Hasil untuk "Medical philosophy. Medical ethics"

Xiaorui Su, Shvat Messica, Yepeng Huang et al.

Foundation models trained on patient electronic health records (EHRs) require tokenizing medical data into sequences of discrete vocabulary items. Existing tokenizers treat medical codes from EHRs as isolated textual tokens. However, each medical code is defined by its textual description, its position in ontological hierarchies, and its relationships to other codes, such as disease co-occurrences and drug-treatment associations. Medical vocabularies contain more than 600,000 codes with critical information for clinical reasoning. We introduce MedTok, a multimodal medical code tokenizer that uses the text descriptions and relational context of codes. MedTok processes text using a language model encoder and encodes the relational structure with a graph encoder. It then quantizes both modalities into a unified token space, preserving modality-specific and cross-modality information. We integrate MedTok into five EHR models and evaluate it on operational and clinical tasks across in-patient and out-patient datasets, including outcome prediction, diagnosis classification, drug recommendation, and risk stratification. Swapping standard EHR tokenizers with MedTok improves AUPRC across all EHR models, by 4.10% on MIMIC-III, 4.78% on MIMIC-IV, and 11.32% on EHRShot, with the largest gains in drug recommendation. Beyond EHR modeling, we demonstrate using MedTok tokenizer with medical QA systems. Our results demonstrate the potential of MedTok as a unified tokenizer for medical codes, improving tokenization for medical foundation models.

Ao Li, Bin Yan, Bingfeng Cai et al.

Recent advancements in large language models have significantly accelerated their adoption in healthcare applications, including AI-powered medical consultations, diagnostic report assistance, and medical search tools. However, medical tasks often demand highly specialized knowledge, professional accuracy, and customization capabilities, necessitating a robust and reliable foundation model. QuarkMed addresses these needs by leveraging curated medical data processing, medical-content Retrieval-Augmented Generation (RAG), and a large-scale, verifiable reinforcement learning pipeline to develop a high-performance medical foundation model. The model achieved 70% accuracy on the Chinese Medical Licensing Examination, demonstrating strong generalization across diverse medical benchmarks. QuarkMed offers a powerful yet versatile personal medical AI solution, already serving over millions of users at ai.quark.cn.

Kayla O'Sullivan-Steben, Luc Galarneau, John Kildea

Introduction: The rise in public medical imaging datasets has raised concerns about patient reidentification from head CT scans. However, existing defacing algorithms often remove or distort Organs at Risk (OARs) and Planning Target Volumes (PTVs) in head and neck cancer (HNC) patients, and ignore DICOM-RT Structure Set and Dose data. Therefore, we developed and validated a novel automated defacing algorithm that preserves these critical structures while removing identifiable features from HNC CTs and DICOM-RT data. Methods: Eye contours were used as landmarks to automate the removal of CT pixels above the inferior-most eye slice and anterior to the eye midpoint. Pixels within PTVs were retained if they intersected with the removed region. The body contour and dose map were reshaped to reflect the defaced image. We validated our approach on 829 HNC CTs from 622 patients. Privacy protection was evaluated by applying the FaceNet512 facial recognition algorithm before and after defacing on 3D-rendered CT pairs from 70 patients. Research utility was assessed by examining the impact of defacing on autocontouring performance using LimbusAI and analyzing PTV locations relative to the defaced regions. Results: Before defacing, FaceNet512 matched 97% of patients' CTs. After defacing, this rate dropped to 4%. LimbusAI effectively autocontoured organs in the defaced CTs, with perfect Dice scores of 1 for OARs below the defaced region, and excellent scores exceeding 0.95 for OARs on the same slices as the crop. We found that 86% of PTVs were entirely below the cropped region, 9.1% were on the same slice as the crop without overlap, and only 4.9% extended into the cropped area. Conclusions: We developed a novel defacing algorithm that anonymizes HNC CT scans and related DICOM-RT data while preserving essential structures, enabling the sharing of HNC imaging datasets for Big Data and AI.

