Hasil untuk "Medical philosophy. Medical ethics"

Zhiyao Ren, Yibing Zhan, Siyuan Liang et al.

Large-scale language models (LLMs) often offer clinical judgments based on incomplete information, increasing the risk of misdiagnosis. Existing studies have primarily evaluated confidence in single-turn, static settings, overlooking the coupling between confidence and correctness as clinical evidence accumulates during real consultations, which limits their support for reliable decision-making. We propose the first benchmark for assessing confidence in multi-turn interaction during realistic medical consultations. Our benchmark unifies three types of medical data for open-ended diagnostic generation and introduces an information sufficiency gradient to characterize the confidence-correctness dynamics as evidence increases. We implement and compare 27 representative methods on this benchmark; two key insights emerge: (1) medical data amplifies the inherent limitations of token-level and consistency-level confidence methods, and (2) medical reasoning must be evaluated for both diagnostic accuracy and information completeness. Based on these insights, we present MedConf, an evidence-grounded linguistic self-assessment framework that constructs symptom profiles via retrieval-augmented generation, aligns patient information with supporting, missing, and contradictory relations, and aggregates them into an interpretable confidence estimate through weighted integration. Across two LLMs and three medical datasets, MedConf consistently outperforms state-of-the-art methods on both AUROC and Pearson correlation coefficient metrics, maintaining stable performance under conditions of information insufficiency and multimorbidity. These results demonstrate that information adequacy is a key determinant of credible medical confidence modeling, providing a new pathway toward building more reliable and interpretable large medical models.

Yiming GOU, Zhimin FANG

Shared decision-making (SDM) centers on the "person with the illness" as the subject of clinical decisions, upholds "informed consent" as its guiding principle, and adopts "high-quality joint participation" as its clinical practice method. This aligns well with the holistic approach of psychosomatic medicine, which emphasizes the integration of physiological, psychological, and social information in patient care. Empowering psychosomatic medicine through SDM can deepen patients' understanding of mind-body interaction therapies, boost their confidence in overcoming illness, and ultimately support their journey from psychological well-being to physical health. However, practical challenges in implementing SDM continue to hinder the development of psychosomatic medicine. To address these issues, it is essential to adopt a multi-stakeholder collaborative approach that focuses on physician-led guidance in decision-making, effective patient participation, and institutional support for SDM mechanisms within hospitals. These efforts can help optimize SDM and enhance the practice of psychosomatic medicine.

Xiuqiao Yang, Hong Lin, Shuning Liu et al.

Abstract Background This study aims to identify current deficiencies in the protection of human subjects participating in clinical trials in China and propose strategies for safeguarding their rights. Methods We conducted a comprehensive literature review on the protection of human subjects in clinical trials and gathered insights from experts and scholars among stakeholders. The Delphi expert consultation method was used to analyze and summarize the shortcomings in China’s regulatory framework for human subject protection and to develop strategies for improvement. Two rounds of surveys were conducted with experts from research institutions, ethics committees, regulatory agencies, sponsors, and Site Management Organizations (SMOs). The top three issues and proposed solutions were discussed and addressed based on expert consensus. Results A total of 30 articles were reviewed, leading to the identification of 46 distinct issues, which were categorized into three groups: compensation, privacy, and informed consent. Sixteen respondents completed both rounds of the survey, which included 56 questions (10 new questions were proposed in the first round). Compensation-related issues included the absence of a comprehensive “mandatory insurance system,” incomplete insurance systems and compensation procedures, and the lack of clear differentiation between liability for clinical trial infringements and medical harm. Privacy concerns involved inadequate regulations, privacy risks associated with third-party recruitment, and data entry by clinical research coordinators. Problems related to informed consent were primarily due to inadequate awareness and capacity among investigators, a lack of oversight by ethics committees, and the absence of legal standards for broad informed consent. Conclusions By improving the details of compensation rights, privacy protection, and informed consent in regulations, all parties involved in clinical trials can be encouraged to more effectively protect the rights and interests of subjects.

Qinyue Zheng, Salman Abdullah, Sam Rawal et al.

