Challenges and barriers of using large language models (LLM) such as ChatGPT for diagnostic medicine with a focus on digital pathology - a recent scoping review.
The integration of large language models (LLMs) like ChatGPT in diagnostic medicine, with a focus on digital pathology, has garnered significant attention. However, understanding the challenges and barriers associated with the use of LLMs in this context is crucial for their successful implementation.
A scoping review was conducted to explore the challenges and barriers of using LLMs, in diagnostic medicine with a focus on digital pathology. A comprehensive search was conducted using electronic databases, including PubMed and Google Scholar, for relevant articles published within the past four years. The selected articles were critically analyzed to identify and summarize the challenges and barriers reported in the literature.
The scoping review identified several challenges and barriers associated with the use of LLMs in diagnostic medicine. These included limitations in contextual understanding and interpretability, biases in training data, ethical considerations, impact on healthcare professionals, and regulatory concerns. Contextual understanding and interpretability challenges arise due to the lack of true understanding of medical concepts and lack of these models being explicitly trained on medical records selected by trained professionals, and the black-box nature of LLMs. Biases in training data pose a risk of perpetuating disparities and inaccuracies in diagnoses. Ethical considerations include patient privacy, data security, and responsible AI use. The integration of LLMs may impact healthcare professionals' autonomy and decision-making abilities. Regulatory concerns surround the need for guidelines and frameworks to ensure safe and ethical implementation.
The scoping review highlights the challenges and barriers of using LLMs in diagnostic medicine with a focus on digital pathology. Understanding these challenges is essential for addressing the limitations and developing strategies to overcome barriers. It is critical for health professionals to be involved in the selection of data and fine tuning of the models. Further research, validation, and collaboration between AI developers, healthcare professionals, and regulatory bodies are necessary to ensure the responsible and effective integration of LLMs in diagnostic medicine.
Ullah E
，Parwani A
，Baig MM
，Singh R
... -
《Diagnostic Pathology》
Ethics of Procuring and Using Organs or Tissue from Infants and Newborns for Transplantation, Research, or Commercial Purposes: Protocol for a Bioethics Scoping Review.
Since the inception of transplantation, it has been crucial to ensure that organ or tissue donations are made with valid informed consent to avoid concerns about coercion or exploitation. This issue is particularly challenging when it comes to infants and younger children, insofar as they are unable to provide consent. Despite their vulnerability, infants' organs and tissues are considered valuable for biomedical purposes due to their size and unique properties. This raises questions about the conditions under which it is permissible to remove and use these body parts for transplantation, research, or commercial purposes. The aim of this protocol is to establish a foundation for a scoping review that will identify, clarify, and categorise the main ethical arguments regarding the permissibility of removing and using organs or tissues from infants. The scoping review will follow the methodology outlined by the Joanna Briggs Institute (JBI), consisting of five stages: (1) identifying the research question, (2) developing the search strategy, (3) setting inclusion criteria, (4) extracting data, and (5) presenting and analysing the results. We will include both published and unpublished materials that explicitly discuss the ethical arguments related to the procurement and use of infant organs or tissues in the biomedical context. The search will cover various databases, including the National Library of Medicine, Web of Science, EBSCO, and others, as well as grey literature sources. Two raters will independently assess the eligibility of articles, and data from eligible studies will be extracted using a standardised form. The extracted data will then be analysed descriptively through qualitative content analysis.
There has been debate about how to respect the rights and interests of organ and tissue donors since the beginning of transplantation practice, given the moral risks involved in procuring parts of their bodies and using them for transplantation or research. A major concern has been to ensure that, at a minimum, donation of organs or other bodily tissues for transplantation or research is done under conditions of valid informed consent, so as to avoid coercion or exploitation among other moral harms. In the case of infants and younger children, however, this concern poses special difficulties insofar as infants and younger children are deemed incapable of providing valid consent. Due to their diminutive size and other distinctive properties, infants' organs and tissues are seen as valuable for biomedical purposes. Yet, the heightened vulnerability of infants raises questions about when and whether it is ever permissible to remove these body parts or use them in research or for other purposes. The aim of this protocol is to form the basis of a systematic scoping review to identify, clarify, and systematise the main ethical arguments for and against the permissibility of removing and using infant or newborn (hereafter, "infant") organs or tissues in the biomedical context (i.e. for transplantation, research, or commercial purposes).
Our scoping review will broadly follow the well-established methodology outlined by the Joanna Briggs Institute ( Peters et al., 2020). We will follow a five-stage review process: (1) identification of the research question, (2) development of the search strategy, (3) inclusion criteria, (4) data extraction, and (5) presentation and analysis of the results. Published and unpublished bibliographic material (including reports, dissertations, book chapters, etc.) will be considered based on the following inclusion criteria: the presence of explicit (bio)ethical arguments or reasons (concept) for or against the procurement and use of organs or tissues from infants, defined as a child from birth until 1 year old (population), in the biomedical domain, including transplantation, research, and commercial development (context). We will search for relevant studies in the National Library of Medicine (including PubMed and MEDLINE), Virtual Health Library, Web of Science, Google Scholar, EBSCO, Google Scholar, PhilPapers, The Bioethics Literature Database (BELIT), EthxWeb as well as grey literature sources (e.g., Google, BASE, OpenGrey, and WorldCat) and the reference lists of key studies to identify studies suitable for inclusion. A three-stage search strategy will be used to determine the eligibility of articles, as recommended by the JBI methodological guidelines. We will exclude sources if (a) the full text is not accessible, (b) the main text is in a language other than English, or (c) the focus is exclusively on scientific, legal, or religious/theological arguments. All articles will be independently assessed for eligibility between two raters (MB & XL); data from eligible articles will be extracted and charted using a standardised data extraction form. The extracted data will be analysed descriptively using basic qualitative content analysis.
