrollo de robots para la medición, cálculo y predicción ha aumentado la confiabilidad, validez y reproducibilidad de las pruebas diagnósticas con IA, induciendo a una fácil elección de dicha tecnología en el laboratorio clínico. Sin embargo, la IA en la ML entraña una serie de reflexiones éticas que deben considerarse. La incipiente tecnología en desarrollo, la presencia de sesgos cognitivos en los algoritmos y datos, la incertidumbre del funcionamiento del robot, las limitaciones tecnológicas, la amenaza a la privacidad y la ausencia de un marco legal abren conflictos éticos que laceran la equidad, la seguridad y la autonomía del hombre. El imperativo tecnológico de la IA en la ML no debe superar la responsabilidad, ni atentar contra la dignidad de la persona.
In May 2023, The Guardian announced that babies had been born through mitochondrial replacement therapy (MRT). MRT and its ethical and legal implications have been discussed in the media for over a decade. These discussions have been examined by social scientists and communication scholars. In this article, we seek to determine whether and, if so, how social representations have changed since this announcement. Using thematic analysis and social representations theory, we studied a corpus of 70 English language newspaper articles. Results show three thematic dichotomies: (1) moderation vs. sensationalism; (2) ontologising vs. de-ontologising MRT; and (3) using metaphors for persuasion vs. explanation. The societal concern representation largely dominated reporting around 2015 and the hope and opportunity representation was prominent in current reporting. We argue that the hope representation may facilitate greater patient and public acceptance of MRT but that it may also limit awareness, understanding and discussion of its possible risks and limitations.
This study presents Medical Vision Generalist (MVG), the first foundation model capable of handling various medical imaging tasks -- such as cross-modal synthesis, image segmentation, denoising, and inpainting -- within a unified image-to-image generation framework. Specifically, MVG employs an in-context generation strategy that standardizes the handling of inputs and outputs as images. By treating these tasks as an image generation process conditioned on prompt image-label pairs and input images, this approach enables a flexible unification of various tasks, even those spanning different modalities and datasets. To capitalize on both local and global context, we design a hybrid method combining masked image modeling with autoregressive training for conditional image generation. This hybrid approach yields the most robust performance across all involved medical imaging tasks. To rigorously evaluate MVG's capabilities, we curated the first comprehensive generalist medical vision benchmark, comprising 13 datasets and spanning four imaging modalities (CT, MRI, X-ray, and micro-ultrasound). Our results consistently establish MVG's superior performance, outperforming existing vision generalists, such as Painter and LVM. Furthermore, MVG exhibits strong scalability, with its performance demonstrably improving when trained on a more diverse set of tasks, and can be effectively adapted to unseen datasets with only minimal task-specific samples. The code is available at \url{https://github.com/OliverRensu/MVG}.
Vinaytosh Mishra, Kishu Gupta, Deepika Saxena
et al.
Electronic Health Records (EHR) are crucial for the success of digital healthcare, with a focus on putting consumers at the center of this transformation. However, the digitalization of healthcare records brings along security and privacy risks for personal data. The major concern is that different countries have varying standards for the security and privacy of medical data. This paper proposed a novel and comprehensive framework to standardize these rules globally, bringing them together on a common platform. To support this proposal, the study reviews existing literature to understand the research interest in this issue. It also examines six key laws and standards related to security and privacy, identifying twenty concepts. The proposed framework utilized K-means clustering to categorize these concepts and identify five key factors. Finally, an Ordinal Priority Approach is applied to determine the preferred implementation of these factors in the context of EHRs. The proposed study provides a descriptive then prescriptive framework for the implementation of privacy and security in the context of electronic health records. Therefore, the findings of the proposed framework are useful for professionals and policymakers in improving the security and privacy associated with EHRs.
With the continuous advancement of technology, artificial intelligence has significantly impacted various fields, particularly healthcare. Generative models, a key AI technology, have revolutionized medical image generation, data analysis, and diagnosis. This article explores their application in intelligent medical devices. Generative models enhance diagnostic speed and accuracy, improving medical service quality and efficiency while reducing equipment costs. These models show great promise in medical image generation, data analysis, and diagnosis. Additionally, integrating generative models with IoT technology facilitates real-time data analysis and predictions, offering smarter healthcare services and aiding in telemedicine. Challenges include computational demands, ethical concerns, and scenario-specific limitations.
