Hasil untuk "Medical philosophy. Medical ethics"

Scott P. McGrath, Katherine K. Kim, Karnjit Johl et al.

The integration of artificial intelligence (AI) into healthcare is accelerating, yet medical education has not kept pace with these technological advancements. This paper synthesizes current knowledge on AI in medical education through a comprehensive analysis of the literature, identifying key competencies, curricular approaches, and implementation strategies. The aim is highlighting the critical need for structured AI education across the medical learning continuum and offer a framework for curriculum development. The findings presented suggest that effective AI education requires longitudinal integration throughout medical training, interdisciplinary collaboration, and balanced attention to both technical fundamentals and clinical applications. This paper serves as a foundation for medical educators seeking to prepare future physicians for an AI-enhanced healthcare environment.

G. Starke, F. Gille, Alberto Termine et al.

Background The integration of artificial intelligence (AI) into health care has become a crucial element in the digital transformation of health systems worldwide. Despite the potential benefits across diverse medical domains, a significant barrier to the successful adoption of AI systems in health care applications remains the prevailing low user trust in these technologies. Crucially, this challenge is exacerbated by the lack of consensus among experts from different disciplines on the definition of trust in AI within the health care sector. Objective We aimed to provide the first consensus-based analysis of trust in AI in health care based on an interdisciplinary panel of experts from different domains. Our findings can be used to address the problem of defining trust in AI in health care applications, fostering the discussion of concrete real-world health care scenarios in which humans interact with AI systems explicitly. Methods We used a combination of framework analysis and a 3-step consensus process involving 18 international experts from the fields of computer science, medicine, philosophy of technology, ethics, and social sciences. Our process consisted of a synchronous phase during an expert workshop where we discussed the notion of trust in AI in health care applications, defined an initial framework of important elements of trust to guide our analysis, and agreed on 5 case studies. This was followed by a 2-step iterative, asynchronous process in which the authors further developed, discussed, and refined notions of trust with respect to these specific cases. Results Our consensus process identified key contextual factors of trust, namely, an AI system’s environment, the actors involved, and framing factors, and analyzed causes and effects of trust in AI in health care. Our findings revealed that certain factors were applicable across all discussed cases yet also pointed to the need for a fine-grained, multidisciplinary analysis bridging human-centered and technology-centered approaches. While regulatory boundaries and technological design features are critical to successful AI implementation in health care, ultimately, communication and positive lived experiences with AI systems will be at the forefront of user trust. Our expert consensus allowed us to formulate concrete recommendations for future research on trust in AI in health care applications. Conclusions This paper advocates for a more refined and nuanced conceptual understanding of trust in the context of AI in health care. By synthesizing insights into commonalities and differences among specific case studies, this paper establishes a foundational basis for future debates and discussions on trusting AI in health care.

Prasad Iyer

No abstract

Shuaibo Li, Zhaohu Xing, Hongqiu Wang et al.

The rapid advancement of generative AI in medical imaging has introduced both significant opportunities and serious challenges, especially the risk that fake medical images could undermine healthcare systems. These synthetic images pose serious risks, such as diagnostic deception, financial fraud, and misinformation. However, research on medical forensics to counter these threats remains limited, and there is a critical lack of comprehensive datasets specifically tailored for this field. Additionally, existing media forensic methods, which are primarily designed for natural or facial images, are inadequate for capturing the distinct characteristics and subtle artifacts of AI-generated medical images. To tackle these challenges, we introduce \textbf{MedForensics}, a large-scale medical forensics dataset encompassing six medical modalities and twelve state-of-the-art medical generative models. We also propose \textbf{DSKI}, a novel \textbf{D}ual-\textbf{S}tage \textbf{K}nowledge \textbf{I}nfusing detector that constructs a vision-language feature space tailored for the detection of AI-generated medical images. DSKI comprises two core components: 1) a cross-domain fine-trace adapter (CDFA) for extracting subtle forgery clues from both spatial and noise domains during training, and 2) a medical forensic retrieval module (MFRM) that boosts detection accuracy through few-shot retrieval during testing. Experimental results demonstrate that DSKI significantly outperforms both existing methods and human experts, achieving superior accuracy across multiple medical modalities.