Jimenez Eladio, Hao Wu

Machine Reading Comprehension (MRC) holds a pivotal role in shaping Medical Question Answering Systems (QAS) and transforming the landscape of accessing and applying medical information. However, the inherent challenges in the medical field, such as complex terminology and question ambiguity, necessitate innovative solutions. One key solution involves integrating specialized medical datasets and creating dedicated datasets. This strategic approach enhances the accuracy of QAS, contributing to advancements in clinical decision-making and medical research. To address the intricacies of medical terminology, a specialized dataset was integrated, exemplified by a novel Span extraction dataset derived from emrQA but restructured into 163,695 questions and 4,136 manually obtained answers, this new dataset was called emrQA-msquad dataset. Additionally, for ambiguous questions, a dedicated medical dataset for the Span extraction task was introduced, reinforcing the system's robustness. The fine-tuning of models such as BERT, RoBERTa, and Tiny RoBERTa for medical contexts significantly improved response accuracy within the F1-score range of 0.75 to 1.00 from 10.1% to 37.4%, 18.7% to 44.7% and 16.0% to 46.8%, respectively. Finally, emrQA-msquad dataset is publicy available at https://huggingface.co/datasets/Eladio/emrqa-msquad.

Yue Jiang, Jiawei Chen, Dingkang Yang et al.

Automatic medical report generation (MRG), which possesses significant research value as it can aid radiologists in clinical diagnosis and report composition, has garnered increasing attention. Despite recent progress, generating accurate reports remains arduous due to the requirement for precise clinical comprehension and disease diagnosis inference. Furthermore, owing to the limited accessibility of medical data and the imbalanced distribution of diseases, the underrepresentation of rare diseases in training data makes large-scale medical visual language models (LVLMs) prone to hallucinations, such as omissions or fabrications, severely undermining diagnostic performance and further intensifying the challenges for MRG in practice. In this study, to effectively mitigate hallucinations in medical report generation, we propose a chain-of-medical-thought approach (CoMT), which intends to imitate the cognitive process of human doctors by decomposing diagnostic procedures. The radiological features with different importance are structured into fine-grained medical thought chains to enhance the inferential ability during diagnosis, thereby alleviating hallucination problems and enhancing the diagnostic accuracy of MRG. The code and dataset have been released at https://github.com/FRENKIE-CHIANG/CoMT.

Qi Chen, Ruoshan Zhao, Sinuo Wang et al.

Medical vision-and-language models (MVLMs) have attracted substantial interest due to their capability to offer a natural language interface for interpreting complex medical data. Their applications are versatile and have the potential to improve diagnostic accuracy and decision-making for individual patients while also contributing to enhanced public health monitoring, disease surveillance, and policy-making through more efficient analysis of large data sets. MVLMS integrate natural language processing with medical images to enable a more comprehensive and contextual understanding of medical images alongside their corresponding textual information. Unlike general vision-and-language models trained on diverse, non-specialized datasets, MVLMs are purpose-built for the medical domain, automatically extracting and interpreting critical information from medical images and textual reports to support clinical decision-making. Popular clinical applications of MVLMs include automated medical report generation, medical visual question answering, medical multimodal segmentation, diagnosis and prognosis and medical image-text retrieval. Here, we provide a comprehensive overview of MVLMs and the various medical tasks to which they have been applied. We conduct a detailed analysis of various vision-and-language model architectures, focusing on their distinct strategies for cross-modal integration/exploitation of medical visual and textual features. We also examine the datasets used for these tasks and compare the performance of different models based on standardized evaluation metrics. Furthermore, we highlight potential challenges and summarize future research trends and directions. The full collection of papers and codes is available at: https://github.com/YtongXie/Medical-Vision-and-Language-Tasks-and-Methodologies-A-Survey.

Yi-Ling Wu, Tsai-Wen Lin, Chun-Yi Yang et al.

