Significance: Differences in immune functioning stem from multiple factors, including sex and aging. However, the specific roles of these variables in immunity remain elusive. We profiled immunocytes from young and old males and females at single-cell resolution and constructed a precise atlas of blood-circulating immunocytes. T cell– and B cell–activated signals were higher in young females than males, while aging increased the sex-related differences in immunocytes, cellular composition, and inflammatory signaling. Additionally, males showed a higher accumulation of inflammatory factors during aging, whereas cell–cell communication analysis revealed different trends in gene expression between females and males with aging. These findings might aid in the understanding of the mechanisms underlying sex-based differences in immunity and disease susceptibility across the lifespan.

Background: COVID‐19 is currently a global pandemic, but the response of human immune system to severe acute respiratory syndrome coronavirus 2 (SARS‐CoV‐2) infection remains unclear. Noncoding RNAs serve as immune regulators and thus may play a critical role in disease progression.Methods: We performed multi‐transcriptome sequencing of both noncoding RNAs and mRNAs isolated from the red blood cell depleted whole blood of moderate and severe COVID‐19 patients. The functions of noncoding RNAs were validated by analyses of the expression of downstream mRNAs. We further utilized the single‐cell RNA‐seq data of COVID‐19 patients from Wilk et al. and Chua et al. to characterize noncoding RNA functions in different cell types.Results: We defined four types of microRNAs with different expression tendencies that could serve as biomarkers for COVID‐19 progress. We also identified miR‐146a‐5p, miR‐21‐5p, miR‐142‐3p, and miR‐15b‐5p as potential contributors to the disease pathogenesis, possibly serving as biomarkers of severe COVID‐19 and as candidate therapeutic targets. In addition, the transcriptome profiles consistently suggested hyperactivation of the immune response, loss of T‐cell function, and immune dysregulation in severe patients.Conclusions: Collectively, these findings provide a comprehensive view of the noncoding and coding transcriptional landscape of peripheral immune cells during COVID‐19, furthering our understanding and offering novel insights into COVID‐19 pathogenesis.

Large‐scale artificial intelligence (AI) models such as ChatGPT have the potential to improve performance on many benchmarks and real‐world tasks. However, it is difficult to develop and maintain these models because of their complexity and resource requirements. As a result, they are still inaccessible to healthcare industries and clinicians. This situation might soon be changed because of advancements in graphics processing unit (GPU) programming and parallel computing. More importantly, leveraging existing large‐scale AIs such as GPT‐4 and Med‐PaLM and integrating them into multiagent models (e.g., Visual‐ChatGPT) will facilitate real‐world implementations. This review aims to raise awareness of the potential applications of these models in healthcare. We provide a general overview of several advanced large‐scale AI models, including language models, vision‐language models, graph learning models, language‐conditioned multiagent models, and multimodal embodied models. We discuss their potential medical applications in addition to the challenges and future directions. Importantly, we stress the need to align these models with human values and goals, such as using reinforcement learning from human feedback, to ensure that they provide accurate and personalized insights that support human decision‐making and improve healthcare outcomes.

Background: Large language models (LLMs) demonstrated advanced performance in processing clinical information. However, commercially available LLMs lack specialized medical knowledge and remain susceptible to generating inaccurate information. Given the need for self-management in diabetes, patients commonly seek information online. We introduce the Retrieval-augmented Information System for Enhancement (RISE) framework and evaluate its performance in enhancing LLMs to provide accurate responses to diabetes-related inquiries. Objective: This study aimed to evaluate the potential of the RISE framework, an information retrieval and augmentation tool, to improve the LLM’s performance to accurately and safely respond to diabetes-related inquiries. Methods: The RISE, an innovative retrieval augmentation framework, comprises 4 steps: rewriting query, information retrieval, summarization, and execution. Using a set of 43 common diabetes-related questions, we evaluated 3 base LLMs (GPT-4, Anthropic Claude 2, Google Bard) and their RISE-enhanced versions respectively. Assessments were conducted by clinicians for accuracy and comprehensiveness and by patients for understandability. Results: The integration of RISE significantly improved the accuracy and comprehensiveness of responses from all 3 base LLMs. On average, the percentage of accurate responses increased by 12% (15/129) with RISE. Specifically, the rates of accurate responses increased by 7% (3/43) for GPT-4, 19% (8/43) for Claude 2, and 9% (4/43) for Google Bard. The framework also enhanced response comprehensiveness, with mean scores improving by 0.44 (SD 0.10). Understandability was also enhanced by 0.19 (SD 0.13) on average. Data collection was conducted from September 30, 2023 to February 5, 2024. Conclusions: The RISE significantly improves LLMs’ performance in responding to diabetes-related inquiries, enhancing accuracy, comprehensiveness, and understandability. These improvements have crucial implications for RISE’s future role in patient education and chronic illness self-management, which contributes to relieving medical resource pressures and raising public awareness of medical knowledge.

Fundus fluorescein angiography (FFA) is a crucial diagnostic tool for chorioretinal diseases, but its interpretation requires significant expertise and time. Prior studies have used Artificial Intelligence (AI)-based systems to assist FFA interpretation, but these systems lack user interaction and comprehensive evaluation by ophthalmologists. Here, we used large language models (LLMs) to develop an automated interpretation pipeline for both report generation and medical question-answering (QA) for FFA images. The pipeline comprises two parts: an image-text alignment module (Bootstrapping Language-Image Pre-training) for report generation and an LLM (Llama 2) for interactive QA. The model was developed using 654,343 FFA images with 9392 reports. It was evaluated both automatically, using language-based and classification-based metrics, and manually by three experienced ophthalmologists. The automatic evaluation of the generated reports demonstrated that the system can generate coherent and comprehensible free-text reports, achieving a BERTScore of 0.70 and F1 scores ranging from 0.64 to 0.82 for detecting top-5 retinal conditions. The manual evaluation revealed acceptable accuracy (68.3%, Kappa 0.746) and completeness (62.3%, Kappa 0.739) of the generated reports. The generated free-form answers were evaluated manually, with the majority meeting the ophthalmologists’ criteria (error-free: 70.7%, complete: 84.0%, harmless: 93.7%, satisfied: 65.3%, Kappa: 0.762–0.834). This study introduces an innovative framework that combines multi-modal transformers and LLMs, enhancing ophthalmic image interpretation, and facilitating interactive communications during medical consultation.

Although long-read single-cell RNA isoform sequencing (scISO-Seq) can reveal alternative RNA splicing in individual cells, it suffers from a low read throughput. Here, we introduce HIT-scISOseq, a method that removes most artifact cDNAs and concatenates multiple cDNAs for PacBio circular consensus sequencing (CCS) to achieve high-throughput and high-accuracy single-cell RNA isoform sequencing. HIT-scISOseq can yield >10 million high-accuracy long-reads in a single PacBio Sequel II SMRT Cell 8M. We also report the development of scISA-Tools that demultiplex HIT-scISOseq concatenated reads into single-cell cDNA reads with >99.99% accuracy and specificity. We apply HIT-scISOseq to characterize the transcriptomes of 3375 corneal limbus cells and reveal cell-type-specific isoform expression in them. HIT-scISOseq is a high-throughput, high-accuracy, technically accessible method and it can accelerate the burgeoning field of long-read single-cell transcriptomics.