S M A Sharif, Rizwan Ali Naqvi, Mithun Biswas et al.

Due to numerous hardware shortcomings, medical image acquisition devices are susceptible to producing low-quality (i.e., low contrast, inappropriate brightness, noisy, etc.) images. Regrettably, perceptually degraded images directly impact the diagnosis process and make the decision-making manoeuvre of medical practitioners notably complicated. This study proposes to enhance such low-quality images by incorporating end-to-end learning strategies for accelerating medical image analysis tasks. To the best concern, this is the first work in medical imaging which comprehensively tackles perceptual enhancement, including contrast correction, luminance correction, denoising, etc., with a fully convolutional deep network. The proposed network leverages residual blocks and a residual gating mechanism for diminishing visual artefacts and is guided by a multi-term objective function to perceive the perceptually plausible enhanced images. The practicability of the deep medical image enhancement method has been extensively investigated with sophisticated experiments. The experimental outcomes illustrate that the proposed method could outperform the existing enhancement methods for different medical image modalities by 5.00 to 7.00 dB in peak signal-to-noise ratio (PSNR) metrics and 4.00 to 6.00 in DeltaE metrics. Additionally, the proposed method can drastically improve the medical image analysis tasks' performance and reveal the potentiality of such an enhancement method in real-world applications. Code Available: https://github.com/sharif-apu/DPE_JBHI

Laura Marques Castelhano, Gilberto de Araujo Guimarães, Isabel Baptista

Abstract Background The medical care provided by the physician is an important part of the hospital scene and the action of caring. Assessments of the physician-patient meeting are based on welcome and the physician’s ability to be perceived as hospitable by the patient. By definition, to be hospitable is to have the ability to welcome, care for, reassure, and be courteous, respectful, and trustworthy. This article aims to understand patients’ perceptions of medical care perceived as not hospitable, characterized by a lack of care and welcome, in a hospital environment, based on a complaint’s website. Method The research method used was qualitative analysis and the research strategy was documentary research. The data were collected on a complaints registration platform. The theoretical framework used was the theory of Hospitality. The study selected, coded, and categorized the complaints of 127 patients at the 09 most renowned private hospitals in Brazil. The Voyant tools assisted in the textual analysis of complaints while coding classified them into categories. Results After evaluating the reasons and elements of the complaint, the following was analyzed the encounter characterized as hostile and inhospitable and the attitudes perceived by the patients were grouped into what was defined as “the 4 D’s of non-hospitality”: dehumanization, disregard, dereliction of duty, and disability. Each of the attitudes was characterized by the physician’s behavior and the sensations, emotions, and feelings triggered in the patient. Conclusions Patients’ perception of the not hospitable encounter may be hostile or inhospitable. The physician’s attitude is an important criterion for evaluating the encounter. The physician’s attitude and the form of care are key factors in a culture focused on hospitality in the hospital environment. Hostile and inhospitable attitudes affect the physician-patient relationship and may compromise the patient’s well-being.

Jonathan Adams

Ivone Laurentino dos Santos

O Século XXI chegou e com ele o anúncio de uma “próxima onda”: a Inteligência Artificial (IA). Urge que ampliemos o debate sobre os limites da ciência, com ênfase na criação de mecanismos bioéticos de controle das práticas tecnológicas que se avizinham. Afinal, quais os possíveis impactos da IA nas gerações futuras? Como evitar que as pessoas socialmente desassistidas sejam ainda mais vulnerabilizadas pelo uso da IA? Este estudo, em forma de revisão crítica de literatura, tem como escopo refletir as potencialidades da IA na construção de um mundo com mais justiça e paz social. Conclui-se pela insuficiência de estudos bioéticos da IA, à luz de princípios como dignidade humana, direitos humanos e liberdades fundamentais. Enquanto isso, a contemporaneidade forja subjetividades líquidas, que, de modo similar às máquinas — cada vez mais “humanizadas” —, existem em função de realidades virtuais, em detrimento das demandas e dos problemas concretos das coletividades.