Abstract Background The Patient Right to Autonomy Act (PRAA), implemented in Taiwan in 2019, enables the creation of advance decisions (AD) through advance care planning (ACP). This legal framework allows for the withholding and withdrawal of life-sustaining treatment (LST) or artificial nutrition and hydration (ANH) in situations like irreversible coma, vegetative state, severe dementia, or unbearable pain. This study aims to investigate preferences for LST or ANH across various clinical conditions, variations in participant preferences, and factors influencing these preferences among urban residents. Methods Employing a survey of legally structured AD documents and convenience sampling for data collection, individuals were enlisted from Taipei City Hospital, serving as the primary trial and demonstration facility for ACP in Taiwan since the commencement of the PRAA in its inaugural year. The study examined ADs and ACP consultation records, documenting gender, age, welfare entitlement, disease conditions, family caregiving experience, location of ACP consultation, participation of second-degree relatives, and the intention to participate in ACP. Results Data from 2337 participants were extracted from electronic records. There was high consistency in the willingness to refuse LST and ANH, with significant differences noted between terminal diseases and extremely severe dementia. Additionally, ANH was widely accepted as a time-limited treatment, and there was a prevalent trend of authorizing a health care agent (HCA) to make decisions on behalf of participants. Gender differences were observed, with females more inclined to decline LST and ANH, while males tended towards accepting full or time-limited treatment. Age also played a role, with younger participants more open to treatment and authorizing HCA, and older participants more prone to refusal. Conclusion Diverse preferences in LST and ANH were shaped by the public’s current understanding of different clinical states, gender, age, and cultural factors. Our study reveals nuanced end-of-life preferences, evolving ADs, and socio-demographic influences. Further research could explore evolving preferences over time and healthcare professionals’ perspectives on LST and ANH decisions for neurological patients..

Shantanu Ganguly , Nivedita Pandey

Academic integrity is a set of ethical ideals and values that guide the behavior of individuals in academic and educational settings. It encompasses honesty, trustworthiness, fairness, and a commitment to upholding the highest standards of ethical conduct in the quest for knowledge, learning, and research. Academic integrity is essential in maintaining the trustworthiness, reputation, and effectiveness of educational institutions and scholarly communities. Whereas, AI, or Artificial Intelligence, is a broad field of computer science that focuses on creating frameworks, software, or machines that can perform tasks that would typically require human intelligence. These tasks include problem-solving, learning from experience, understanding natural language, recognizing patterns, and making choices. AI systems aim to mimic or replicate human cognitive functions, and they can range from simple rule-based systems to highly complex, autodidactic neural networks. AI can significantly impact academic integrity and research in both positive and potentially challenging ways.

Rafaela Rossi, Manoela Duarte Selbach, Euler Westphal

Resumo Perante a realidade atual de exploração excessiva dos recursos naturais, a bioética promove um importante debate interdisciplinar abrangendo ramos éticos e científicos. Por muitos anos, um processo de industrialização expressivo aumentou a produção de bens de consumo e gerou uma mentalidade consumista. A valorização da lucratividade e do consumismo evidenciaram os impactos do conheci mento perigoso, a exemplo do uso indiscriminado de agrotóxicos e de testes de engenharia genética. Nesse contexto, a população teve acesso a uma quantidade extraordinária de informações, embora não soubesse como utilizá-las de maneira adequada, fato que salienta a importância da bioética para mediar conflitos, promovendo uma discussão entre especialistas e a população. Por fim, ressalta-se a necessidade de conscientizar as pessoas quanto aos impactos ambientais de suas atividades, objetivando mudar atitudes em relação ao ambiente e possibilitar um convívio mais harmônico entre os seres humanos e as diferentes espécies animais e vegetais.

