JHJili Hu

Jili Hu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jili Hu has a total of 44 co-authors. Here are the top co-authors by number of shared publications:

  • Qingqing Zhou

    Scool of Medical Information Engineering, Anhui University of Chinese Medicine

    7 shared publications
  • Hongxing Kan

    School of Medical Information Engineering, Anhui University of Chinese Medicine, Hefei, China

    6 shared publications
  • Hongxing Kan

    School of Medical Informatics Engineering, Anhui University of Chinese Medicine, Hefei, China

    6 shared publications
  • Yuchen Duan

    School of Medical Information Engineering, Anhui University of Chinese Medicine

    6 shared publications
  • Can Liu

    School of Medical Information Engineering, Anhui University of Chinese Medicine, Hefei, China

    5 shared publications
  • Chi Qin

    School of Medical Information Engineering, Anhui University of Chinese Medicine

    5 shared publications

Latest Publications

  • Colorimetric discrimination of chrysanthemum polyphenols via tunable MOF-818 nanozyme sensor array

    by Rui Dong, Li Jin, Jili Hu, Jianhua Shu, Chun Ma, Chengle Li, Hongxing Kan, Liping Sun

  • Open Access

    From static guidelines to dynamic personalization: a novel AI-driven evidence-based paradigm for low-concentration atropine prescribing in myopia control

    by Yu Liu, Qingqing Zhou, Ling Ma, Yan Chen, Liping Sun, Jili Hu, Hongxing Kan

    Background: The rapid increase in the global incidence of myopia poses challenges for prevention and management. Evidence-based low-concentration atropine eye drops can effectively slow down the progression of myopia. However the massive and constantly updated research data place a burden on clinicians, especially in primary care or regions with limited resources, hindering knowledge integration and evidence-based decision-making. There is still a gap in patients' access to reliable and personalized guidance. To address this issue, we developed MyoATP-AI-powered evidence based decision support system specifically designed for low-concentration atropine myopia control, built upon a GraphRAG and chain-of-thought reasoning architecture. Methods: We systematically searched PubMed (2000–2025) for literature on “atropine, myopia”, screening 104 relevant clinical articles and constructing a specialized dataset. Based on this, we developed MyoATP-AI, an AI-assisted diagnostic system combining GraphRAG and chain-of-thought reasoning. The knowledge graph structure was optimized through community detection and graph embedding. System performance was evaluated using the BLEU, ROUGE, and RAGAS frameworks. Five ophthalmologists rated the system's safety, professionalism, fluency, comprehensiveness, and satisfaction. Finally, we compared the 2024 consensus opinion with MyoATP-AI. Results: MyoATP-AI demonstrated excellent performance in fidelity, relevance, and context recall. The automated scoring was high: BLEU (0.9479), ROUGE-1 (0.969), ROUGE-L (0.9677), fidelity (0.947), answer relevance (0.9587), and context recall rate (0.925). Experts gave highly positive evaluations of the system across all dimensions, indicating its great potential in clinical decision support and patient education, as it can provide safe, professional, fluent, and comprehensive responses. Discussion: MyoATP-AI is a knowledge graph-based question-answering system that integrates GraphRAG and CoT technology for low-concentration atropine control of myopia. It can provide accurate and useful clinical advice, which, on the one hand, can assist doctors in making evidence-based decisions, and on the other hand, can offer reliable and easily understandable medical guidance to patients. Future work will expand the dataset to enhance the system's applicability in different scenarios and help with the prevention and control of myopia.

  • Open Access

    Knowledge-guided adaptive educational support for traditional Chinese medicine using large language models and knowledge graphs: integrating Confucian educational principles

    by Jili Hu, Yuchen Duan, Qingqing Zhou, Denggao Zheng, Yu Li, Chi Qin, Yu Liu, Hongxing Kan, Fan Xu

    Introduction: The Confucian principle of “teaching students in accordance with their aptitude” remains challenging to implement at scale in Traditional Chinese Medicine (TCM) education. We developed an Intelligent TCM Tutoring System integrating a large language model (LLM) with a domain-specific knowledge graph (KG) derived from the Golden Mirror of Medicine and evaluated its system performance and short-term educational outcomes. Methods: System outputs were rated by five TCM teachers. In a three-group pedagogical experiment, 125 student volunteers were randomly allocated to self-directed learning, LLM-assisted learning, or learning with the integrated system, and 102 questionnaires were included in the final analysis. Results: The integrated system received higher expert ratings than the LLM baseline without KG integration in instructional content generation, intelligent question answering, and automated test generation and grading. Students using the integrated system achieved significantly higher immediate post-test scores than both comparison groups and reported more favorable post-session learning experience ratings in relevant comparisons. Discussion: These findings provide preliminary evidence that an LLM-KG system can enhance immediate learning outcomes and learning experiences in this educational setting.

