BACKGROUND: 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.
METHODS: 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.
RESULTS: 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.
CONCLUSIONS: 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.

Telomere length (TL) is an important biological variable that can influence a variety of disease-related complex traits as well as host-environment interactions such as drug and nutritional responses. Chronic kidney disease (CKD) is a common global health challenge especially with the currently aging world population. We conducted a PubMed database search according to the preferred reporting items for systematic reviews and meta-analysis (PRISMA) guidelines for systematic reviews. Studies in adults (18 years and above) in which TL was determined and correlated with CKD, renal traits, and function were included, while animal model studies were excluded. Nine studies comprising 7829 participants, published between 2005 and 2016, met the inclusion criteria. These included eight observational studies (six being prospective), and one clinical trial. Participants in two studies were diabetic patients with varying stages of CKD, and nondialysis chronic glomerulonephritis CKD patients in two other studies. TL measurements used polymerase chain reaction in five studies, terminal restriction fragmentation in three studies, and quantitative fluorescence in situ hybridization in one study. Short TL was independently associated with increased risk of prevalent microalbuminuria in diabetic men with CKD (p = 0.007). Among CKD patients with heterogeneous etiologies, however, there was an unadjusted lower risk (p < 0.001). Short TL was significantly associated with CKD progression among smokers (p = 0.001) and diabetic patients (p = 0.03). On the other hand, long TL was paradoxically associated with longer diagnosed duration of moderate CKD. We postulate that shortening TL might be associated with CKD prevalence/occurrence or declining kidney function, but this association is likely offset by the cellular telomere reparative process in those surviving longer with CKD. This systematic review underscores the need for future omics and human genetics research to delineate the contribution of TL to CKD, renal dysfunction, and related health outcomes. Telomeres and telomerase activity hold great promise for CKD risk stratification and personalized medicine.