Lorenzo Gallego Borghini

En marzo de 2020, ante la llegada de la COVID-19, España decretó uno de los confinamientos más estrictos de Occidente. Esta medida sanitaria tan extrema plantea un conflicto ético de valores que se traslada, en lo político, a los derechos fundamentales y, en última instancia, a los derechos humanos. En este artículo se repasan los derechos afectados y se analiza el confinamiento impuesto por España e imitado luego por los países latinoamericanos, con el prisma de los principios éticos relativos a la contención de epidemias. El confinamiento fue una intervención inédita, que no estaba probada y cuya eficacia era desconocida; conllevó una vulneración grave de los derechos civiles sin justificación científica y sin verdaderos resultados epidemiológicos. Evitar el mismo error en futuras pandemias depende en parte de un escrupuloso respeto por los principios éticos que ya están recogidos en la legislación vigente.

Niketha Sabesan, Nivethitha, J. N Shreyah et al.

Web scraping is a technique that allows us to extract data from websites automatically. in the field of medicine, web scraping can be used to collect information about medical procedures, treatments, and healthcare providers. this information can be used to improve patient care, monitor the quality of healthcare services, and identify areas for improvement. one area where web scraping can be particularly useful is in medical ministrations. medical ministrations are the actions taken to provide medical care to patients, and web scraping can help healthcare providers identify the most effective ministrations for their patients. for example, healthcare providers can use web scraping to collect data about the symptoms and medical histories of their patients, and then use this information to determine the most appropriate ministrations. they can also use web scraping to gather information about the latest medical research and clinical trials, which can help them stay up-to-date with the latest treatments and procedures.

Masashi Takeshita, Rzepka Rafal, Kenji Araki

Moral AI has been studied in the fields of philosophy and artificial intelligence. Although most existing studies are only theoretical, recent developments in AI have made it increasingly necessary to implement AI with morality. On the other hand, humans are under the moral uncertainty of not knowing what is morally right. In this paper, we implement the Maximizing Expected Choiceworthiness (MEC) algorithm, which aggregates outputs of models based on three normative theories of normative ethics to generate the most appropriate output. MEC is a method for making appropriate moral judgments under moral uncertainty. Our experimental results suggest that the output of MEC correlates to some extent with commonsense morality and that MEC can produce equally or more appropriate output than existing methods.

Mingyuan Meng, Lei Bi, Michael Fulham et al.

Survival prediction is crucial for cancer patients as it provides early prognostic information for treatment planning. Recently, deep survival models based on deep learning and medical images have shown promising performance for survival prediction. However, existing deep survival models are not well developed in utilizing multi-modality images (e.g., PET-CT) and in extracting region-specific information (e.g., the prognostic information in Primary Tumor (PT) and Metastatic Lymph Node (MLN) regions). In view of this, we propose a merging-diverging learning framework for survival prediction from multi-modality images. This framework has a merging encoder to fuse multi-modality information and a diverging decoder to extract region-specific information. In the merging encoder, we propose a Hybrid Parallel Cross-Attention (HPCA) block to effectively fuse multi-modality features via parallel convolutional layers and cross-attention transformers. In the diverging decoder, we propose a Region-specific Attention Gate (RAG) block to screen out the features related to lesion regions. Our framework is demonstrated on survival prediction from PET-CT images in Head and Neck (H&N) cancer, by designing an X-shape merging-diverging hybrid transformer network (named XSurv). Our XSurv combines the complementary information in PET and CT images and extracts the region-specific prognostic information in PT and MLN regions. Extensive experiments on the public dataset of HEad and neCK TumOR segmentation and outcome prediction challenge (HECKTOR 2022) demonstrate that our XSurv outperforms state-of-the-art survival prediction methods.

Felicitas Selter, Kirsten Persson, Peter Kunzmann et al.

