Explore the vast range of titles available.

Diabetic Retinopathy (DR) is a major cause of blindness worldwide. Early detection and treatment are crucial to prevent vision loss, making accurate and timely diagnosis critical. Deep learning technology has shown promise in the automated diagnosis of DR, and in particular, multi-lesion segmentation tasks. In this paper, we propose a novel Transformer-based model for DR segmentation that incorporates hyperbolic embeddings and a spatial prior module. The proposed model is primarily built on a traditional Vision Transformer encoder and further enhanced by incorporating a spatial prior module for image convolution and feature continuity, followed by feature interaction processing using the spatial feature injector and extractor. Hyperbolic embeddings are used to classify feature matrices from the model at the pixel level. We evaluated the proposed model’s performance on the publicly available datasets and compared it with other widely used DR segmentation models. The results show that our model outperforms these widely used DR segmentation models. The incorporation of hyperbolic embeddings and a spatial prior module into the Vision Transformer-based model significantly improves the accuracy of DR segmentation. The hyperbolic embeddings enable us to better capture the underlying geometric structure of the feature matrices, which is important for accurate segmentation. The spatial prior module improves the continuity of the features and helps to better distinguish between lesions and normal tissues. Overall, our proposed model has potential for clinical use in automated DR diagnosis, improving accuracy and speed of diagnosis. Our study shows that the integration of hyperbolic embeddings and a spatial prior module with a Vision Transformer-based model improves the performance of DR segmentation models. Future research can explore the application of our model to other medical imaging tasks, as well as further optimization and validation in real-world clinical settings.

Traditional methods for synthesizing nanozymes are often time-consuming and complex, hindering efficiency. Artificial intelligence (AI) has the potential to simplify these processes, but there are very few dedicated nanozyme databases available, limiting the resources for research and application. To address this gap, we developed AI-ZYMES, a comprehensive nanozyme database featuring 1,085 entries and 400 types of nanozymes. The platform incorporates several key innovations that distinguish it from existing databases: Firstly, standardized Data Curation: AI-ZYMES resolves inconsistencies in catalytic metrics (e.g., K m , V max ), morphologies, and dispersion systems, enabling reliable cross-study comparisons, something that existing resources like DiZyme and nanozymes.net lack.Secondly, dual AI Framework: A gradient-boosting regressor predicts kinetic constants (K m , V max , K cat ) with an R 2 up to 0.85, while an AdaBoost classifier identifies enzyme-mimicking activities based solely on nanozyme names, surpassing traditional random forest models in predictive accuracy.Lastly, ChatGPT-based Synthesis Assistant: The platform includes an AI-driven assistant for literature extraction (67.55% accuracy) and synthesis pathway generation via semantic analysis (90% accuracy). This reduces manual effort and minimizes errors in large language model outputs, ensuring high-quality results.These innovations make AI-ZYMES a valuable tool for accelerating nanozyme research and application, including antimicrobial therapy, biosensing, and environmental remediation. The platform improves data accessibility, reduces experimental redundancy, and speeds up the translation of discoveries into practical use. By bridging the data fragmentation and predictive limitations of existing systems, AI-ZYMES establishes a new benchmark for AI-driven advancements in nanomaterials.

Chinese patent medicine (CPM) is a typical type of traditional Chinese medicine (TCM) preparation that uses Chinese herbs as raw materials and is an important means of treating diseases in TCM. Chinese patent medicine instructions (CPMI) serve as a guide for patients to use drugs safely and effectively. In this study, we apply a pre-trained language model to the domain of CPM. We have meticulously assembled, processed, and released the first CPMI dataset and fine-tuned the ChatGLM-6B base model, resulting in the development of CPMI-ChatGLM. We employed consumer-grade graphics cards for parameter-efficient fine-tuning and investigated the impact of LoRA and P-Tuning v2, as well as different data scales and instruction data settings on model performance. We evaluated CPMI-ChatGLM using BLEU, ROUGE, and BARTScore metrics. Our model achieved scores of 0.7641, 0.8188, 0.7738, 0.8107, and − 2.4786 on the BLEU-4, ROUGE-1, ROUGE-2, ROUGE-L and BARTScore metrics, respectively. In comparison experiments and human evaluation with four large language models of similar parameter scales, CPMI-ChatGLM demonstrated state-of-the-art performance. CPMI-ChatGLM demonstrates commendable proficiency in CPM recommendations, making it a promising tool for auxiliary diagnosis and treatment. Furthermore, the various attributes in the CPMI dataset can be used for data mining and analysis, providing practical application value and research significance.