LLMs are bound to transform healthcare with advanced decision support and flexible chat assistants. However, LLMs are prone to generate inaccurate medical content. To ground LLMs in high-quality medical knowledge, LLMs have been equipped with external knowledge via RAG, where unstructured medical knowledge is split into small text chunks that can be selectively retrieved and integrated into the LLMs context. Yet, existing RAG pipelines rely on raw, unstructured medical text, which can be noisy, uncurated and difficult for LLMs to effectively leverage. Systematic approaches to organize medical knowledge to best surface it to LLMs are generally lacking. To address these challenges, we introduce MIRIAD, a large-scale, curated corpus of 5,821,948 medical QA pairs, each rephrased from and grounded in a passage from peer-reviewed medical literature using a semi-automated pipeline combining LLM generation, filtering, grounding, and human annotation. Unlike prior medical corpora, which rely on unstructured text, MIRIAD encapsulates web-scale medical knowledge in an operationalized query-response format, which enables more targeted retrieval. Experiments on challenging medical QA benchmarks show that augmenting LLMs with MIRIAD improves accuracy up to 6.7% compared to unstructured RAG baselines with the same source corpus and with the same amount of retrieved text. Moreover, MIRIAD improved the ability of LLMs to detect medical hallucinations by 22.5 to 37% (increase in F1 score). We further introduce MIRIAD-Atlas, an interactive map of MIRIAD spanning 56 medical disciplines, enabling clinical users to visually explore, search, and refine medical knowledge. MIRIAD promises to unlock a wealth of down-stream applications, including medical information retrievers, enhanced RAG applications, and knowledge-grounded chat interfaces, which ultimately enables more reliable LLM applications in healthcare.

Adrien Bazoge

This work introduces MediQAl, a French medical question answering dataset designed to evaluate the capabilities of language models in factual medical recall and reasoning over real-world clinical scenarios. MediQAl contains 32,603 questions sourced from French medical examinations across 41 medical subjects. The dataset includes three tasks: (i) Multiple-Choice Question with Unique answer, (ii) Multiple-Choice Question with Multiple answer, and (iii) Open-Ended Question with Short-Answer. Each question is labeled as Understanding or Reasoning, enabling a detailed analysis of models' cognitive capabilities. We validate the MediQAl dataset through extensive evaluation with 14 large language models, including recent reasoning-augmented models, and observe a significant performance gap between factual recall and reasoning tasks. Our evaluation provides a comprehensive benchmark for assessing language models' performance on French medical question answering, addressing a crucial gap in multilingual resources for the medical domain.

Xiaoke Huang, Juncheng Wu, Hui Liu et al.

Test-time scaling has emerged as a powerful technique for enhancing the reasoning capabilities of large language models. However, its effectiveness in medical reasoning remains uncertain, as the medical domain fundamentally differs from mathematical tasks in terms of knowledge representation and decision-making processes. In this paper, we provide the first comprehensive investigation of test-time scaling for medical reasoning and present m1, a simple yet effective approach that increases a model's medical reasoning capability at inference. Our evaluation across diverse medical tasks demonstrates that test-time scaling consistently enhances medical reasoning, enabling lightweight fine-tuned models under 10B parameters to establish new state-of-the-art performance, while our 32B model rivals previous 70B-scale medical LLMs. However, we identify an optimal reasoning token budget of approximately 4K, beyond which performance may degrade due to overthinking. Budget forcing, which extends test-time computation through iterative prompts, helps models double-check answers but does not necessarily improve the overall medical QA performance and, in some cases, even introduces errors into previously correct responses. Our case-by-case analysis identifies insufficient medical knowledge as a key bottleneck that prevents further performance gains through test-time scaling. We find that increasing data scale, improving data quality, and expanding model capacity consistently enhance medical knowledge grounding, enabling continued performance improvements, particularly on challenging medical benchmarks where smaller models reach saturation. These findings underscore fundamental differences between medical and mathematical reasoning in LLMs, highlighting that enriched medical knowledge, other than increased reasoning depth alone, is essential for realizing the benefits of test-time scaling.

Jingkun Yue, Siqi Zhang, Zinan Jia et al.