Maram HALİLOĞLU

ez-Zehrâvî, birçok tıbbi başarıya imza atmış önemli bir cerrah olarak bilinir. Özellikle " Kitâbü’t-Tasrîf'" adlı eseri, genel cerrahiyi kapsayan 30 ciltten oluşmaktadır. Bu eserinin son cildi ise cerrahiye özel olup, kemik kırıklarının tedavi ve yönetim yöntemlerine dair önemli bilgiler içermektedir. Bu çalışma, iki ana bölümden oluşmaktadır. Birinci bölümde, ez-Zehrâvî’nin Endülüs'teki yaşamı ve soyunu ele alınmakta; ayrıca "et-Tasrîf" adlı kitabı detaylı bir şekilde incelenmekte ve bu önemli eserin yabancı dillere çevirisi üzerinde durulmaktadır. İkinci bölümde ise kırık tedavisi ile ilgili kısım kapsamlı bir şekilde incelenmiştir. Bu bölümde, ez-Zehrâvî’nin otuzuncu makalesinde belirttiği yaklaşık 23 kırık türü ayrıntılı olarak ele alınmakta ve bu kırıkların tedavisinde kullandığı yöntemler açıklanmaktadır. ez-Zehrâvî, kemiklerin doğru kaynaması için gerekli yöntemleri kapsamlı bir şekilde tanımlamış ve dönemin imkânlarıyla, röntgen ya da radyoloji cihazları olmaksızın kırıkların tedavisi konusunda dikkate değer bir yaratıcılık sergilemiştir. Bu makale, ez-Zehrâvî’nin bir Müslüman tabip olarak kemik kırıkları alanındaki katkılarını ve başarılarını ortaya koymayı amaçlamaktadır.

Majid Movahed Majd, Sahar Hojjati Far, Serajoddin Mahmoudiani

Background and Objectives: One of the dimensions of health in a holistic approach is spiritual health, which affects other dimensions of health and has been emphasized more in recent years than in the past. On the other hand, health literacy has been proposed as a necessity to identify health determinants and use information resources regarding health promotion. Considering the importance of spiritual health and the role of health literacy in maintaining and improving the health of individuals and society, this study was designed and implemented to investigate health literacy, spiritual health, and the relationship between the two among the youth population in Shiraz City, Iran. Methods: The present study was conducted using the cross-sectional analytical method. For this purpose, 400 men and women aged 15 to 29 years living in Shiraz City in 2022 were surveyed through random cluster sampling. The research tools included the Iranian health literacy questionnaire (IHLQ) and the spiritual health questions from the lifestyle questionnaire. The questioning process lasted for two months, and the data were analyzed using mean comparison statistics and linear regression analysis (P<0.005). Results: Health literacy had a direct and significant relationship with the level of spiritual health. As the level of health literacy among individuals increased, so did their level of spiritual health (P<0.005). Age, gender, marriage, and education had no significant effect on spiritual health. Conclusion: Based on the research results regarding the relationship between health literacy and spiritual health, as well as the importance of spiritual health as one of the dimensions of overall health, it seems necessary to consider and promote health literacy This promotion requires the efforts of educational institutions and the media.

Dovile Juodelyte, Enzo Ferrante, Yucheng Lu et al.

