The federated learning paradigm is wellsuited for the field of medical image analysis, as it can effectively cope with machine learning on isolated multicenter data while protecting the privacy of participating parties. However, current research on optimization algorithms in federated learning often focuses on limited datasets and scenarios, primarily centered around natural images, with insufficient comparative experiments in medical contexts. In this work, we conduct a comprehensive evaluation of several state-of-the-art federated learning algorithms in the context of medical imaging. We conduct a fair comparison of classification models trained using various federated learning algorithms across multiple medical imaging datasets. Additionally, we evaluate system performance metrics, such as communication cost and computational efficiency, while considering different federated learning architectures. Our findings show that medical imaging datasets pose substantial challenges for current federated learning optimization algorithms. No single algorithm consistently delivers optimal performance across all medical federated learning scenarios, and many optimization algorithms may underperform when applied to these datasets. Our experiments provide a benchmark and guidance for future research and application of federated learning in medical imaging contexts. Furthermore, we propose an efficient and robust method that combines generative techniques using denoising diffusion probabilistic models with label smoothing to augment datasets, widely enhancing the performance of federated learning on classification tasks across various medical imaging datasets. Our code will be released on GitHub, offering a reliable and comprehensive benchmark for future federated learning studies in medical imaging.
The need for robust and diverse data sets to train clinical large language models (cLLMs) is critical given that currently available public repositories often prove too limited in size or scope for comprehensive medical use. While resources like PubMed provide foundational medical literature, they capture only a narrow range of formal publications and omit the broader medical discourse on the internet. To address these deficits, we introduce TheBlueScrubs-v1, a curated dataset of over 25 billion medical tokens - nearly three times larger than PubMed - drawn from a broad-scale internet corpus. Our two-stage filtering pipeline employs a Logistic Regression model for document screening (achieving an AUC of approximately 0.95 on external validation), followed by verification via a 70B-parameter Llama 3.1 instruct model. Each text is assigned three LLM-based quality scores encompassing medical relevance, precision and factual detail, and safety and ethical standards. Clinician reviews confirm high concordance with these automated evaluations, and a specialized cancer classifier further labels approximately 11 billion oncology tokens. Two demonstration tasks highlight the dataset's practical value: first, we distill the safety evaluations to a smaller BERT-style model that reaches an AUC near 0.96 on unseen data; second, we fine-tune a compact LLM on a filtered subset, showing measurable improvements over standard baselines in medical benchmarks as well as private ones. This Data Descriptor details the dataset's creation and validation, underscoring its potential utility for medical AI research.
Existing Medical Large Vision-Language Models (Med-LVLMs), encapsulating extensive medical knowledge, demonstrate excellent capabilities in understanding medical images. However, there remain challenges in visual localization in medical images, which is crucial for abnormality detection and interpretation. To address these issues, we propose a novel UMed-LVLM designed to unveil medical abnormalities. Specifically, we collect a Medical Abnormalities Unveiling (MAU) dataset and propose a two-stage training method for UMed-LVLM training. To collect MAU dataset, we propose a prompt method utilizing the GPT-4V to generate diagnoses based on identified abnormal areas in medical images. Moreover, the two-stage training method includes Abnormal-Aware Instruction Tuning and Abnormal-Aware Rewarding, comprising Relevance Reward, Abnormal Localization Reward and Vision Relevance Reward. Experimental results demonstrate that our UMed-LVLM significantly outperforms existing Med-LVLMs in identifying and understanding medical abnormalities, achieving a 58% improvement over the baseline. In addition, this work shows that enhancing the abnormality detection capabilities of Med-LVLMs significantly improves their understanding of medical images and generalization capability.
Acquiring medical expertise is a critical component of medical education and professional development. While existing studies focus primarily on constructing medical knowledge bases or developing learning tools based on the structured, private healthcare data, they often lack methods for extracting expertise from unstructured medical texts. These texts constitute a significant portion of medical literature and offer greater flexibility and detail compared to structured data formats. Furthermore, many studies fail to provide explicit analytical and learning pathways in this context. This paper introduces MExplore, an interactive visual analytics system designed to support the acquisition of medical expertise. To address the challenges of the inconsistencies and confidentiality concerns inherent in unstructured medical texts, we propose a workflow that employs a fine-tuned BERT-based model to extract medical entities (MEs) from them. We then present a novel multilevel visual analysis framework that integrates multiple coordinated visualizations, enabling a progressive and interactive exploration of medical knowledge. To assess the effectiveness of MExplore, we conducted three case studies, a user study, and interviews with domain experts. The results indicate that the system significantly enhances the medical expertise acquisition process, providing an effective interactive approach for acquiring and retaining knowledge from medical texts.