Visual grounding is essential for precise perception and reasoning in multimodal large language models (MLLMs), especially in medical imaging domains. While existing medical visual grounding benchmarks primarily focus on single-image scenarios, real-world clinical applications often involve sequential images, where accurate lesion localization across different modalities and temporal tracking of disease progression (e.g., pre- vs. post-treatment comparison) require fine-grained cross-image semantic alignment and context-aware reasoning. To remedy the underrepresentation of image sequences in existing medical visual grounding benchmarks, we propose MedSG-Bench, the first benchmark tailored for Medical Image Sequences Grounding. It comprises eight VQA-style tasks, formulated into two paradigms of the grounding tasks, including 1) Image Difference Grounding, which focuses on detecting change regions across images, and 2) Image Consistency Grounding, which emphasizes detection of consistent or shared semantics across sequential images. MedSG-Bench covers 76 public datasets, 10 medical imaging modalities, and a wide spectrum of anatomical structures and diseases, totaling 9,630 question-answer pairs. We benchmark both general-purpose MLLMs (e.g., Qwen2.5-VL) and medical-domain specialized MLLMs (e.g., HuatuoGPT-vision), observing that even the advanced models exhibit substantial limitations in medical sequential grounding tasks. To advance this field, we construct MedSG-188K, a large-scale instruction-tuning dataset tailored for sequential visual grounding, and further develop MedSeq-Grounder, an MLLM designed to facilitate future research on fine-grained understanding across medical sequential images. The benchmark, dataset, and model are available at https://huggingface.co/MedSG-Bench

Sammie N. G. Jansen, Bart A. Kamphorst, Bob C. Mulder et al.

Abstract Background Scientific and technological advancements in mapping and understanding the interrelated pathways through which biological and environmental exposures affect disease development create new possibilities for detecting disease risk factors. Early detection of such risk factors may help prevent disease onset or moderate the disease course, thereby decreasing associated disease burden, morbidity, and mortality. However, the ethical implications of screening for disease risk factors are unclear and the current literature provides a fragmented and case-by-case picture. Methods To identify key ethical considerations arising from the early detection of disease risk factors, we performed a systematic scoping review. The Scopus, Embase, and Philosopher’s Index databases were searched for peer-reviewed, academic records, which were included if they were written in English or Dutch and concerned the ethics of (1) early detection of (2) disease risk factors for (3) disease caused by environmental factors or gene-environment interactions. All records were reviewed independently by at least two researchers. Results After screening 2034 titles and abstracts, and 112 full papers, 55 articles were included in the thematic synthesis of the results. We identified eight common ethical themes: (1) Reliability and uncertainty in early detection, (2) autonomy, (3) privacy, (4) beneficence and non-maleficence, (5) downstream burdens on others, (6) responsibility, (7) justice, and (8) medicalization and conceptual disruption. We identified several gaps in the literature, including a relative scarcity of research on ethical considerations associated with environmental preventive health interventions, a dearth of practical suggestions on how to address expressed concerns about overestimating health capacities, and a lack of insights into preventing undue attribution of health responsibility to individuals. Conclusions The ethical concerns arising with the early detection of risk factors are often interrelated and complex. Comprehensive ethical analyses are needed that are better embedded in normative frameworks and also assess and weigh the expected benefits of early risk factor detection. Such research is necessary for developing and implementing responsible and fair preventive health policies.

Anubhav Gupta, Islam Osman, Mohamed S. Shehata et al.

Medical imaging tasks are very challenging due to the lack of publicly available labeled datasets. Hence, it is difficult to achieve high performance with existing deep-learning models as they require a massive labeled dataset to be trained effectively. An alternative solution is to use pre-trained models and fine-tune them using the medical imaging dataset. However, all existing models are pre-trained using natural images, which is a completely different domain from that of medical imaging, which leads to poor performance due to domain shift. To overcome these problems, we propose a large-scale unlabeled dataset of medical images and a backbone pre-trained using the proposed dataset with a self-supervised learning technique called Masked autoencoder. This backbone can be used as a pre-trained model for any medical imaging task, as it is trained to learn a visual representation of different types of medical images. To evaluate the performance of the proposed backbone, we used four different medical imaging tasks. The results are compared with existing pre-trained models. These experiments show the superiority of our proposed backbone in medical imaging tasks.

Yicheng Wu, Xiangde Luo, Zhe Xu et al.