Current transferability estimation methods designed for natural image datasets are often suboptimal in medical image classification. These methods primarily focus on estimating the suitability of pre-trained source model features for a target dataset, which can lead to unrealistic predictions, such as suggesting that the target dataset is the best source for itself. To address this, we propose a novel transferability metric that combines feature quality with gradients to evaluate both the suitability and adaptability of source model features for target tasks. We evaluate our approach in two new scenarios: source dataset transferability for medical image classification and cross-domain transferability. Our results show that our method outperforms existing transferability metrics in both settings. We also provide insight into the factors influencing transfer performance in medical image classification, as well as the dynamics of cross-domain transfer from natural to medical images. Additionally, we provide ground-truth transfer performance benchmarking results to encourage further research into transferability estimation for medical image classification. Our code and experiments are available at https://github.com/DovileDo/transferability-in-medical-imaging.

Łukasz Grzybowski, Jakub Pokrywka, Michał Ciesiółka et al.

Large Language Models (LLMs) have demonstrated significant potential in handling specialized tasks, including medical problem-solving. However, most studies predominantly focus on English-language contexts. This study introduces a novel benchmark dataset based on Polish medical licensing and specialization exams (LEK, LDEK, PES) taken by medical doctor candidates and practicing doctors pursuing specialization. The dataset was web-scraped from publicly available resources provided by the Medical Examination Center and the Chief Medical Chamber. It comprises over 24,000 exam questions, including a subset of parallel Polish-English corpora, where the English portion was professionally translated by the examination center for foreign candidates. By creating a structured benchmark from these existing exam questions, we systematically evaluate state-of-the-art LLMs, including general-purpose, domain-specific, and Polish-specific models, and compare their performance against human medical students. Our analysis reveals that while models like GPT-4o achieve near-human performance, significant challenges persist in cross-lingual translation and domain-specific understanding. These findings underscore disparities in model performance across languages and medical specialties, highlighting the limitations and ethical considerations of deploying LLMs in clinical practice.

Jiayuan Zhu, Abdullah Hamdi, Yunli Qi et al.

Medical image segmentation plays a pivotal role in clinical diagnostics and treatment planning, yet existing models often face challenges in generalization and in handling both 2D and 3D data uniformly. In this paper, we introduce Medical SAM 2 (MedSAM-2), a generalized auto-tracking model for universal 2D and 3D medical image segmentation. The core concept is to leverage the Segment Anything Model 2 (SAM2) pipeline to treat all 2D and 3D medical segmentation tasks as a video object tracking problem. To put it into practice, we propose a novel \emph{self-sorting memory bank} mechanism that dynamically selects informative embeddings based on confidence and dissimilarity, regardless of temporal order. This mechanism not only significantly improves performance in 3D medical image segmentation but also unlocks a \emph{One-Prompt Segmentation} capability for 2D images, allowing segmentation across multiple images from a single prompt without temporal relationships. We evaluated MedSAM-2 on five 2D tasks and nine 3D tasks, including white blood cells, optic cups, retinal vessels, mandibles, coronary arteries, kidney tumors, liver tumors, breast cancer, nasopharynx cancer, vestibular schwannoma, mediastinal lymph nodules, cerebral artery, inferior alveolar nerve, and abdominal organs, comparing it against state-of-the-art (SOTA) models in task-tailored, general and interactive segmentation settings. Our findings demonstrate that MedSAM-2 surpasses a wide range of existing models and updates new SOTA on several benchmarks. The code is released on the project page: https://supermedintel.github.io/Medical-SAM2/.

Xijie Huang, Xinyuan Wang, Hantao Zhang et al.