Orhun Utku Aydin, Alexander Koch, Adam Hilbert
et al.
Despite the potential of synthetic medical data for augmenting and improving the generalizability of deep learning models, memorization in generative models can lead to unintended leakage of sensitive patient information and limit model utility. Thus, the use of memorizing generative models in the medical domain can jeopardize patient privacy. We propose a framework for identifying replicas, i.e. nearly identical copies of the training data, in synthetic medical image datasets. Our REpLIca deteCTion (RELICT) framework for medical image generative models evaluates image similarity using three complementary approaches: (1) voxel-level analysis, (2) feature-level analysis by a pretrained medical foundation model, and (3) segmentation-level analysis. Two clinically relevant 3D generative modelling use cases were investigated: non-contrast head CT with intracerebral hemorrhage (N=774) and time-of-flight MR angiography of the Circle of Willis (N=1,782). Expert visual scoring was used as the reference standard to assess the presence of replicas. We report the balanced accuracy at the optimal threshold to assess replica classification performance. The reference visual rating identified 45 of 50 and 5 of 50 generated images as replicas for the NCCT and TOF-MRA use cases, respectively. Image-level and feature-level measures perfectly classified replicas with a balanced accuracy of 1 when an optimal threshold was selected for the NCCT use case. A perfect classification of replicas for the TOF-MRA case was not possible at any threshold, with the segmentation-level analysis achieving a balanced accuracy of 0.79. Replica detection is a crucial but neglected validation step for the development of generative models in medical imaging. The proposed RELICT framework provides a standardized, easy-to-use tool for replica detection and aims to facilitate responsible and ethical medical image synthesis.
The development of Open-Source Software (OSS) is not only a technical challenge, but also a social one due to the diverse mixture of contributors. To this aim, social-coding platforms, such as GitHub, provide the infrastructure needed to host and develop the code, but also the support for enabling the community's collaboration, which is driven by non-coding contributions, such as issues (i.e., change proposals or bug reports) or comments to existing contributions. As with any other social endeavor, this development process faces ethical challenges, which may put at risk the project's sustainability. To foster a productive and positive environment, OSS projects are increasingly deploying codes of conduct, which define rules to ensure a respectful and inclusive participatory environment, with the Contributor Covenant being the main model to follow. However, monitoring and enforcing these codes of conduct is a challenging task, due to the limitations of current approaches. In this paper, we propose an approach to classify the ethical quality of non-coding contributions in OSS projects by relying on Large Language Models (LLM), a promising technology for text classification tasks. We defined a set of ethical metrics based on the Contributor Covenant and developed a classification approach to assess ethical behavior in OSS non-coding contributions, using prompt engineering to guide the model's output.
Abstract Background Investigator-initiated clinical trials have flourished in China. However, research on stakeholders’ perceptions and management capacity of investigator-initiated clinical trials, which are crucial for optimizing resource utilization, timely identifying barriers affecting high-quality Investigator-initiated clinical trials output, and providing evidence for establishing, improving, and evaluating the quality management system for Investigator-initiated clinical trials, is rare. Our objective is to assess the perception of the standardized quality management of Investigator-initiated clinical trials among stakeholders at different levels of healthcare institutions. Methods We conducted a cross-sectional study using an electronic survey designed using REDCap conducted between June and September 2024 in Healthcare institutions of various levels in Beijing, China. Hospital level, education level, years in research, familiarity, distinction ability, medical personnel, research administrators, methodologists, and other personnel were investigated as potential influencing factors. The primary outcomes were the total number of correct answers and weighted correct rates for each domain and all six domains. Results A total of 717 individuals participated in the study. The distribution of total correct answers and weighted correct rates across all domains was 20.0 (15.0–23.0) and 0.8 (0.6–0.9), respectively. Participants from higher-level hospitals, those with higher education levels, greater familiarity, and higher distinction ability, and administrators performed significantly better in terms of the total number of correct answers and weighted correct rates across all domains. Conclusions The stakeholders performed well overall. However, much room for improvement still exists. Hospital level, education level, familiarity, distinction ability, and the role of research administrators can influence the overall performance of stakeholders. Establishing, improving, and evaluating a quality management system for Investigator-initiated clinical trials in China is crucial. Trial registration Not applicable.
