Explore the vast range of titles available.

This study proposes CRIBC, a novel Named Entity Recognition (NER) model tailored for Chinese medical texts, specifically focusing on diabetes‐related data. By improving entity recognition accuracy, CRIBC facilitates the construction of a comprehensive knowledge graph to enhance diabetes research and clinical decision‐making. CRIBC integrates Chinese‐RoBERTa‐WWM‐EXT, IDCNN, BiLSTM, and CRF to optimize entity extraction. The model was trained on the DiaKG dataset and validated on the CMeEE dataset. Performance was evaluated using precision, recall, and F1‐score. A diabetes knowledge graph was then constructed based on the extracted entities and relationships. CRIBC achieved an F1‐score of 80.88% on the DiaKG dataset and 67.91% on the CMeEE dataset, outperforming baseline models. The constructed knowledge graph contains 23,134 nodes and 42,520 edges, providing structured insights into diabetes management, aiding clinical decision‐making and medical research. CRIBC significantly enhances NER accuracy in Chinese medical texts, enabling efficient knowledge graph construction for diabetes management. Future research will focus on expanding datasets and refining the model's capabilities for broader medical applications. This study proposes CRIBC, an advanced Named Entity Recognition (NER) model tailored for Chinese medical text processing. By integrating Chinese‐RoBERTa‐WWM‐EXT with BiLSTM‐CRF and IDCNN, CRIBC enables more accurate entity extraction and knowledge representation. The resulting diabetes knowledge graph enhances information structuring, supporting clinical decision‐making and advancing medical text analysis.

Addressing the challenges in elucidating the mechanisms of complex diseases such as Type 2 Diabetes Mellitus (T2DM), this study aims to construct a domain-specific cross-medicine knowledge graph (CMKG) and develop a unified path scoring framework that couples graph embeddings with rule-based reasoning, enabling high-precision, interpretable prioritization and explanation of potential drug candidates. First, multi-source biomedical data from Hetionet, SymMap, TCMBank, STRING, and TTD were integrated. Using Jaccard and overlap-based fusion strategies, entity alignment and relation consolidation were performed to construct a deep CMKG bridged by genes. Second, four graph embedding models (TransE, DistMult, ComplEx, and RotatE) were introduced for link prediction and evaluated using MRR and Hits@K. Finally, to overcome the interpretability limitations of black-box predictions, AnyBURL rule learning was combined with depth-first search (DFS). We innovatively introduced an Ingredient Specificity Index (ISI) and a hybrid path confidence calibration mechanism, constructing a unified path scoring system incorporating length decay, node/relation weights, and experimental evidence bonuses to screen the most critical mechanistic paths. The constructed CMKG contains 15 entity types (245,235 entities) and 52 relation types (7,155,373 triples), covering 709 core T2DM genes. Link prediction stability tests across multiple random seeds showed that the ComplEx model consistently performed best in handling complex multi-mapping relations (MRR = 0.213 ± 0.004, Hits@10 = 0.418 ± 0.003). Consequently, the fully converged ComplEx model (Peak Hits@10 = 0.48) was utilized for comprehensive prediction. Retaining the top 100 predictions, Abelmoschus manihot and Topiramate ranked highest among TCM herbs and modern medicine compounds, respectively. Path analysis based on the scoring system revealed deep multi-target mechanisms, including insulin signaling sensitization, inflammatory regulation, and chromatin/cell-cycle intervention. The proposed gene-bridged graph embedding and unified path scoring framework successfully translates probabilistic predictions into biologically traceable semantic explanations. Rigorous ablation and parameter sensitivity experiments confirm that the framework achieves a robust balance between knowledge coverage and explanatory specificity, providing a transparent, robust, and scalable methodological foundation for candidate drug prioritization in complex diseases.

Diabetes is a worldwide health issue affecting millions of people. Machine learning methods have shown promising results in improving diabetes prediction, particularly through the analysis of gene expression data. While gene expression data can provide valuable insights, challenges arise from the fact that the number of patients in expression datasets is usually limited, and the data from different datasets with different gene expressions cannot be easily combined. This work proposes a novel approach to address these challenges by integrating multiple gene expression datasets and domain-specific knowledge using knowledge graphs, a unique tool for biomedical data integration, and to learn uniform patient representations for subjects contained in different incompatible datasets. Different strategies and KG embedding methods are explored to generate vector representations, serving as inputs for a classifier. Extensive experiments demonstrate the efficacy of our approach, revealing weighted F1-score improvements in diabetes prediction up to 13% when integrating multiple gene expression datasets and domain-specific knowledge about protein functions and interactions.