Annotation ambiguity due to inherent data uncertainties such as blurred boundaries in medical scans and different observer expertise and preferences has become a major obstacle for training deep-learning based medical image segmentation models. To address it, the common practice is to gather multiple annotations from different experts, leading to the setting of multi-rater medical image segmentation. Existing works aim to either merge different annotations into the "groundtruth" that is often unattainable in numerous medical contexts, or generate diverse results, or produce personalized results corresponding to individual expert raters. Here, we bring up a more ambitious goal for multi-rater medical image segmentation, i.e., obtaining both diversified and personalized results. Specifically, we propose a two-stage framework named D-Persona (first Diversification and then Personalization). In Stage I, we exploit multiple given annotations to train a Probabilistic U-Net model, with a bound-constrained loss to improve the prediction diversity. In this way, a common latent space is constructed in Stage I, where different latent codes denote diversified expert opinions. Then, in Stage II, we design multiple attention-based projection heads to adaptively query the corresponding expert prompts from the shared latent space, and then perform the personalized medical image segmentation. We evaluated the proposed model on our in-house Nasopharyngeal Carcinoma dataset and the public lung nodule dataset (i.e., LIDC-IDRI). Extensive experiments demonstrated our D-Persona can provide diversified and personalized results at the same time, achieving new SOTA performance for multi-rater medical image segmentation. Our code will be released at https://github.com/ycwu1997/D-Persona.

Junde Wu, Jiayuan Zhu, Yunli Qi et al.

We introduce a novel graph-based Retrieval-Augmented Generation (RAG) framework specifically designed for the medical domain, called \textbf{MedGraphRAG}, aimed at enhancing Large Language Model (LLM) capabilities for generating evidence-based medical responses, thereby improving safety and reliability when handling private medical data. Graph-based RAG (GraphRAG) leverages LLMs to organize RAG data into graphs, showing strong potential for gaining holistic insights from long-form documents. However, its standard implementation is overly complex for general use and lacks the ability to generate evidence-based responses, limiting its effectiveness in the medical field. To extend the capabilities of GraphRAG to the medical domain, we propose unique Triple Graph Construction and U-Retrieval techniques over it. In our graph construction, we create a triple-linked structure that connects user documents to credible medical sources and controlled vocabularies. In the retrieval process, we propose U-Retrieval which combines Top-down Precise Retrieval with Bottom-up Response Refinement to balance global context awareness with precise indexing. These effort enable both source information retrieval and comprehensive response generation. Our approach is validated on 9 medical Q\&A benchmarks, 2 health fact-checking benchmarks, and one collected dataset testing long-form generation. The results show that MedGraphRAG consistently outperforms state-of-the-art models across all benchmarks, while also ensuring that responses include credible source documentation and definitions. Our code is released at: https://github.com/MedicineToken/Medical-Graph-RAG.

Reza Nasirigerdeh, Nader Razmi, Julia A. Schnabel et al.

Machine unlearning is the process of removing the impact of a particular set of training samples from a pretrained model. It aims to fulfill the "right to be forgotten", which grants the individuals such as patients the right to reconsider their contribution in models including medical imaging models. In this study, we evaluate the effectiveness (performance) and computational efficiency of different unlearning algorithms in medical imaging domain. Our evaluations demonstrate that the considered unlearning algorithms perform well on the retain set (samples whose influence on the model is allowed to be retained) and forget set (samples whose contribution to the model should be eliminated), and show no bias against male or female samples. They, however, adversely impact the generalization of the model, especially for larger forget set sizes. Moreover, they might be biased against easy or hard samples, and need additional computational overhead for hyper-parameter tuning. In conclusion, machine unlearning seems promising for medical imaging, but the existing unlearning algorithms still needs further improvements to become more practical for medical applications.

Asifullah Khan, Zunaira Rauf, Abdul Rehman Khan et al.