Mohammad Mahbub Ur Rahim, Salome Rahim, Md. Kaoser Bin Siddique
et al.
The ever-growing volume of scientific research challenges for traditional publishing models. This necessitates innovative approaches to journal editing and adopting by Artificial Intelligence (AI) in publication. This scoping review aims to explore the emerging trends shaping the field of journal editing by AI. Literature employed to search relevant databases published between 2008 and 2024. A total of 25 studies met the inclusion criteria. The review synthesizes key trends of inclusion of the technological tools integration for manuscript processing, the rise of open-access publishing models, and evolving considerations around research ethics. The study underscores the pivotal role of emerging trends in shaping the future of scientific publishing. It offers valuable perspectives for editors to adeptly maneuver through the evolving terrain of scholarly communication. By suggesting possible best practices, it serves as a beacon for maintaining editorial excellence. Furthermore, it identifies critical domains warranting deeper exploration, thereby setting the stage for continuous advancement in the field. This forward-looking approach not only facilitates informed decision-making but also fosters a proactive stance towards embracing change in scientific discourse.
Este estudio explora la formación en bioética y ética aplicada de los profesionales de cuidados paliativos pediátricos en un hospital de tercer nivel en España. A través de cuestionarios autoadministrados, se analizan las perspectivas éticas y la formación para abordar los procesos de toma de decisiones complejas. Los resultados muestran una predominancia de la ética del cuidado y de la responsabilidad entre los participantes, junto a una formación limitada y desigual en bioética según el perfil profesional. El malestar moral, la falta de un método formal y el uso de la intuición y sentido común como guías son fuentes de dificultad para mantener la objetividad en su práctica. Se concluye que es necesaria una formación continua y adaptada, así como la creación de espacios seguros de reflexión, para mejorar la toma de decisiones y reducir el malestar moral.
Medical philosophy. Medical ethics, Business ethics
Artificial Intelligence (AI) has become essential in modern healthcare, with large language models (LLMs) offering promising advances in clinical decision-making. Traditional model-based approaches, including those leveraging in-context demonstrations and those with specialized medical fine-tuning, have demonstrated strong performance in medical language processing but struggle with real-time adaptability, multi-step reasoning, and handling complex medical tasks. Agent-based AI systems address these limitations by incorporating reasoning traces, tool selection based on context, knowledge retrieval, and both short- and long-term memory. These additional features enable the medical AI agent to handle complex medical scenarios where decision-making should be built on real-time interaction with the environment. Therefore, unlike conventional model-based approaches that treat medical queries as isolated questions, medical AI agents approach them as complex tasks and behave more like human doctors. In this paper, we study the choice of the backbone LLM for medical AI agents, which is the foundation for the agent's overall reasoning and action generation. In particular, we consider the emergent o1 model and examine its impact on agents' reasoning, tool-use adaptability, and real-time information retrieval across diverse clinical scenarios, including high-stakes settings such as intensive care units (ICUs). Our findings demonstrate o1's ability to enhance diagnostic accuracy and consistency, paving the way for smarter, more responsive AI tools that support better patient outcomes and decision-making efficacy in clinical practice.
Conventional medical artificial intelligence (AI) models face barriers in clinical application and ethical issues owing to their inability to handle the privacy-sensitive characteristics of medical data. We present a novel personalized federated learning (pFL) method for medical visual question answering (VQA) models, addressing privacy reliability challenges in the medical domain. Our method introduces learnable prompts into a Transformer architecture to efficiently train it on diverse medical datasets without massive computational costs. Then we introduce a reliable client VQA model that incorporates Dempster-Shafer evidence theory to quantify uncertainty in predictions, enhancing the model's reliability. Furthermore, we propose a novel inter-client communication mechanism that uses maximum likelihood estimation to balance accuracy and uncertainty, fostering efficient integration of insights across clients.