IntroductionAt first glance, human and (companion animal) veterinary medicine share challenging processes in end-of-life (EOL) decision-making. At the same time, treatment options in both professions are substantially different. The potential of an interdisciplinary exchange between both fields has been neglected by empirical research so far.MethodsIn this qualitative study, professionals from both fields were brought together in interdisciplinary focus groups to investigate the ethical aspects of convergences and divergences in EOL situations in human and veterinary medicine. The authors present and discuss an innovative mix of materials and methods as stimuli for discussion and for generating hypotheses.ResultsThe results point toward a general convergence of issues, challenges, and judgements in EOL situations in both fields, such as professional ethos, communication with the family and the role thereof as well as the ideals of death, clearly exceeding the expectations of study participants. At the same time, the study highlights a few prominent differences such as the access to patients' preferences or legal and practical constraints.DiscussionThe findings suggest that using social science methods in empirical interdisciplinary biomedical-veterinary ethics could help to shed more light on this new area. Animal as well as human patients can potentially benefit from this mutual, scientifically accompanied exchange and the resulting identification and corrections of misconceptions.

Cristina Bosmani, Sonia Carboni, Caroline Samer et al.

Abstract Background We assessed potential consent bias in a cohort of > 40,000 adult patients asked by mail after hospitalization to consent to the use of past, present and future clinical and biological data in an ongoing ‘general consent’ program at a large tertiary hospital in Switzerland. Methods In this retrospective cohort study, all adult patients hospitalized between April 2019 and March 2020 were invited to participate to the general consent program. Demographic and clinical characteristics were extracted from patients’ electronic health records (EHR). Data of those who provided written consent (signatories) and non-responders were compared and analyzed with R studio. Results Of 44,819 patients approached, 10,299 (23%) signed the form. Signatories were older (median age 54 [IQR 38–72] vs. 44 years [IQR 32–60], p < .0001), more comorbid (2614/10,299 [25.4%] vs. 4912/28,676 [17.1%] with Charlson comorbidity index ≤ 4, p < .0001), and more often of Swiss nationality (6592/10,299 [64%] vs. 13,813/28,676 [48.2%], p < .0001). Conclusions Our results suggest that actively seeking consent creates a bias and compromises the external validity of data obtained via ‘general consent’ programs. Other options, such as opt-out consent procedures, should be further assessed.

Tajwar Abrar Aleef, Julio Lobo, Ali Baghani et al.

This article describes a novel quasi-real time system for quantitative and volumetric measurement of tissue elasticity in the prostate. Tissue elasticity is computed by using a local frequency estimator to measure the three dimensional local wavelengths of a steady-state shear wave within the prostate gland. The shear wave is created using a mechanical voice coil shaker which transmits multi-frequency vibrations transperineally. Radio frequency data is streamed directly from a BK Medical 8848 trans-rectal ultrasound transducer to an external computer where tissue displacement due to the excitation is measured using a speckle tracking algorithm. Bandpass sampling is used that eliminates the need for an ultra fast frame rate to track the tissue motion and allows for accurate reconstruction at a sampling frequency that is below the Nyquist rate. A roll motor with computer control is used to rotate the sagittal array of the transducer and obtain the 3D data. Two CIRS phantoms were used to validate both the accuracy of the elasticity measurement as well as the functional feasibility of using the system for in vivo prostate imaging. The system has been used in two separate clinical studies as a method for cancer identification. The results, presented here, show numerical and visual correlations between our stiffness measurements and cancer likelihood as determined from pathology results. Initial published results using this system include an area under the receiver operating characteristic curve of 0.82+/-0.01 with regards to prostate cancer identification in the peripheral zone.

Zhihong Lin, Donghao Zhang, Qingyi Tao et al.

Medical Visual Question Answering~(VQA) is a combination of medical artificial intelligence and popular VQA challenges. Given a medical image and a clinically relevant question in natural language, the medical VQA system is expected to predict a plausible and convincing answer. Although the general-domain VQA has been extensively studied, the medical VQA still needs specific investigation and exploration due to its task features. In the first part of this survey, we collect and discuss the publicly available medical VQA datasets up-to-date about the data source, data quantity, and task feature. In the second part, we review the approaches used in medical VQA tasks. We summarize and discuss their techniques, innovations, and potential improvements. In the last part, we analyze some medical-specific challenges for the field and discuss future research directions. Our goal is to provide comprehensive and helpful information for researchers interested in the medical visual question answering field and encourage them to conduct further research in this field.