Security concerns related to Large Language Models (LLMs) have been extensively explored, yet the safety implications for Multimodal Large Language Models (MLLMs), particularly in medical contexts (MedMLLMs), remain insufficiently studied. This paper delves into the underexplored security vulnerabilities of MedMLLMs, especially when deployed in clinical environments where the accuracy and relevance of question-and-answer interactions are critically tested against complex medical challenges. By combining existing clinical medical data with atypical natural phenomena, we define the mismatched malicious attack (2M-attack) and introduce its optimized version, known as the optimized mismatched malicious attack (O2M-attack or 2M-optimization). Using the voluminous 3MAD dataset that we construct, which covers a wide range of medical image modalities and harmful medical scenarios, we conduct a comprehensive analysis and propose the MCM optimization method, which significantly enhances the attack success rate on MedMLLMs. Evaluations with this dataset and attack methods, including white-box attacks on LLaVA-Med and transfer attacks (black-box) on four other SOTA models, indicate that even MedMLLMs designed with enhanced security features remain vulnerable to security breaches. Our work underscores the urgent need for a concerted effort to implement robust security measures and enhance the safety and efficacy of open-source MedMLLMs, particularly given the potential severity of jailbreak attacks and other malicious or clinically significant exploits in medical settings. Our code is available at https://github.com/dirtycomputer/O2M_attack.

Wei Zhu, Wenfeng Li, Xing Tian et al.

Knowledge of the medical decision process, which can be modeled as medical decision trees (MDTs), is critical to build clinical decision support systems. However, the current MDT construction methods rely heavily on time-consuming and laborious manual annotation. In this work, we propose a novel task, Text2MDT, to explore the automatic extraction of MDTs from medical texts such as medical guidelines and textbooks. We normalize the form of the MDT and create an annotated Text-to-MDT dataset in Chinese with the participation of medical experts. We investigate two different methods for the Text2MDT tasks: (a) an end-to-end framework which only relies on a GPT style large language models (LLM) instruction tuning to generate all the node information and tree structures. (b) The pipeline framework which decomposes the Text2MDT task to three subtasks. Experiments on our Text2MDT dataset demonstrate that: (a) the end-to-end method basd on LLMs (7B parameters or larger) show promising results, and successfully outperform the pipeline methods. (b) The chain-of-thought (COT) prompting method \cite{Wei2022ChainOT} can improve the performance of the fine-tuned LLMs on the Text2MDT test set. (c) the lightweight pipelined method based on encoder-based pretrained models can perform comparably with LLMs with model complexity two magnititudes smaller. Our Text2MDT dataset is open-sourced at \url{https://tianchi.aliyun.com/dataset/95414}, and the source codes are open-sourced at \url{https://github.com/michael-wzhu/text2dt}.

Yi-Tzu Chen, Chuan-Hang Yu, Yu-Chao Chang

Dentistry is a highly skill oriented profession where tactile skill plays a major role in delivering dental treatment. Clinical competency-based dental curriculum is emphasized in the traditional dental education. However, face to face interactions between patient and dentist act as the daily routine during clinical practice. It is not surprised that holistic oral healthcare is the core guideline of year 112 teaching hospital accreditation (http://ftp.jct.org.tw: 8080/fbsharing/6OduGDVI). The definition of holistic oral healthcare refers to provide the patient-centered oral care which should consider physical, psychological, spiritual, and social issues. It is also necessary to respect and respond the need and value of patients during clinical oral care. Humanism as well as humanities have been recognized as the soul of medical health education. The cultivation of medical humanities is crucial for professional identity formation in dental education. The incorporation of humanistic education into traditional simulation based courses is important from dentists’ cultivation period to career development. Medical humanity has been defined as a combination of its relevant disciplines including ethics, philosophy, religious studies, history, literature, and so forth. The implementation of medical humanities education could foster students’ critical thinking, scientific process, self-

B Bahtiri, Q Maxhuni, R Ferizi

Transformations in the biological, medical and legal processes of infertility, substantial modifications in family structure and the advancement of methods and techniques of reproductive technology will affect the next step in both legal and medical terms to address the regulation of bioethics and law in Kosovo. There is a need to establish perspectives in both ethical and professional terms, since the Republic of Kosovo is in the process of drafting a Civil Code. Many of these issues have been raised and addressed during the review and evaluation of family law in the context of harmonisation and inclusion of this law in the Civil Code of the Republic of Kosovo. During the several meetings of official members with different interest groups regarding family law, the need has been raised to regulate family law to be included in the Civil Code for motherhood and fatherhood in the case of reproduction with biomedical assistance, as well as for the birth contract as a donation for another person (so-called surrogate motherhood). These bioethical and legal issues indicate the urgent need for legal harmonisation of a multidimensional platform specifically based on the principles of public health and universal human rights Conclusion. These bio-ethical and legal interferences indicate the urgent need for legal harmonization of a multidimensional platform specifically designed based on the principles of public health and universal human rights.