Diabetes management requires constant monitoring and individualized adjustments. This study proposes a novel approach that leverages digital twins and personal health knowledge graphs (PHKGs) to revolutionize diabetes care. Our key contribution lies in developing a real-time, patient-centric digital twin framework built on PHKGs. This framework integrates data from diverse sources, adhering to HL7 standards and enabling seamless information access and exchange while ensuring high levels of accuracy in data representation and health insights. PHKGs offer a flexible and efficient format that supports various applications. As new knowledge about the patient becomes available, the PHKG can be easily extended to incorporate it, enhancing the precision and accuracy of the care provided. This dynamic approach fosters continuous improvement and facilitates the development of new applications. As a proof of concept, we have demonstrated the versatility of our digital twins by applying it to different use cases in diabetes management. These include predicting glucose levels, optimizing insulin dosage, providing personalized lifestyle recommendations, and visualizing health data. By enabling real-time, patient-specific care, this research paves the way for more precise and personalized healthcare interventions, potentially improving long-term diabetes management outcomes.

A digital twin is a virtual representation of a patient's disease, facilitating real-time monitoring, analysis, and simulation. This enables the prediction of disease progression, optimization of care delivery, and improvement of outcomes. Here, we introduce a digital twin framework for type 2 diabetes (T2D) that integrates machine learning with multiomic data, knowledge graphs, and mechanistic models. By analyzing a substantial multiomic and clinical dataset, we constructed predictive machine learning models to forecast disease progression. Furthermore, knowledge graphs were employed to elucidate and contextualize multiomic-disease relationships. Our findings not only reaffirm known targetable disease components but also spotlight novel ones, unveiled through this integrated approach. The versatile components presented in this study can be incorporated into a digital twin system, enhancing our grasp of diseases and propelling the advancement of precision medicine.

Non-Insulin-Dependent Diabetes Mellitus (NIDDM) is a chronic health condition caused by high blood sugar levels, and if not treated early, it can lead to serious complications i.e. blindness. Human Activity Recognition (HAR) offers potential for early NIDDM diagnosis, emerging as a key application for HAR technology. This research introduces DiabSense, a state-of-the-art smartphone-dependent system for early staging of NIDDM. DiabSense incorporates HAR and Diabetic Retinopathy (DR) upon leveraging the power of two different Graph Neural Networks (GNN). HAR uses a comprehensive array of 23 human activities resembling Diabetes symptoms, and DR is a prevalent complication of NIDDM. Graph Attention Network (GAT) in HAR achieved 98.32% accuracy on sensor data, while Graph Convolutional Network (GCN) in the Aptos 2019 dataset scored 84.48%, surpassing other state-of-the-art models. The trained GCN analyzed retinal images of four experimental human subjects for DR report generation, and GAT generated their average duration of daily activities over 30 days. The daily activities in non-diabetic periods of diabetic patients were measured and compared with the daily activities of the experimental subjects, which helped generate risk factors. Fusing risk factors with DR conditions enabled early diagnosis recommendations for the experimental subjects despite the absence of any apparent symptoms. The comparison of DiabSense system outcome with clinical diagnosis reports in the experimental subjects was conducted using the A1C test. The test results confirmed the accurate assessment of early diagnosis requirements for experimental subjects by the system. Overall, DiabSense exhibits significant potential for ensuring early NIDDM treatment, improving millions of lives worldwide.

Decision-making in the era of big data is always a challenge. Recently, various methods especially graph sampling have been presented to assist the decision more effectively. As real-world graphs are large, constantly evolving, and distributed in nature, it becomes necessary to sample their structures for many different goals. Therefore, acquiring a comprehensive and in-depth understanding of graph sampling is essential to strengthen this field. In addition, graph sampling techniques often rely on edge or vertex sampling without effective methods for rule or path sampling. In this paper, we propose a novel framework for the rule-based sampling method on fuzzy knowledge graphs. In this framework, fuzzy knowledge graphs are built on integrated databases from multiple sources. We design a purposive random sampling method based on fuzzy rules on graphs to prioritize important rules for output inference. The remaining important rules form the core structure of the fuzzy knowledge graph, known as the Fuzzy Knowledge Graph Structure (FKGS). This structure is considered as a compression mechanism to reduce computational complexity when representing and performing calculations for large-scale data problems. Experimental results based on benchmark datasets on diabetes mellitus show that the sampling method greatly reduces the calculation time while maintaining high accuracy. Moreover, the purposive random sampling method results in significantly higher accuracy than the random sampling method. Besides, the ANOVA method is also conducted to statistically validate the model. The results are significant for decision-making in the context of big data.