Background Reliable identification of cancer subtypes is crucial for devising personalized treatment strategies. Integrating multi-omics data has proven to be an effective method for analyzing cancer subtypes. By combining molecular information across various layers, a more comprehensive understanding of biological characteristics and disease mechanisms can be achieved. Results We propose DEGCN, a novel deep learning model that integrates a three-channel Variational Autoencoder (VAE) for multi-omics dimensionality reduction and a densely connected Graph Convolutional Network (GCN) for effective subtype classification. DEGCN leverages the complementary strengths of non-linear feature extraction and graph-based relational learning, enabling accurate and robust classification of renal cancer subtypes. Experimental results demonstrate that DEGCN achieves a cross-validated classification accuracy of 97.06% ± 2.04% on renal cancer data, outperforming conventional machine learning algorithms and state-of-the-art deep learning models. Moreover, its generalization ability is validated on breast and gastric cancer datasets from TCGA, with cross-validated classification accuracies of 89.82% ± 2.29% and 88.64% ± 5.24%, respectively, indicating strong cross-cancer predictive performance. Conclusion The study highlights the outstanding performance of DEGCN in heterogeneous data integration and classification accuracy, demonstrating the model’s potential in cancer subtype prediction and its application in guiding clinical treatment.

Traditional Chinese Medicine (TCM) case records encapsulate vast clinical experiences and theoretical insights, holding significant research and practical value. However, traditional case studies face challenges such as large data volumes, complex information, and difficulties in efficient retrieval and analysis. This study aimed to address these issues by leveraging modern data techniques to improve access and analysis of TCM case records. A total of 679 case records from Wang Zhongqi, a renowned physician of Xin'an Medicine, a branch of TCM, covering 41 diseases, were selected. The study involved four stages: pattern layer construction, knowledge extraction, integration, and data storage and visualization. A large language model (LLM) was employed to automatically extract key entities, including symptoms, pathogenesis, treatment principles, and prescriptions. These were structured into a TCM case knowledge graph. The LLM successfully identified and extracted relevant entities, which were then organized into relational triples. A TCM case query system based on natural language input was developed. The system's performance, evaluated using the RAGAS framework, achieved high scores: 0.9375 in faithfulness, 0.9686 in answer relevancy, and 0.9500 in context recall; In human evaluations, the levels of safety and usability are significantly higher than those of LLMs without using RAG. The results demonstrate that integrating LLMs with a knowledge graph significantly enhances the efficiency and accuracy of retrieving TCM case information. This approach could play a crucial role in modernizing TCM research and improving access to clinical insights. Future research may explore expanding the dataset and refining the query system for broader applications.

Large Language Models (LLMs) play a crucial role in clinical information processing, showcasing robust generalization across diverse language tasks. However, existing LLMs, despite their significance, lack optimization for clinical applications, presenting challenges in terms of illusions and interpretability. The Retrieval-Augmented Generation (RAG) model addresses these issues by providing sources for answer generation, thereby reducing errors. This study explores the application of RAG technology in clinical gastroenterology to enhance knowledge generation on gastrointestinal diseases. We fine-tuned the embedding model using a corpus consisting of 25 guidelines on gastrointestinal diseases. The fine-tuned model exhibited an 18% improvement in hit rate compared to its base model, gte-base-zh. Moreover, it outperformed OpenAI's Embedding model by 20%. Employing the RAG framework with the llama-index, we developed a Chinese gastroenterology chatbot named \"GastroBot,\" which significantly improves answer accuracy and contextual relevance, minimizing errors and the risk of disseminating misleading information. When evaluating GastroBot using the RAGAS framework, we observed a context recall rate of 95%. The faithfulness to the source, stands at 93.73%. The relevance of answers exhibits a strong correlation, reaching 92.28%. These findings highlight the effectiveness of GastroBot in providing accurate and contextually relevant information about gastrointestinal diseases. During manual assessment of GastroBot, in comparison with other models, our GastroBot model delivers a substantial amount of valuable knowledge while ensuring the completeness and consistency of the results. Research findings suggest that incorporating the RAG method into clinical gastroenterology can enhance the accuracy and reliability of large language models. Serving as a practical implementation of this method, GastroBot has demonstrated significant enhancements in contextual comprehension and response quality. Continued exploration and refinement of the model are poised to drive forward clinical information processing and decision support in the gastroenterology field.

