Author(s)

XiaoMiao Gui^1,2, XinQi Hu², KeFan Yuan³, RuiNa Wang^2*

Affiliation(s)

¹Institute of Scientific and Technical Information of China, Beijing 100038, China.
²School of Public Health, Hubei University of Medicine, Shiyan 442000, Hubei, China.
³Xiantao Hospital of Traditional Chinese Medicine, Xiantao 433000, Hubei, China.

Corresponding Author

RuiNa Wang

ABSTRACT

Stroke is a leading cause of death and disability worldwide. Despite the extensive use of traditional Chinese medicine (TCM) formulas in stroke treatment, systematic analyses of their multi-drug synergy and compatibility patterns remain scarce. This study leverages knowledge graph technology to integrate multi-source TCM formula data and constructs a knowledge graph for stroke-related TCM prescriptions. By combining frequency analysis, cluster analysis, and association rule mining, the study systematically uncovers medication patterns. A total of 1,403 validated formulas were included, identifying nine high-frequency herbs (frequency ≥ 200), such as Saposhnikoviae Radix and Glycyrrhizae Radix. These were categorized into four synergistic clusters. Five strong association rules were identified (e.g., “Ligustici Rhizoma and Almond → Ephedrae Herba” and “Scutellaria Baicalensis and Saposhnikoviae Radix → Glycyrrhizae Radix”). The utility of the knowledge graph in multidimensional retrieval and intelligent reasoning was validated. This study provides data support and a methodological paradigm for the standardized application and modernization of TCM in stroke treatment.

KEYWORDS

Knowledge graph; Traditional Chinese medicine formulas; Prescription pattern; Stroke

CITE THIS PAPER

XiaoMiao Gui, XinQi Hu, KeFan Yuan, RuiNa Wang. Analysis of prescription patterns of traditional Chinese medicine formulas for stroke treatment. Journal of Pharmaceutical and Medical Research. 2025, 7(2): 1-4. DOI: https://doi.org/10.61784/jpmr3037.

REFERENCES

[1] Parisa Fallahtafti, Amirhossein Habibzadeh, Negar Ghasemloo, et al. Stroke burden in North Africa and the Middle East, 1990-2021: an analysis based on the global burden of disease study. BMC neurology, 2025, 25 (1), 277-277.

[2] Yin Xinyi, Li Shutang, Wang Junwei, et al. Research progress of active compounds from traditional Chinese medicine in the treatment of stroke. European journal of medicinal chemistry, 2025, 291(5), 117599.

[3] Xu Min, Wu RuiXia, Li XiaoLi, et al. Traditional medicine in China for ischemic stroke: bioactive components, pharmacology, and mechanisms. Journal of integrative neuroscience, 2022, 21 (1), 26-26.

[4] Zhao Jianfeng, Zhang Wei, Yu Hai. Prospects and Analysis of Traditional Chinese Medicine Standards Through the Transition of Chinese Pharmacopeia. Journal of Pharmaceutical Innovation, 2022, 18 (2), 349-355.

[5] Zhang Peng, Zhang Dingfan, Zhou Wuai, et al. Network pharmacology: towards the artificial intelligence-based precision traditional Chinese medicine. Briefings in bioinformatics, 2023, 25 (1), 1-12.

[6] Zhang Zheng, Wu Hengyang, Wang Na. A Knowledge-Enhanced Disease Diagnosis Method Based on Prompt Learning and BERT Integration. Journal on Artificial Intelligence, 2025, 7 (1), 17-37.

[7] Gao Yanjun, Li Ruizhe, Emma Croxford, et al. Leveraging Medical Knowledge Graphs Into Large Language Models for Diagnosis Prediction: Design and Application Study. JMIR AI, 2025, 4(1), e58670: p1-p17.

[8] Alain García Olea, Ane G Domingo Aldama, Marcos Merino, et al. The Application of Deep Learning Tools on Medical Reports to Optimize the Input of an Atrial-Fibrillation-Recurrence Predictive Model. Journal of Clinical Medicine, 2025, 14 (7), 2297-2297.

[9] Priyanka Khalate, Shilpa Gite, Biswajeet Pradhan, et al. Advancements and gaps in natural language processing and machine learning applications in healthcare: a comprehensive review of electronic medical records and medical imaging. Frontiers in Physics, 2024, 12(12), 1445204-1445204.