Biomedical data is inherently multimodal, consisting of electronic health records, medical imaging, digital pathology, genome sequencing, wearable sensors, and more. The application of artificial intelligence tools to these multifaceted sensing technologies has the potential to revolutionize the prognosis, diagnosis, and management of human health and disease. However, current approaches to biomedical AI typically only train and evaluate with one or a small set of medical modalities and tasks. This limitation hampers the development of comprehensive tools that can leverage the rich interconnected information across many heterogeneous biomedical sensors. To address this challenge, we present MultiMed, a benchmark designed to evaluate and enable large-scale learning across a wide spectrum of medical modalities and tasks. MultiMed consists of 2.56 million samples across ten medical modalities such as medical reports, pathology, genomics, and protein data, and is structured into eleven challenging tasks, including disease prognosis, protein structure prediction, and medical question answering. Using MultiMed, we conduct comprehensive experiments benchmarking state-of-the-art unimodal, multimodal, and multitask models. Our analysis highlights the advantages of training large-scale medical models across many related modalities and tasks. Moreover, MultiMed enables studies of generalization across related medical concepts, robustness to real-world noisy data and distribution shifts, and novel modality combinations to improve prediction performance. MultiMed will be publicly available and regularly updated and welcomes inputs from the community.
With the increasing application of large language models (LLMs) in the medical domain, evaluating these models' performance using benchmark datasets has become crucial. This paper presents a comprehensive survey of various benchmark datasets employed in medical LLM tasks. These datasets span multiple modalities including text, image, and multimodal benchmarks, focusing on different aspects of medical knowledge such as electronic health records (EHRs), doctor-patient dialogues, medical question-answering, and medical image captioning. The survey categorizes the datasets by modality, discussing their significance, data structure, and impact on the development of LLMs for clinical tasks such as diagnosis, report generation, and predictive decision support. Key benchmarks include MIMIC-III, MIMIC-IV, BioASQ, PubMedQA, and CheXpert, which have facilitated advancements in tasks like medical report generation, clinical summarization, and synthetic data generation. The paper summarizes the challenges and opportunities in leveraging these benchmarks for advancing multimodal medical intelligence, emphasizing the need for datasets with a greater degree of language diversity, structured omics data, and innovative approaches to synthesis. This work also provides a foundation for future research in the application of LLMs in medicine, contributing to the evolving field of medical artificial intelligence.
Jan Domaradzki, Justyna Czekajewska, Dariusz Walkowiak
Abstract Background Over the last few decades biobanks have been recognised as institutions that may revolutionise biomedical research and the development of personalised medicine. Poland, however, still lacks clear regulations regarding the running of biobanks and the conducting of biomedical research. While the awareness of the general public regarding biobanks is low, healthcare professions and medical students also lack basic knowledge regarding biobanks, and such ignorance may affect their support for biobanks. Methods This study is aimed at assessing the knowledge and attitudes of future healthcare professionals towards the donation of human biological material for research purposes and is based on a sample of 865 Polish medical students at Poznań University of Medical Sciences. Results This research has shown that the awareness of medical students’ regarding biobanks is low. It has also shown that while the majority of future healthcare professionals enrolled in this study supported the idea of biobank research and declared themselves willing to donate, still many students felt ambivalent about the biobanking of human biological material for research purposes and expressed concerns over biobanking research. While the primarily motivation to participate in biobank research was the desire to help advance science and to develop innovative therapies, the most common reason for a refusal was the fear that the government, insurance companies or employers, might have access to the samples. Concerns over unethical use of samples and data safety were also prevalent. More than half of students opted for a study-specific model of consent and only a few opted for broad consent. Conclusions This research suggests that a lack of knowledge about biobanks, their role and activities may affect medical students’ support for biobanks and their active participation in the collection and management of biospecimens for research purposes. Since in the future medical, nursing and pharmacy students will be involved in the collection, storage, testing and analysis of biospecimens from their patients, medical students in all professional fields should be trained regarding the concept, purposes and operational procedures of biobanks, as well as the ethical, legal and social implications of biobank research.