Foundation models are becoming valuable tools in medicine. Yet despite their promise, the best way to leverage Large Language Models (LLMs) in complex medical tasks remains an open question. We introduce a novel multi-agent framework, named Medical Decision-making Agents (MDAgents) that helps address this gap by automatically assigning a collaboration structure to a team of LLMs. The assigned solo or group collaboration structure is tailored to the medical task at hand, emulating real-world medical decision-making processes adapted to tasks of varying complexities. We evaluate our framework and baseline methods using state-of-the-art LLMs across a suite of real-world medical knowledge and medical diagnosis benchmarks, including a comparison of LLMs' medical complexity classification against human physicians. MDAgents achieved the best performance in seven out of ten benchmarks on tasks requiring an understanding of medical knowledge and multi-modal reasoning, showing a significant improvement of up to 4.2% (p < 0.05) compared to previous methods' best performances. Ablation studies reveal that MDAgents effectively determines medical complexity to optimize for efficiency and accuracy across diverse medical tasks. Notably, the combination of moderator review and external medical knowledge in group collaboration resulted in an average accuracy improvement of 11.8%. Our code can be found at https://github.com/mitmedialab/MDAgents.
Jin Shi, D. Bendig, Horst Christian Vollmar
et al.
Background Artificial intelligence (AI), conceived in the 1950s, has permeated numerous industries, intensifying in tandem with advancements in computing power. Despite the widespread adoption of AI, its integration into medicine trails other sectors. However, medical AI research has experienced substantial growth, attracting considerable attention from researchers and practitioners. Objective In the absence of an existing framework, this study aims to outline the current landscape of medical AI research and provide insights into its future developments by examining all AI-related studies within PubMed over the past 2 decades. We also propose potential data acquisition and analysis methods, developed using Python (version 3.11) and to be executed in Spyder IDE (version 5.4.3), for future analogous research. Methods Our dual-pronged approach involved (1) retrieving publication metadata related to AI from PubMed (spanning 2000-2022) via Python, including titles, abstracts, authors, journals, country, and publishing years, followed by keyword frequency analysis and (2) classifying relevant topics using latent Dirichlet allocation, an unsupervised machine learning approach, and defining the research scope of AI in medicine. In the absence of a universal medical AI taxonomy, we used an AI dictionary based on the European Commission Joint Research Centre AI Watch report, which emphasizes 8 domains: reasoning, planning, learning, perception, communication, integration and interaction, service, and AI ethics and philosophy. Results From 2000 to 2022, a comprehensive analysis of 307,701 AI-related publications from PubMed highlighted a 36-fold increase. The United States emerged as a clear frontrunner, producing 68,502 of these articles. Despite its substantial contribution in terms of volume, China lagged in terms of citation impact. Diving into specific AI domains, as the Joint Research Centre AI Watch report categorized, the learning domain emerged dominant. Our classification analysis meticulously traced the nuanced research trajectories across each domain, revealing the multifaceted and evolving nature of AI’s application in the realm of medicine. Conclusions The research topics have evolved as the volume of AI studies increases annually. Machine learning remains central to medical AI research, with deep learning expected to maintain its fundamental role. Empowered by predictive algorithms, pattern recognition, and imaging analysis capabilities, the future of AI research in medicine is anticipated to concentrate on medical diagnosis, robotic intervention, and disease management. Our topic modeling outcomes provide a clear insight into the focus of AI research in medicine over the past decades and lay the groundwork for predicting future directions. The domains that have attracted considerable research attention, primarily the learning domain, will continue to shape the trajectory of AI in medicine. Given the observed growing interest, the domain of AI ethics and philosophy also stands out as a prospective area of increased focus.
We are introducing SM70, a 70 billion-parameter Large Language Model that is specifically designed for SpassMed's medical devices under the brand name 'JEE1' (pronounced as G1 and means 'Life'). This large language model provides more accurate and safe responses to medical-domain questions. To fine-tune SM70, we used around 800K data entries from the publicly available dataset MedAlpaca. The Llama2 70B open-sourced model served as the foundation for SM70, and we employed the QLoRA technique for fine-tuning. The evaluation is conducted across three benchmark datasets - MEDQA - USMLE, PUBMEDQA, and USMLE - each representing a unique aspect of medical knowledge and reasoning. The performance of SM70 is contrasted with other notable LLMs, including Llama2 70B, Clinical Camel 70 (CC70), GPT 3.5, GPT 4, and Med-Palm, to provide a comparative understanding of its capabilities within the medical domain. Our results indicate that SM70 outperforms several established models in these datasets, showcasing its proficiency in handling a range of medical queries, from fact-based questions derived from PubMed abstracts to complex clinical decision-making scenarios. The robust performance of SM70, particularly in the USMLE and PUBMEDQA datasets, suggests its potential as an effective tool in clinical decision support and medical information retrieval. Despite its promising results, the paper also acknowledges the areas where SM70 lags behind the most advanced model, GPT 4, thereby highlighting the need for further development, especially in tasks demanding extensive medical knowledge and intricate reasoning.