Ethical review is not required as scoping reviews are a form of secondary data analysis that synthesise data from publicly available sources. Our dissemination strategy includes peer review publication, presentation at conferences, and outreach to relevant stakeholders.
The results will be reported according to the PRISMA-ScR guidelines. An overview of the general data from the included studies will be presented in the form of graphs or tables showing the distribution of studies by year or period of publication, country of origin, and key ethical arguments. These results will be accompanied by a narrative summary describing how each included study or article relates to the aims of this review. Research gaps will be identified and limitations of the review will also be highlighted.
A paper summarising the findings from this review will be published in a peer-reviewed journal. In addition, a synthesis of the key findings will be disseminated to biomedical settings (e.g., conferences or workshops, potentially including ones linked to university hospitals) in the UK, USA, Türkiye, and Singapore. They will also be shared with the academic community and policy makers involved in the organ procurement organisations (OPO), which will potentially consider our recommendations in their decision-making processes regarding infant tissue/organ donation practice in these countries.
The use of a rigorous, well-established methodological framework will ensure the production of a high-quality scoping review that will contribute to the bioethics literature.A comprehensive search of disciplinary and cross-disciplinary databases will be undertaken to ensure coverage of all possible sources that meet the inclusion criteria for the review.This review will focus exclusively on infant tissue/organ procurement/use in biomedical contexts, providing a comprehensive and reliable source of ethical arguments for future debates on this sensitive topic.The review will be limited to articles published in English, which increases the risk of missing relevant sources published in other languages.The review will be limited to articles for which the full text is available, which increases the risk of missing relevant sources that otherwise may have been included in the scoping review had the full text been accessible.
Barış M
，Lim X
，T Almonte M
，Shaw D
，Brierley J
，Porsdam Mann S
，Nguyen T
，Menikoff J
，Wilkinson D
，Savulescu J
，Earp BD
... -
《-》
The Role of Large Language Models in Transforming Emergency Medicine: Scoping Review.
Artificial intelligence (AI), more specifically large language models (LLMs), holds significant potential in revolutionizing emergency care delivery by optimizing clinical workflows and enhancing the quality of decision-making. Although enthusiasm for integrating LLMs into emergency medicine (EM) is growing, the existing literature is characterized by a disparate collection of individual studies, conceptual analyses, and preliminary implementations. Given these complexities and gaps in understanding, a cohesive framework is needed to comprehend the existing body of knowledge on the application of LLMs in EM.
Given the absence of a comprehensive framework for exploring the roles of LLMs in EM, this scoping review aims to systematically map the existing literature on LLMs' potential applications within EM and identify directions for future research. Addressing this gap will allow for informed advancements in the field.
Using PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) criteria, we searched Ovid MEDLINE, Embase, Web of Science, and Google Scholar for papers published between January 2018 and August 2023 that discussed LLMs' use in EM. We excluded other forms of AI. A total of 1994 unique titles and abstracts were screened, and each full-text paper was independently reviewed by 2 authors. Data were abstracted independently, and 5 authors performed a collaborative quantitative and qualitative synthesis of the data.
A total of 43 papers were included. Studies were predominantly from 2022 to 2023 and conducted in the United States and China. We uncovered four major themes: (1) clinical decision-making and support was highlighted as a pivotal area, with LLMs playing a substantial role in enhancing patient care, notably through their application in real-time triage, allowing early recognition of patient urgency; (2) efficiency, workflow, and information management demonstrated the capacity of LLMs to significantly boost operational efficiency, particularly through the automation of patient record synthesis, which could reduce administrative burden and enhance patient-centric care; (3) risks, ethics, and transparency were identified as areas of concern, especially regarding the reliability of LLMs' outputs, and specific studies highlighted the challenges of ensuring unbiased decision-making amidst potentially flawed training data sets, stressing the importance of thorough validation and ethical oversight; and (4) education and communication possibilities included LLMs' capacity to enrich medical training, such as through using simulated patient interactions that enhance communication skills.
LLMs have the potential to fundamentally transform EM, enhancing clinical decision-making, optimizing workflows, and improving patient outcomes. This review sets the stage for future advancements by identifying key research areas: prospective validation of LLM applications, establishing standards for responsible use, understanding provider and patient perceptions, and improving physicians' AI literacy. Effective integration of LLMs into EM will require collaborative efforts and thorough evaluation to ensure these technologies can be safely and effectively applied.
Preiksaitis C
，Ashenburg N
，Bunney G
，Chu A
，Kabeer R
，Riley F
，Ribeira R
，Rose C
... -
《JMIR Medical Informatics》
ResearchGate
(全网免费下载)
钛学术
(全网免费下载)