Medical image segmentation plays a crucial role in various healthcare applications, enabling accurate diagnosis, treatment planning, and disease monitoring. Traditionally, convolutional neural networks (CNNs) dominated this domain, excelling at local feature extraction. However, their limitations in capturing long-range dependencies across image regions pose challenges for segmenting complex, interconnected structures often encountered in medical data. In recent years, Vision Transformers (ViTs) have emerged as a promising technique for addressing the challenges in medical image segmentation. Their multi-scale attention mechanism enables effective modeling of long-range dependencies between distant structures, crucial for segmenting organs or lesions spanning the image. Additionally, ViTs' ability to discern subtle pattern heterogeneity allows for the precise delineation of intricate boundaries and edges, a critical aspect of accurate medical image segmentation. However, they do lack image-related inductive bias and translational invariance, potentially impacting their performance. Recently, researchers have come up with various ViT-based approaches that incorporate CNNs in their architectures, known as Hybrid Vision Transformers (HVTs) to capture local correlation in addition to the global information in the images. This survey paper provides a detailed review of the recent advancements in ViTs and HVTs for medical image segmentation. Along with the categorization of ViT and HVT-based medical image segmentation approaches, we also present a detailed overview of their real-time applications in several medical image modalities. This survey may serve as a valuable resource for researchers, healthcare practitioners, and students in understanding the state-of-the-art approaches for ViT-based medical image segmentation.

Mingyuan Meng, Yuxin Xue, Dagan Feng et al.

Dense prediction is a fundamental requirement for many medical vision tasks such as medical image restoration, registration, and segmentation. The most popular vision model, Convolutional Neural Networks (CNNs), has reached bottlenecks due to the intrinsic locality of convolution operations. Recently, transformers have been widely adopted for dense prediction for their capability to capture long-range visual dependence. However, due to the high computational complexity and large memory consumption of self-attention operations, transformers are usually used at downsampled feature resolutions. Such usage cannot effectively leverage the tissue-level textural information available only at the full image resolution. This textural information is crucial for medical dense prediction as it can differentiate the subtle human anatomy in medical images. In this study, we hypothesize that Multi-layer Perceptrons (MLPs) are superior alternatives to transformers in medical dense prediction where tissue-level details dominate the performance, as MLPs enable long-range dependence at the full image resolution. To validate our hypothesis, we develop a full-resolution hierarchical MLP framework that uses MLPs beginning from the full image resolution. We evaluate this framework with various MLP blocks on a wide range of medical dense prediction tasks including restoration, registration, and segmentation. Extensive experiments on six public well-benchmarked datasets show that, by simply using MLPs at full resolution, our framework outperforms its CNN and transformer counterparts and achieves state-of-the-art performance on various medical dense prediction tasks.

Yang Tan, Mingchen Li, Zijie Huang et al.

Generative large language models (LLMs) have shown great success in various applications, including question-answering (QA) and dialogue systems. However, in specialized domains like traditional Chinese medical QA, these models may perform unsatisfactorily without fine-tuning on domain-specific datasets. To address this, we introduce MedChatZH, a dialogue model designed specifically for traditional Chinese medical QA. Our model is pre-trained on Chinese traditional medical books and fine-tuned with a carefully curated medical instruction dataset. It outperforms several solid baselines on a real-world medical dialogue dataset. We release our model, code, and dataset on https://github.com/tyang816/MedChatZH to facilitate further research in the domain of traditional Chinese medicine and LLMs.

Quan Huu Cap, Atsushi Fukuda, Hitoshi Iyatomi

Medical images are extremely valuable for supporting medical diagnoses. However, in practice, low-quality (LQ) medical images, such as images that are hazy/blurry, have uneven illumination, or are out of focus, among others, are often obtained during data acquisition. This leads to difficulties in the screening and diagnosis of medical diseases. Several generative adversarial networks (GAN)-based image enhancement methods have been proposed and have shown promising results. However, there is a quality-originality trade-off among these methods in the sense that they produce visually pleasing results but lose the ability to preserve originality, especially the structural inputs. Moreover, to our knowledge, there is no objective metric in evaluating the structure preservation of medical image enhancement methods in unsupervised settings due to the unavailability of paired ground-truth data. In this study, we propose a framework for practical unsupervised medical image enhancement that includes (1) a non-reference objective evaluation of structure preservation for medical image enhancement tasks called Laplacian structural similarity index measure (LaSSIM), which is based on SSIM and the Laplacian pyramid, and (2) a novel unsupervised GAN-based method called Laplacian medical image enhancement (LaMEGAN) to support the improvement of both originality and quality from LQ images. The LaSSIM metric does not require clean reference images and has been shown to be superior to SSIM in capturing image structural changes under image degradations, such as strong blurring on different datasets. The experiments demonstrated that our LaMEGAN achieves a satisfactory balance between quality and originality, with robust structure preservation performance while generating compelling visual results with very high image quality scores. The code will be made available at https://github.com/AillisInc/USPMIE.