Peilun Shi, Jianing Qiu, Sai Mu Dalike Abaxi
et al.
In this paper, we examine the recent Segment Anything Model (SAM) on medical images, and report both quantitative and qualitative zero-shot segmentation results on nine medical image segmentation benchmarks, covering various imaging modalities, such as optical coherence tomography (OCT), magnetic resonance imaging (MRI), and computed tomography (CT), as well as different applications including dermatology, ophthalmology, and radiology. Those benchmarks are representative and commonly used in model development. Our experimental results indicate that while SAM presents remarkable segmentation performance on images from the general domain, its zero-shot segmentation ability remains restricted for out-of-distribution images, e.g., medical images. In addition, SAM exhibits inconsistent zero-shot segmentation performance across different unseen medical domains. For certain structured targets, e.g., blood vessels, the zero-shot segmentation of SAM completely failed. In contrast, a simple fine-tuning of it with a small amount of data could lead to remarkable improvement of the segmentation quality, showing the great potential and feasibility of using fine-tuned SAM to achieve accurate medical image segmentation for a precision diagnostics. Our study indicates the versatility of generalist vision foundation models on medical imaging, and their great potential to achieve desired performance through fine-turning and eventually address the challenges associated with accessing large and diverse medical datasets in support of clinical diagnostics.
Machine learning in medical imaging often faces a fundamental dilemma, namely, the small sample size problem. Many recent studies suggest using multi-domain data pooled from different acquisition sites/centers to improve statistical power. However, medical images from different sites cannot be easily shared to build large datasets for model training due to privacy protection reasons. As a promising solution, federated learning, which enables collaborative training of machine learning models based on data from different sites without cross-site data sharing, has attracted considerable attention recently. In this paper, we conduct a comprehensive survey of the recent development of federated learning methods in medical image analysis. In this survey, we first introduce the background knowledge of federated learning for dealing with privacy protection and collaborative learning issues in medical imaging. We then present a comprehensive review of recent advances in federated learning methods for medical image analysis. Specifically, existing methods are categorized based on three critical aspects of a federated learning system, including client end, server end, and communication techniques. In each category, we summarize the existing federated learning methods according to specific research problems in medical image analysis and also provide insights into the motivations of different approaches. In addition, we provide a review of existing benchmark medical imaging datasets and software platforms for current federated learning research. We also conduct an experimental study to empirically evaluate typical federated learning methods for medical image analysis. This survey can help to better understand the current research status, challenges, and potential research opportunities in this promising research field.
Abstract Background The fourth section of the 1967 Abortion Act states that individuals (including health care practitioners) do not have to participate in an abortion if they have a conscientious objection. A conscientious objection is a refusal to participate in abortion on the grounds of conscience. This may be informed by religious, moral, philosophical, ethical, or personal beliefs. Currently, there is very little investigation into the impact of conscientious objection on service users in Britain. The perspectives of service users are imperative in understanding the real-world consequences and potential impact of conscientious objection and should be considered when creating and reviewing policies and guidelines. This research provided a platform for women and those who can become pregnant to share their experiences and opinions at a time when these voices are largely excluded in the great tradition of Western political philosophy and law-making processes. Method Five service users were interviewed using a narrative interview approach to uncover their abortion journeys and experiences of conscientious objection. Findings The findings were presented as found poems and uncovered that doctors are not always: informing service users that they have a conscientious objection to abortion, giving service users enough information to access abortion (indirect referral), treating them non-judgmentally, and providing medically correct information. Service users did not experience burdens such as long waiting times and were still able to access legal abortion. However, service users did experience negative emotional effects, as they were often left feeling scared, angry, and hopeless when they were not referred and/or were mistreated. Conclusions Findings indicate that conscientious objection could work in practice. However, it is currently failing some individuals on an emotional level, as not all doctors are adhering to guidelines. Conscientious objection in Britain needs to be addressed, to ensure service users receive fair, impartial, non-judgmental care.