Open Access Article
International Journal of Clinical Research. 2025; 9: (5) ; 153-157 ; DOI: 10.12208/j.ijcr.20250260.
Construction of medical knowledge graph based on symptom weight information of diseases
基于疾病症状权重信息的医疗知识图谱构建
作者：
王宁1,
吴靖1,
王远2,
翟文彪1,
傅新杰1 *
1 嘉兴职业技术学院互联网学院 浙江嘉兴
2 嘉兴大学生物与化学工程学院 浙江嘉兴
*通讯作者：
傅新杰,单位： 嘉兴职业技术学院互联网学院 浙江嘉兴；
发布时间: 2025-05-29 总浏览量: 50
PDF 全文下载
引用本文
摘要
针对互联网医疗信息冗余、真实性存疑及现有知识图谱疾病覆盖局限、症状权重缺失等问题，本研究提出一种融合多源异构数据的医疗知识图谱构建方法。通过整合权威医疗网站半结构化数据与开源医疗知识图谱，设计多阶段构建流程，并引入基于联合搜索频次的疾病-症状动态权重计算方法，最终构建了一个包含疾病症状权重信息的医疗知识图谱。该图谱不仅解决了疾病症状权重关系不明确的问题，还实现了对碎片化医疗信息的有效整合与深度挖掘，为医疗领域的相关研究提供有价值的数据资源。
关键词： 信息冗余；疾病症状权重；医疗知识图谱
Abstract
To address the challenges of redundant and unreliable internet-based medical information, as well as the limitations of existing knowledge graphs in disease coverage and symptom weight representation, this study proposes a medical knowledge graph construction method integrating multi-source heterogeneous data. By combining semi-structured data from authoritative medical websites with open-source medical knowledge graphs, a multi-stage construction framework is designed, and an innovative dynamic disease-symptom weight calculation method based on joint search frequency is introduced. The resulting knowledge graph incorporates disease-symptom weight information, resolving ambiguities in symptom-disease relationships while achieving effective integration and in-depth mining of fragmented medical data. This work provides valuable data resources for medical research and clinical decision support.
Key words： Information redundancy; Disease-symptom weights; Medical knowledge graph
参考文献 References
[1] YU S, WANG H, LIU T, et al. A knowledge-driven network for fine-grained relationship detection between miRNA and disease [J]. 2022, 23(3): bbac058.
[2] YE Q, HSIEH C-Y, YANG Z, et al. A unified drug–target interaction prediction framework based on knowledge graph and recommendation system [J]. 2021, 12(1): 6775.
[3] LI N, YANG Z, LUO L, et al. KGHC: a knowledge graph for hepatocellular carcinoma [J]. 2020, 20: 1-11.
[4] YIN Y, ZHANG L, WANG Y, et al. Question answering system based on knowledge graph in traditional Chinese medicine diagnosis and treatment of viral hepatitis B [J]. 2022, 2022(1): 7139904.
[5] JI S, PAN S, CAMBRIA E, et al. A survey on knowledge graphs: Representation, acquisition, and applications [J]. 2021, 33(2): 494-514.
[6] HUANG L, GUAN H, LIANG Y, et al. Covid-19 knowledge graph for drug and vaccine development; proceedings of the 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), F, 2021 [C]. IEEE.
[7] 刘勇, 齐梦霁. 基于糖尿病防治的医学知识图谱构建的研究 [J]. 医学信息, 2020, 33(18): 11-4.
[8] 刘金垒, 惠小珊, 张振鹏, et al. 基于中医诊疗指南的冠心病知识图谱构建 [J]. 中国实验方剂学杂志, 2023, 29(07): 208-15.
引用本文
王宁, 吴靖, 王远, 翟文彪, 傅新杰, 基于疾病症状权重信息的医疗知识图谱构建[J]. 国际临床研究杂志, 2025; 9: (5) : 153-157.