基于知识图谱的儿童疾病推理模型
Children’s Disease Reasoning Model Based on Knowledge Graph

DOI: 10.12677/CSA.2022.122028, PP. 280-289

Keywords: 知识图谱，疾病推理，自适应机制
Knowledge Graph, Disease Reasoning, Adaptive Mechanism

Full-Text   Cite this paper   Add to My Lib

Abstract:

为提高儿童多种疾病推理的准确率，提出以知识图谱为数据基础并结合推理机的儿童疾病推理算法。通过Neo4j构建知识图谱对数据进行储存和应用，而推理机以TransE推理机为基础，并结合朴素贝叶斯分类器来提升推理机处理不同疾病含有同种症状的问题的能力，再通过建立的自适应机制来降低不同疾病的症状数不同对推理机的影响。实验结果表明，所提出算法在疾病推理的精确率，召回率和F1值上均有所提升，说明该方法提高了儿童多种疾病推理的准确率。
To improve the accuracy of children’s multiple diseases reasoning, a children’s disease reasoning algorithm based on the knowledge graph and the reasoning machine is proposed. A knowledge graph is constructed by Neo4j to store and apply the data, and the inference engine is based on the TransE inference engine, and the Naive Bayes Classifier is combined to improve the ability to deal with problems with the same symptoms in different diseases, and an adaptive mechanism is established to reduce the impact of different symptoms of different diseases on the reasoning machine. The experimental results show that the proposed algorithm improves the precision, recall and F1 value of disease reasoning, indicating that this method improves the accuracy of children’s multiple disease reasoning.

References

[1]	Wang, J., Liu, N., Hu, Q., et al. (2020) The Intelligent Diagnostic System for Common Diseases Using the Optimized Medical Knowledge Graph. 2020 International Wireless Communications and Mobile Computing, Limassol, Cyprus, 15-19 June 2020, 1504-1509. https://doi.org/10.1109/IWCMC48107.2020.9148406
[2]	Qiu, W., Zhang, Y. and Cheng, B. (2018) Building Syndrome and Symptom Association Network by Bayesian Network. 4th International Con-ference on Computer and Communications (ICCC), Chengdu, China, 7-10 December 2018, 1762-1766. https://doi.org/10.1109/CompComm.2018.8780599
[3]	龚乐君, 张立鹏, 李宇茜, 吴向辉, 高志宏, 潘传迪, 杨庚. 基于决策树的乳腺癌病历文本的挖掘与决策[J]. 南京师大学报(自然科学版), 2019, 42(3): 42-51.
[4]	Jia, Y., Tan, Z. and Zhang, J. (2019) DKDR: An Approach of Knowledge Graph and Deep Reinforcement Learning for Dis-ease Diagnosis. 2019 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Com-puting, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom), Xiamen, China, 16-18 December 2019,1303-1308. https://doi.org/10.1109/ISPA-BDCloud-SustainCom-SocialCom48970.2019.00187
[5]	刘勘, 张雅荃. 基于医疗知识图谱的并发症辅助诊断[J]. 中文信息学报, 2020, 34(10): 85-93+104.
[6]	Chai, X. (2020) Diagnosis Meth-od of Thyroid Disease Combining Knowledge Graph and Deep Learning. IEEE Access, 8, 14978-149795. https://doi.org/10.1109/ACCESS.2020.3016676
[7]	官赛萍, 靳小龙, 贾岩涛, 王元卓, 程学旗. 面向知识图谱的知识推理研究进展[J]. 软件学报, 2018, 29(10): 2966-2994.
[8]	王鑫, 陈蔚雪, 杨雅君, 张小旺, 冯志勇. 知识图谱划分算法研究综述[J]. 计算机学报, 2021, 44(1): 235-260.
[9]	董丽丽, 程炯, 张翔, 叶娜. 融合知识图谱与深度学习的疾病诊断方法研究[J]. 计算机科学与探索, 2020, 14(5): 815-824.
[10]	关媛媛, 郝阳, 田春颖, 孙璇, 王东军, 田之魁, 王泓午. 基于CiteSpace的舌诊诊断标准研究的可视化分析[J].世界科学技术-中医药现代化, 2021, 23(1): 263-270.
[11]	Zou, Y. and Liu, Y. (2020) The Implementation Knowledge Graph of Air Crash Data Based on Neo4j. 4th Information Technology, Networking, Electronic and Automation Control Conference, Chongqing, China, 12-14 June 2020, 1699-1702. https://doi.org/10.1109/ITNEC48623.2020.9085182
[12]	Choi, W. and Lee, H. (2019) Inference of Biomedical Relations among Chemicals, Genes, Diseases, and Symptoms Using Knowledge Repre-sentation Learning. IEEE Access, 7, 179373-179384. https://doi.org/10.1109/ACCESS.2019.2957812

Full-Text