Ceren ARSLAN ÖZÜDOĞRU

İnsanlık tarihi boyunca, tedavi mekanları farklı gelişim evresi geçirmiştir. Mağaralarda başlayan süreç; çadırlara, evlere, dini kurumlara taşınmış zamanla kendi mekanlarını yaratmıştır. Anadolu’da Türklerin iki büyük devleti olan Anadolu Selçuklu ve Osmanlı Devleti’nin sağlık kuruluşlarına odaklanan eser; antik dönemlerden başlamak üzere sağlık mekanlarının gelişimi, işleyişi, mimarisi, tarihi, tedavi yöntemleri ve çevresel etkileri alanına değinerek kapsamlı bir çalışma ortaya koymaktadır. Çalışmayı farklı kılan unsurlar; mimari-tedavi etkileşimini irdelemesi, terapötik unsurlara vurgu yapması, tıbbî gelişimin mimari ve tedavi yöntemleri bazında incelemesidir. Antik çağlardan başlamak üzere Osmanlı Devleti’nin sonlarına kadar mimari tasarımla hastaların tedavi sürecine katkıda bulunmaya çalışıldığı görülmektedir. Gün ışığı, temiz hava, yeşil alan, botanik ve doğal su kaynakları bu amaçla kullanılan unsurlar olmuştur. Bunun mimariye yansımaları havuz, pencere, aydınlık feneri, hamam, bahçe gibi unsurlarda karşılık bulduğu görülmüştür. Her dönemde sağlık mekanlarının kuruluş amacı aynı olsa da mimari yorum, kültürel etkileşim ve tedavi yöntemleri farklılık göstermiştir.

Yucheng Shi, Shaochen Xu, Tianze Yang et al.

Large Language Models (LLMs), although powerful in general domains, often perform poorly on domain-specific tasks such as medical question answering (QA). In addition, LLMs tend to function as "black-boxes", making it challenging to modify their behavior. To address the problem, our work employs a transparent process of retrieval augmented generation (RAG), aiming to improve LLM responses without the need for fine-tuning or retraining. Specifically, we propose a comprehensive retrieval strategy to extract medical facts from an external knowledge base, and then inject them into the LLM's query prompt. Focusing on medical QA, we evaluate the impact of different retrieval models and the number of facts on LLM performance using the MedQA-SMILE dataset. Notably, our retrieval-augmented Vicuna-7B model exhibited an accuracy improvement from 44.46% to 48.54%. This work underscores the potential of RAG to enhance LLM performance, offering a practical approach to mitigate the challenges posed by black-box LLMs.

Helena Montenegro, Jaime S. Cardoso

Case-based explanations are an intuitive method to gain insight into the decision-making process of deep learning models in clinical contexts. However, medical images cannot be shared as explanations due to privacy concerns. To address this problem, we propose a novel method for disentangling identity and medical characteristics of images and apply it to anonymize medical images. The disentanglement mechanism replaces some feature vectors in an image while ensuring that the remaining features are preserved, obtaining independent feature vectors that encode the images' identity and medical characteristics. We also propose a model to manufacture synthetic privacy-preserving identities to replace the original image's identity and achieve anonymization. The models are applied to medical and biometric datasets, demonstrating their capacity to generate realistic-looking anonymized images that preserve their original medical content. Additionally, the experiments show the network's inherent capacity to generate counterfactual images through the replacement of medical features.