Jin Shuyan, Liang Haobin, Zhang Wenxia, Li Huan
Health Department, Shenzhen Maternity and Child Healthcare Hospital, Shenzhen, China.
School of Economics and Statistics, Guangzhou University, Guangzhou, China.
JMIR Med Inform. 2024 Feb 22;12:e52210. doi: 10.2196/52210.
The incidence of breast cancer has remained high and continues to rise since the 21st century. Consequently, there has been a significant increase in research efforts focused on breast cancer prevention and treatment. Despite the extensive body of literature available on this subject, systematic integration is lacking. To address this issue, knowledge graphs have emerged as a valuable tool. By harnessing their powerful knowledge integration capabilities, knowledge graphs offer a comprehensive and structured approach to understanding breast cancer prevention and treatment.
We aim to integrate literature data on breast cancer treatment and prevention, build a knowledge graph, and provide support for clinical decision-making.
We used Medical Subject Headings terms to search for clinical trial literature on breast cancer prevention and treatment published on PubMed between 2018 and 2022. We downloaded triplet data from the Semantic MEDLINE Database (SemMedDB) and matched them with the retrieved literature to obtain triplet data for the target articles. We visualized the triplet information using NetworkX for knowledge discovery.
Within the scope of literature research in the past 5 years, malignant neoplasms appeared most frequently (587/1387, 42.3%). Pharmacotherapy (267/1387, 19.3%) was the primary treatment method, with trastuzumab (209/1805, 11.6%) being the most commonly used therapeutic drug. Through the analysis of the knowledge graph, we have discovered a complex network of relationships between treatment methods, therapeutic drugs, and preventive measures for different types of breast cancer.
This study constructed a knowledge graph for breast cancer prevention and treatment, which enabled the integration and knowledge discovery of relevant literature in the past 5 years. Researchers can gain insights into treatment methods, drugs, preventive knowledge regarding adverse reactions to treatment, and the associations between different knowledge domains from the graph.
自21世纪以来，乳腺癌的发病率一直居高不下且持续上升。因此，针对乳腺癌预防和治疗的研究工作显著增加。尽管关于这一主题已有大量文献，但缺乏系统的整合。为解决这一问题，知识图谱已成为一种有价值的工具。通过利用其强大的知识整合能力，知识图谱为理解乳腺癌的预防和治疗提供了一种全面且结构化的方法。
我们旨在整合乳腺癌治疗和预防的文献数据，构建一个知识图谱，并为临床决策提供支持。
我们使用医学主题词检索2018年至2022年期间在PubMed上发表的关于乳腺癌预防和治疗的临床试验文献。我们从语义医学文献数据库（SemMedDB）下载三元组数据，并将其与检索到的文献进行匹配，以获取目标文章的三元组数据。我们使用NetworkX对三元组信息进行可视化，以进行知识发现。
在过去5年的文献研究范围内，恶性肿瘤出现的频率最高（587/1387，42.3%）。药物治疗（267/1387，19.3%）是主要的治疗方法，曲妥珠单抗（209/1805，11.6%）是最常用的治疗药物。通过对知识图谱的分析，我们发现了不同类型乳腺癌的治疗方法、治疗药物和预防措施之间的复杂关系网络。
本研究构建了一个乳腺癌预防和治疗的知识图谱，实现了过去5年相关文献的整合和知识发现。研究人员可以从该图谱中深入了解治疗方法、药物、治疗不良反应的预防知识以及不同知识领域之间的关联。