  • Open Access

    CMA-DTI: a cross-modal fusion and attentive interaction network for interpretable drug-target interaction prediction

    by Chi Qin, Denggao Zheng, Ziyang Wang, Yu Li, Jingrui Cao, Houchun Qiu, Hongxing Kan, Liping Sun, Yu Liu, Jili Hu

    Background: Drug–target interaction (DTI) prediction is an important task in early-stage drug discovery. Although deep learning methods have improved predictive performance, effectively integrating heterogeneous drug representations and providing interpretable evidence for local interaction patterns remain challenging. Methods: We propose CMA-DTI, a cross-modal fusion and attentive interaction framework for DTI prediction. CMA-DTI integrates GCN-based molecular graph representations, ChemBERTa-derived SMILES representations, and ESM-2 protein residue embeddings. An intra-drug cross-attention module models soft relevance patterns between graph nodes and SMILES tokens, while a drug–protein multi-head attention module captures local relevance between fused drug nodes and protein residues. Results: On BindingDB and BioSNAP, CMA-DTI achieved competitive performance compared with representative machine learning and deep learning baselines. Cold-drug and cold-target evaluations showed that the model retained predictive ability under unseen-drug and unseen-target settings. Ablation results indicated that intra-drug cross-attention performed better than concatenation, addition, and gated fusion. In a representative structural case, attention-ranked residues showed moderate enrichment in ligand-binding pocket residues compared with random rankings. Conclusion: CMA-DTI provides a practical framework for multimodal DTI prediction by combining graph structure, chemical language representations, and protein language model embeddings. Its attention patterns offer hypothesis-generating molecular relevance evidence, but should not be interpreted as causal mechanistic explanations.


  • iCAM-Net: Interpretable herb-disease association prediction via cross-channel attention and molecular interaction signals

    by Denggao Zheng, Chi Qin, Ziyang Wang, Yu Liu, Yunlai Wang, Hongxing Kan, Jili Hu


  • Open Access

    A densely connected framework for cancer subtype classification

    by Yu Li, Denggao Zheng, Kaijie Sun, Chi Qin, Yuchen Duan, Qingqing Zhou, Yunxia Yin, Hongxing Kan, Jili Hu

    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. 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. 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.


  • Open Access

    Artificial intelligence driven platform for rapid catalytic performance assessment of nanozymes

    by Wenjie Xuan, Xiaofo Li, Honglei Gao, Luyao Zhang, Jili Hu, Liping Sun, Hongxing Kan

    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., Km, Vmax), 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 (Km, Vmax, Kcat) with an R2 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.


  • Top Cited Papers
    Open Access

    Research on a traditional Chinese medicine case-based question-answering system integrating large language models and knowledge graphs

    by Yuchen Duan, Qingqing Zhou, Yu Li, Chi Qin, Ziyang Wang, Hongxing Kan, Jili Hu

    Introduction: 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.Methods: 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.Results: 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.Discussion: 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.


  • Open Access

    GastroBot: a Chinese gastrointestinal disease chatbot based on the retrieval-augmented generation

    by Qingqing Zhou, Can Liu, Yuchen Duan, Kaijie Sun, Yu Li, Hongxing Kan, Zongyun Gu, Jianhua Shu, Jili Hu

    Introduction: 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.Methods: 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.Results: 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.Discussion: 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.


  • Open Access

    Exploring the Potential of Large Language Models in Radiological Imaging Systems: Improving User Interface Design and Functional Capabilities

    by Luyao Zhang, Jianhua Shu, Jili Hu, Fangfang Li, Junjun He, Peng Wang, Yiqing Shen

    Large language models (LLMs) have demonstrated remarkable capabilities in natural language processing tasks, including conversation, in-context learning, reasoning, and code generation. This paper explores the potential application of LLMs in radiological information systems (RIS) and assesses the impact of integrating LLMs on RIS development and human–computer interaction. We present ChatUI-RIS, a prototype chat-based user interface that leverages LLM capabilities to enhance RIS functionality and user experience. Through an exploratory study involving 26 medical students, we investigate the efficacy of natural language dialogue for learning and operating RIS. Our findings suggest that LLM integration via a chat interface can significantly improve operational efficiency, reduce learning time, and facilitate rapid expansion of RIS capabilities. By interacting with ChatUI-RIS using natural language instructions, medical students can access and retrieve radiology information in a conversational manner. The LLM-powered chat interface not only streamlines user interactions, but also enables more intuitive and efficient navigation of complex RIS functionalities. Furthermore, the natural language processing capabilities of LLMs can be harnessed to automatically generate code snippets and database queries, accelerating RIS development and customization. Preliminary observations indicate that integrating LLMs in RIS has the potential to revolutionize user interface design, enhance system capabilities, and ultimately improve the overall user experience for radiologists and medical professionals.