Patients with Wilson’s disease (WD) suffer from prospective memory (PM) impairment, and some of patients develop cognitive impairment. However, very little is known about how brain structure and function changes effect PM in WD. Here, we employed multimodal neuroimaging data acquired from 22 WD patients and 26 healthy controls (HC) who underwent three-dimensional T1-weighted, diffusion tensor imaging (DTI), and resting state functional magnetic resonance imaging (RS-fMRI). We investigated gray matter (GM) volumes with voxel-based morphometry, DTI metrics using the fiber tractography method, and RS-fMRI using the seed-based functional connectivity method. Compared with HC, WD patients showed GM volume reductions in the basal ganglia (BG) and occipital fusiform gyrus, as well as volume increase in the visual association cortex. Moreover, whiter matter (WM) tracks of WD were widely impaired in association and limbic fibers. WM tracks in association fibers are significant related to PM in WD patients. Relative to HC, WD patients showed that the visual association cortex functionally connects to the thalamus and hippocampus, which is associated with global cognitive function in patients with WD. Together, these findings suggested that PM impairment in WD may be modulated by aberrant WM in association fibers, and that GM volume changes in the association cortex has no direct effect on cognitive status, but indirectly affect global cognitive function by its aberrant functional connectivity (FC) in patients with WD. Our findings may provide a new window to further study how WD develops into cognitive impairment, and deepen our understanding of the cognitive status and neuropathology of WD.

Gastric cancer (GC) is one of the most common malignancies and is a highly heterogeneous disease; it is also a leading cause of cancer-related death. Owing to the complexity and late-stage diagnosis of GC, the prognosis remains poor. To explore potential biomarkers for GC, GC patient transcriptome data were subjected to a comprehensive approach involving machine learning, binary nomogram prediction model construction, the topological algorithm of CytoHubba, and Kaplan–Meier and Mendelian randomization (MR) analyses. First, gene expression data for normal and GC tissues were assessed via machine learning and the topological algorithm of CytoHubba, and a total of 792 differentially expressed genes (DEGs) and nine core genes were identified. Kaplan–Meier analysis and analysis of a nomogram binary prediction model for the core genes revealed that the expression level of BRCA1 was closely and significantly correlated with the survival time of GC patients, suggesting that BRCA1 may be considered a valuable biomarker for GC diagnosis. Furthermore, MR analysis revealed that BRCA1 promotes the transformation of normal cells into GC cells by regulating NADPH levels, leading to a continuous increase in oxidative stress. This is one of the initial comprehensive analysis involving MR and multidimensional approaches; it revealed the significant role of BRCA1 in GC, providing new ideas on drugs and targets for GC clinical treatment.

The large-scale language model, GPT-4-1106-preview, supports text of up to 128 k characters, which has enhanced the capability of processing vast quantities of text. This model can perform efficient and accurate text data mining without the need for retraining, aided by prompt engineering. The research approach includes prompt engineering and text vectorization processing. In this study, prompt engineering is applied to assist ChatGPT in text mining. Subsequently, the mined results are vectorized and incorporated into a local knowledge base. After cleansing 306 medical papers, data extraction was performed using ChatGPT. Following a validation and filtering process, 241 medical case data entries were obtained, leading to the construction of a local medical knowledge base. Additionally, drawing upon the Langchain framework and utilizing the local knowledge base in conjunction with ChatGPT, we successfully developed a fast and reliable chatbot. This chatbot is capable of providing recommended diagnostic and treatment information for various diseases. The performance of the designed ChatGPT model, which was enhanced by data from the local knowledge base, exceeded that of the original model by 7.90% on a set of medical questions. ChatGPT, assisted by prompt engineering, demonstrates effective data mining capabilities for large-scale medical texts. In the future, we plan to incorporate a richer array of medical case data, expand the scale of the knowledge base, and enhance ChatGPT's performance in the medical field.