Jeya Maria Jose Valanarasu, Poojan Oza, Ilker Hacihaliloglu et al.

Over the past decade, Deep Convolutional Neural Networks have been widely adopted for medical image segmentation and shown to achieve adequate performance. However, due to the inherent inductive biases present in the convolutional architectures, they lack understanding of long-range dependencies in the image. Recently proposed Transformer-based architectures that leverage self-attention mechanism encode long-range dependencies and learn representations that are highly expressive. This motivates us to explore Transformer-based solutions and study the feasibility of using Transformer-based network architectures for medical image segmentation tasks. Majority of existing Transformer-based network architectures proposed for vision applications require large-scale datasets to train properly. However, compared to the datasets for vision applications, for medical imaging the number of data samples is relatively low, making it difficult to efficiently train transformers for medical applications. To this end, we propose a Gated Axial-Attention model which extends the existing architectures by introducing an additional control mechanism in the self-attention module. Furthermore, to train the model effectively on medical images, we propose a Local-Global training strategy (LoGo) which further improves the performance. Specifically, we operate on the whole image and patches to learn global and local features, respectively. The proposed Medical Transformer (MedT) is evaluated on three different medical image segmentation datasets and it is shown that it achieves better performance than the convolutional and other related transformer-based architectures. Code: https://github.com/jeya-maria-jose/Medical-Transformer

Claudia Schulz, Damir Juric

A large number of embeddings trained on medical data have emerged, but it remains unclear how well they represent medical terminology, in particular whether the close relationship of semantically similar medical terms is encoded in these embeddings. To date, only small datasets for testing medical term similarity are available, not allowing to draw conclusions about the generalisability of embeddings to the enormous amount of medical terms used by doctors. We present multiple automatically created large-scale medical term similarity datasets and confirm their high quality in an annotation study with doctors. We evaluate state-of-the-art word and contextual embeddings on our new datasets, comparing multiple vector similarity metrics and word vector aggregation techniques. Our results show that current embeddings are limited in their ability to adequately encode medical terms. The novel datasets thus form a challenging new benchmark for the development of medical embeddings able to accurately represent the whole medical terminology.

Anjany Sekuboyina, Malek E. Husseini, Amirhossein Bayat et al.

Vertebral labelling and segmentation are two fundamental tasks in an automated spine processing pipeline. Reliable and accurate processing of spine images is expected to benefit clinical decision-support systems for diagnosis, surgery planning, and population-based analysis on spine and bone health. However, designing automated algorithms for spine processing is challenging predominantly due to considerable variations in anatomy and acquisition protocols and due to a severe shortage of publicly available data. Addressing these limitations, the Large Scale Vertebrae Segmentation Challenge (VerSe) was organised in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2019 and 2020, with a call for algorithms towards labelling and segmentation of vertebrae. Two datasets containing a total of 374 multi-detector CT scans from 355 patients were prepared and 4505 vertebrae have individually been annotated at voxel-level by a human-machine hybrid algorithm (https://osf.io/nqjyw/, https://osf.io/t98fz/). A total of 25 algorithms were benchmarked on these datasets. In this work, we present the the results of this evaluation and further investigate the performance-variation at vertebra-level, scan-level, and at different fields-of-view. We also evaluate the generalisability of the approaches to an implicit domain shift in data by evaluating the top performing algorithms of one challenge iteration on data from the other iteration. The principal takeaway from VerSe: the performance of an algorithm in labelling and segmenting a spine scan hinges on its ability to correctly identify vertebrae in cases of rare anatomical variations. The content and code concerning VerSe can be accessed at: https://github.com/anjany/verse.