Artificial Intelligence (AI) has been dramatically applied to healthcare in various tasks to support clinicians in disease diagnosis and prognosis. It has been known that accurate diagnosis must be drawn from multiple evidence, namely clinical records, X-Ray images, IoT data, etc called the multi-modal data. Despite the existence of various approaches for multi-modal medical data fusion, the development of comprehensive systems capable of integrating data from multiple sources and modalities remains a considerable challenge. Besides, many machine learning models face difficulties in representation and computation due to the uncertainty and diversity of medical data. This study proposes a novel multi-modal fuzzy knowledge graph framework, called FKG-MM, which integrates multi-modal medical data from multiple sources, offering enhanced computational performance compared to unimodal data. In addition, the FKG-MM framework is based on the fuzzy knowledge graph model, one of the models that represent and compute effectively with medical data in tabular form. Through some experiment scenarios utilizing the well-known BRSET dataset on multi-modal diabetic retinopathy, it has been experimentally validated that the feature selection method, when combining image features with tabular medical data features, gives the highest reliability results among 5 methods including Feature Selection Method, Tensor Product, Hadamard Product, Filter Selection, and Wrapper Selection. In addition, the experiment also confirms that the accuracy of FKG-MM increases by 12–14% when combining image data with tabular medical data than the related methods diagnosing only on tabular data.

Background: The complexity and rapid progression of lesions in diabetic kidney disease pose significant challenges for clinical diagnosis and treatment. The advantages of Traditional Chinese Medicine (TCM) in diagnosing and treating this condition have gradually become evident. However, due to the disease’s complexity and the individualized approach to diagnosis and treatment in Traditional Chinese Medicine, Traditional Chinese Medicine guidelines have limitations in guiding the treatment of diabetic kidney disease. Most medical knowledge is currently stored in the process of recording medical records, which hinders the understanding of diseases and the acquisition of diagnostic and treatment knowledge among young doctors. Consequently, there is a lack of sufficient clinical knowledge to support the diagnosis and treatment of diabetic kidney disease in Traditional Chinese Medicine. Objective: To build a comprehensive knowledge graph for the diagnosis and treatment of diabetic kidney disease in Traditional Chinese Medicine, utilizing clinical guidelines, consensus, and real-world clinical data. On this basis, the knowledge of Traditional Chinese Medicine diagnosis and treatment of diabetic kidney disease was systematically combed and mined. Methods: Normative guideline data and actual medical records were used to construct a knowledge graph of Traditional Chinese Medicine diagnosis and treatment for diabetic kidney disease and the results obtained by data mining techniques enrich the relational attributes. Neo4j graph database was used for knowledge storage, visual knowledge display, and semantic query. Utilizing multi-dimensional relations with hierarchical weights as the core, a reverse retrieval verification process is conducted to address the critical problems of diagnosis and treatment put forward by experts. Results: 903 nodes and 1670 relationships were constructed under nine concepts and 20 relationships. Preliminarily a knowledge graph for Traditional Chinese Medicine diagnosis and treatment of diabetic kidney disease was constructed. Based on the multi-dimensional relationships, the diagnosis and treatment questions proposed by experts were validated through multi-hop queries of the graphs. The results were confirmed by experts and showed good outcomes. Conclusion: This study systematically combed the Traditional Chinese Medicine diagnosis and treatment knowledge of diabetic kidney disease by constructing the knowledge graph. Furthermore, it effectively solved the problem of “knowledge island”. Through visual display and semantic retrieval, the discovery and sharing of diagnosis and treatment knowledge of diabetic kidney disease were realized.

ROBOKOP (Reasoning Over Biomedical Objects linked in Knowledge Oriented Pathways) is an open-source, modular, biomedical, knowledge graph (KG)–based system comprised of several key components: the ROBOKOP KG; a user interface (UI); and a variety of supporting resources, including tools and services to support deep exploration of the ROBOKOP KG and each of its underlying knowledge sources. A custom software pipeline termed Operational Routine for the Ingest and Output of Networks (ORION) standardizes, integrates, and harmonizes ROBOKOP’s knowledge sources as interoperable KGs by leveraging the community-developed Biolink Model’s universal KG schema and upper-level biomedical ontology. A ROBOKOP Graphs interface exposes the ROBOKOP KG and the other interoperable KGs, thus supporting access independent of the UI. All components of ROBOKOP are publicly accessible. Herein, we describe the v1.0 major release of ROBOKOP and highlight its features and functionalities in several application use cases, including a validation use case on asthma gene targets and two user-provided exploratory use cases on cardiotoxicity related to exposure to brominated flame retardants and diabetes mellitus related to exposure to agricultural pesticides.