LIN SHUYUAN SHUYUAN

LIN SHUYUAN SHUYUAN


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 August 2024 in JMIR Medical Informatics
Verified
Journal Article
Open access
CLChang Liu
Chang Liu
ZLZhan Li
Zhan Li
L Jianmin Li
Jianmin Li
YQYiqian Qu
Yiqian Qu
YCYing Chang
Ying Chang
LSLIN SHUYUAN SHUYUAN
LIN SHUYUAN SHUYUAN
Background: Knowledge graphs (KGs) can integrate domain knowledge into a traditional Chinese medicine (TCM) intelligent syndrome differentiation model. However, the quality of current KGs in the TCM domain varies greatly, related to the lack of knowledge graph completion (KGC) and evaluation methods. Objective: This study aims to investigate KGC and evaluation methods tailored for TCM domain knowledge. Methods: In the KGC phase, according to the characteristics of TCM domain knowledge, we proposed a 3-step “entity-ontology-path” completion approach. This approach uses path reasoning, ontology rule reasoning, and association rules. In the KGC quality evaluation phase, we proposed a 3-dimensional evaluation framework that encompasses completeness, accuracy, and usability, using quantitative metrics such as complex network analysis, ontology reasoning, and graph representation. Furthermore, we compared the impact of different graph representation models on KG usability. Results: In the KGC phase, 52, 107, 27, and 479 triples were added by outlier analysis, rule-based reasoning, association rules, and path-based reasoning, respectively. In addition, rule-based reasoning identified 14 contradictory triples. In the KGC quality evaluation phase, in terms of completeness, KG had higher density and lower sparsity after completion, and there were no contradictory rules within the KG. In terms of accuracy, KG after completion was more consistent with prior knowledge. In terms of usability, the mean reciprocal ranking, mean rank, and hit rate of the first N tail entities predicted by the model (Hits@N) of the TransE, RotatE, DistMult, and ComplEx graph representation models all showed improvement after KGC. Among them, the RotatE model achieved the best representation. Conclusions: The 3-step completion approach can effectively improve the completeness, accuracy, and availability of KGs, and the 3-dimensional evaluation framework can be used for comprehensive KGC evaluation. In the TCM field, the RotatE model performed better at KG representation.

27 December 2024 in Journal of Medical Systems
Verified
Journal Article
Closed access
PDF file
YCYing Chang
Ying Chang
JYJianming Yin
Jianming Yin
JLJian-Min Li
Jian-Min Li
CLChang Liu
Chang Liu
LCLingyong Cao
Lingyong Cao
LSLIN SHUYUAN SHUYUAN
LIN SHUYUAN SHUYUAN

23 January 2025 in Frontiers in Endocrinology
Verified
Journal Article
Open access
PDF file
JYJianming Yin
Jianming Yin
CZChuanjie Zheng
Chuanjie Zheng
XLXiaoqian Lin
Xiaoqian Lin
CHChaoqiang Huang
Chaoqiang Huang
ZHZhanhui Hu
Zhanhui Hu
YQYiqian Qu
Yiqian Qu
Previous studies have indicated an association between UHR and diabetes risk, but evidence from large-scale and diverse populations remains limited. This study aims to verify UHR’s independent role in diabetes risk prediction in a large sample population and assess its applicability across different populations. We drew upon data from 30,813 participants collected during the 2005–2018 NHANES cycle. The association between UHR and the risk of diabetes was explored using multivariate logistic regression models, with key predictive factors identified through LASSO regression. Model effectiveness was evaluated through receiver operating characteristic (ROC) curves, decision curve analysis (DCA), and calibration metrics. Additionally, restricted cubic spline (RCS) and threshold effect assessments were applied to examine the nonlinear association between UHR and diabetes risk. The results showed that UHR levels were notably elevated in individuals with diabetes when compared to those without diabetes (p < 0.001). The occurrence of diabetes showed a marked increase across ascending UHR quartiles (6.63%, 10.88%, 14.15%, 18.02%; p < 0.001). Results from multivariate logistic regression indicated that elevated UHR was strongly linked to a heightened risk of diabetes; participants in the highest UHR quartile were found to have nearly four times the risk compared to those in the lowest quartile (OR = 4.063, 95% CI: 3.536–4.669, p < 0.001). Subgroup analyses demonstrated that the predictive effect of UHR was more pronounced in females. Key variables selected via LASSO regression improved the model’s performance. Restricted cubic spline (RCS) analysis indicated an inflection point at UHR = 10; beyond this point, diabetes risk accelerated, and when UHR exceeded 18, the risk increased significantly (OR > 1). ROC curve analysis showed the baseline model (M1) had an area under the curve (AUC) of 0.797, while the multivariable model (M4) after LASSO selection had an AUC of 0.789. Decision curve analysis and calibration curves validated the model’s predictive ability and consistency. This study indicates that UHR may be an independent predictor of diabetes risk, showing a positive correlation with diabetes and a more pronounced predictive effect in females.