Dide de Jongh, Emma K. Massey, the VANGUARD consortium et al.

Abstract Organoids are 3D structures grown from pluripotent stem cells derived from human tissue and serve as in vitro miniature models of human organs. Organoids are expected to revolutionize biomedical research and clinical care. However, organoids are not seen as morally neutral. For instance, tissue donors may perceive enduring personal connections with their organoids, setting higher bars for informed consent and patient participation. Also, several organoid sub-types, e.g., brain organoids and human–animal chimeric organoids, have raised controversy. This systematic review provides an overview of ethical discussions as conducted in the scientific literature on organoids. The review covers both research and clinical applications of organoid technology and discusses the topics informed consent, commercialization, personalized medicine, transplantation, brain organoids, chimeras, and gastruloids. It shows that further ethical research is needed especially on organoid transplantation, to help ensure the responsible development and clinical implementation of this technology in this field.

Luis Alberto Sánchez-Alfaro, Jessyca Gómez Henao

Objetivo: analizar los principios bioéticos y las virtudes éticas en la toma de decisiones de fisioterapeutas de una unidad de cuidado intensivo (UCI) en Bogotá. Metodología: estudio cualitativo en el que participaron fisioterapeutas especialistas en cuidado crítico, trabajadores de una uci en Bogotá. Herramientas de recolección de información: observación participante, diario de campo y entrevista semiestructurada. Se realizó análisis categorial de tipo hermenéutico. Resultados: las principales discusiones bioéticas en la uci remiten a los principios de autonomía, beneficencia, no maleficencia y justicia, tangencialmente a los principios de dignidad humana y derechos humanos, igualdad, justicia y equidad, y respeto de la vulnerabilidad humana y la integridad personal. Algunas virtudes expresadas fueron benevolencia, compasión, cuidado y prudencia. Conclusiones: de acuerdo con los participantes, los principios de respeto por la autonomía, beneficencia, no maleficencia y justicia son herramientas para analizar, reflexionar y solucionar conflictos que día a día ocurren en las UCI; la virtud de la prudencia es la más difícil de cultivar, especialmente por el contexto de grave-dad del paciente en la uci o al informar sobre su estado a familiares. En la UCI se debe fomentar la discusión sobre principios bioéticos basados en derechos humanos y en virtudes éticas del personal asistencial, en aras de prácticas humanizadas y de calidad.

Ling Huang, Su Ruan, Thierry Denoeux

The investigation of uncertainty is of major importance in risk-critical applications, such as medical image segmentation. Belief function theory, a formal framework for uncertainty analysis and multiple evidence fusion, has made significant contributions to medical image segmentation, especially since the development of deep learning. In this paper, we provide an introduction to the topic of medical image segmentation methods using belief function theory. We classify the methods according to the fusion step and explain how information with uncertainty or imprecision is modeled and fused with belief function theory. In addition, we discuss the challenges and limitations of present belief function-based medical image segmentation and propose orientations for future research. Future research could investigate both belief function theory and deep learning to achieve more promising and reliable segmentation results.

José Enrique Gómez Álvarez

El objetivo del artículo es mostrar cómo una versión modificada del método de Sgreccia, con las categorías de adaptabilidad y calidad de vida, resulta de utilidad para formular y pensar los problemas de las personas ancianas y adultos mayores en la emergencia del Covid-19. Para lograr lo anterior se retoman los pasos del método bioético: hecho biomédico, valores antropológicos involucrados y respuesta al problema con las categorías de calidad de vida y adaptabilidad. Se analizan los datos empíricos relacionados con la vejez y el Covid-19, mostrando la vulnerabilidad de este grupo frente a la pandemia. Posteriormente, se derivan los deberes éticos que se generan en torno a las personas mayores y ancianas, establecidas por la reflexión y por medio de las categorías. En conclusión, se busca así que las categorías señaladas nos llevan a reconocer la solidaridad y sociabilidad como el eje del equilibrio entre responsabilidad y deber ante los ancianos.