Various human rights issues arise from the intersection of adolescent motherhood and HIV. While health rights may be the most obvious means by which to address such issues through policy development and legislative means, the right to health is not the only human right that may provide recourse or relief in this regard. This article considers an unexplored avenue of approaching such issues through reliance on the right to enjoy the benefits of scientific progress. The International Covenant on Economic, Social and Cultural Rights provides for the ‘right to science’ in article 15(1)(b) and more recently, as elaborated on in General Comment no. 25 of 2020. This article considers how this right can be relied upon to address issues pertaining to adolescent motherhood and HIV. Precedent from a Venezuelan Supreme Court decision is considered, as well as the normative content of the right to enjoy the benefits of scientific progress. This may be another legal means by which to hold states accountable for the health of young mothers and their children, especially as new practices, medicines and treatments emerge regarding HIV.
Nafisa Labiba Ishrat Huda, Angona Biswas, MD Abdullah Al Nasim
et al.
Invariant scattering transform introduces new area of research that merges the signal processing with deep learning for computer vision. Nowadays, Deep Learning algorithms are able to solve a variety of problems in medical sector. Medical images are used to detect diseases brain cancer or tumor, Alzheimer's disease, breast cancer, Parkinson's disease and many others. During pandemic back in 2020, machine learning and deep learning has played a critical role to detect COVID-19 which included mutation analysis, prediction, diagnosis and decision making. Medical images like X-ray, MRI known as magnetic resonance imaging, CT scans are used for detecting diseases. There is another method in deep learning for medical imaging which is scattering transform. It builds useful signal representation for image classification. It is a wavelet technique; which is impactful for medical image classification problems. This research article discusses scattering transform as the efficient system for medical image analysis where it's figured by scattering the signal information implemented in a deep convolutional network. A step by step case study is manifested at this research work.
Using natural language processing (NLP) technologies to develop medical chatbots makes the diagnosis of the patient more convenient and efficient, which is a typical application in healthcare AI. Because of its importance, lots of research have been come out. Recently, the neural generative models have shown their impressive ability as the core of chatbot, while it cannot scale well when directly applied to medical conversation due to the lack of medical-specific knowledge. To address the limitation, a scalable Medical Knowledge Assisted mechanism, MKA, is proposed in this paper. The mechanism aims to assist general neural generative models to achieve better performance on the medical conversation task. The medical-specific knowledge graph is designed within the mechanism, which contains 6 types of medical-related information, including department, drug, check, symptom, disease, food. Besides, the specific token concatenation policy is defined to effectively inject medical information into the input data. Evaluation of our method is carried out on two typical medical datasets, MedDG and MedDialog-CN. The evaluation results demonstrate that models combined with our mechanism outperform original methods in multiple automatic evaluation metrics. Besides, MKA-Bert-GPT achieves state-of-the-art performance. The open-sourced codes are public: https://github.com/LIANGKE23/Knowledge_Assisted_Medical_Dialogue_Generation_Mechanism
Image registration is a fundamental requirement for medical image analysis. Deep registration methods based on deep learning have been widely recognized for their capabilities to perform fast end-to-end registration. Many deep registration methods achieved state-of-the-art performance by performing coarse-to-fine registration, where multiple registration steps were iterated with cascaded networks. Recently, Non-Iterative Coarse-to-finE (NICE) registration methods have been proposed to perform coarse-to-fine registration in a single network and showed advantages in both registration accuracy and runtime. However, existing NICE registration methods mainly focus on deformable registration, while affine registration, a common prerequisite, is still reliant on time-consuming traditional optimization-based methods or extra affine registration networks. In addition, existing NICE registration methods are limited by the intrinsic locality of convolution operations. Transformers may address this limitation for their capabilities to capture long-range dependency, but the benefits of using transformers for NICE registration have not been explored. In this study, we propose a Non-Iterative Coarse-to-finE Transformer network (NICE-Trans) for image registration. Our NICE-Trans is the first deep registration method that (i) performs joint affine and deformable coarse-to-fine registration within a single network, and (ii) embeds transformers into a NICE registration framework to model long-range relevance between images. Extensive experiments with seven public datasets show that our NICE-Trans outperforms state-of-the-art registration methods on both registration accuracy and runtime.