1 January 2022
Verified
Journal Article
Closed access
YDY. Ding
Y. Ding
YLY. Liu
Y. Liu
YQY. Qu
Y. Qu
MLM. Lin
M. Lin
FDF. Dong
F. Dong
LSLIN SHUYUAN SHUYUAN
LIN SHUYUAN SHUYUAN

12 March 2026 in Frontiers in Medicine
Verified
Journal Article
Open access
PDF file
CLChang Liu
Chang Liu
YCYing Chang
Ying Chang
JLJianmin Li
Jianmin Li
YQYiqian Qu
Yiqian Qu
YLYu Li
Yu Li
LSLIN SHUYUAN SHUYUAN
LIN SHUYUAN SHUYUAN
Background: Large language models (LLMs) offer significant potential for intelligent question answering (Q&A) in healthcare, yet traditional knowledge representation methods fail to capture the complex, hierarchical nature of Traditional Chinese Medicine (TCM) knowledge systems. The lack of effective retrieval-augmented generation (RAG) frameworks specifically tailored for TCM’s unique epistemology limits applications. Objectives: This study aims to evaluate the effectiveness of a novel Tree-Organized Self-Reflective Retrieval (TOSRR) framework in enhancing LLM performance on TCM Q&A tasks through innovative knowledge organization and dynamic self-correction mechanisms. Methods: We developed a hierarchical knowledge representation system that structures TCM knowledge as subject-predicate-object-text (SPO-T) units within a tree-like architecture, enabling multi-dimensional relationships while preserving semantic context. Our iterative self-reflection mechanism implements dynamic knowledge retrieval and validation across textbook chapters and disciplines. Performance was evaluated using randomly selected questions from the TCM Medical Licensing Examination (MLE) and college Classics Course Exam (CCE), representing both standardized clinical knowledge and classical theory assessment. Results: When integrated with GPT-4, the TOSRR framework demonstrated a 19.85% improvement in absolute accuracy on the TCM MLE benchmark and increased recall accuracy from 27 to 38% on CCE datasets. Expert manual evaluation revealed substantial enhancements across critical dimensions: safety, consistency, explainability, compliance, and coherence, with a comprehensive improvement of 18.64 points. Retrieval-Augmented Generation Assessment (RAGAs) metrics confirmed the framework’s superior knowledge utilization, retrieval precision, and resistance to information noise compared to standard RAG approaches. Conclusion: The TOSRR framework enhances LLM performance in TCM knowledge tasks through its hierarchical knowledge representation and self-reflective retrieval approach. And the framework has potential for application in teaching.

21 April 2026 in Frontiers in Medicine
Verified
Journal Article
Open access
JLJianmin Li
Jianmin Li
YCYing Chang
Ying Chang
YLYujia Liu
Yujia Liu
YWYanwen Wang
Yanwen Wang
BOBinkai Ou
Binkai Ou
LZLi-Rong Zheng
Li-Rong Zheng
Background: Retrieval-augmented generation (RAG) technology can empower large language models (LLMs) to generate more accurate, professional, and timely responses without fine-tuning. However, due to the complex reasoning processes and substantial individual differences involved in traditional Chinese medicine (TCM) clinical diagnosis and treatment, traditional RAG methods often exhibit poor performance in this domain. Objective: To address the limitations of conventional RAG approaches in TCM applications, this study aims to develop an improved RAG framework tailored to the characteristics of TCM reasoning. Methods: We developed TCM-DiffRAG, an innovative RAG framework that integrates knowledge graphs (KG) with chains of thought (CoT). TCM-DiffRAG was evaluated on three distinctive TCM test datasets. Results: The experimental results demonstrated that TCM-DiffRAG achieved significant performance improvements over native LLMs. For example, the qwen-plus model achieved scores of 0.927, 0.361, and 0.038, which were significantly enhanced to 0.952, 0.788, and 0.356 with TCM-DiffRAG (McNemar test, p < 0.01). The improvements were even more pronounced for non-Chinese LLMs. Additionally, TCM-DiffRAG outperformed directly supervised fine-tuned (SFT) LLMs and other benchmark RAG methods. Conclusion: TCM-DiffRAG shows that integrating structured TCM knowledge graphs with Chain-of-Thought–based reasoning substantially improves performance in individualized diagnostic tasks. The joint use of universal and personalized knowledge graphs enables effective alignment between general knowledge and clinical reasoning. These results highlight the potential of reasoning-aware RAG frameworks for advancing LLM applications in traditional Chinese medicine.