Page 205 - 《软件学报》2020年第10期

陈德彦 等:基于领域语义知识库的疾病辅助诊断方法 3181

数据对本文建设的领域语义知识库和提出的疾病辅助诊断方法进行了评价,包括与文献[1]中方法的对比、与基
于统计的方法的对比.对比结果表明,本文方法解决了文献[1]中方法存在的问题和不足.同时,与基于统计的方
法对比,本文方法可以避免“冷启动”问题,可以快速支撑大量常见疾病的辅助诊断.采用本文的方法,有望为基层
全科医生提供常见疾病的辅助诊断服务,或者为患者提供疾病自诊服务.
但本文的方法仍然存在一些不足,这也是下一步需要研究的工作.
1) 引入更多的诊断要素:针对患者疾病自诊的场景,通过问卷的方式进一步获取年龄、性别、既往病史、
家族病史等诊断要素;针对院内的辅助诊断,可以从患者的历史诊疗记录中获取既往病史、家族病史、历史检
查检验结果等信息,也可能得到最新的查体、检查、检验等结果数据;
2) 对一些常见的疾病直接建立辅助诊断规则,先进行基于规则推理的疾病诊断;
3) 对本文的方法进行改进,一方面需要考虑多维诊断要素之间存在的关联关系和权重,另一方面需要考虑
不同诊断要素对疾病诊断的贡献作用.

References:
[1] Romero-Tris C, Riaño D, Real F. Ontology-based retrospective and prospective diagnosis and medical knowledge personalization.
In: Knowledge Representation for Health-care. Berlin: Springer-Verlag, 2010. 1–15. [doi: 10.1007/978-3-642-18050-7_1]
[2] Bhatla N, Jyoti K. A novel approach for heart disease diagnosis using data mining and fuzzy logic. Int’l Journal of Computer
Applications, 2012,54(17):16–21. [doi: 10.5120/8658-2498]
[3] Krashenyi I, Popov A, Ramirez J, Gorriz JM. Application of fuzzy logic for Alzheimer’s disease diagnosis. In: Proc. of the Signal
Processing Symp. IEEE, 2015. 85–88. [doi: 10.1109/SPS.2015.7168288]
[4] Chowdhury DR. An artificial neural network model for neonatal disease diagnosis. Int’l Journal of Artificial Intelligence & Expert
Systems, 2011,2(3):96–106.
[5] Salvatore C, Cerasa A, Castiglioni I, et al. Machine learning on brain MRI data for differential diagnosis of Parkinson’s disease and
progressive supranuclear palsy. Journal of Neuroscience Methods, 2014,222:230–237. [doi: 10.1016/j.jneumeth.2013.11.016]
[6] Studer R, Benjamins VR, Fensel D. Knowledge engineering: Principles and methods. Data and Knowledge Engineering, 1998,
25(1/2):161–197. [doi: 10.1016/S0169-023X(97)00056-6]
[7] Berners-Lee T, Hendler J, Lassila O. The semantic Web: A new form of Web content that is meaningful to computers will unleash
a revolution of new possibilities. Scientific American, 2001,284(5):34–43.
[8] Smith B, Ashburner M, Rosse C, et al. The OBO foundry: Coordinated evolution of ontologies to support biomedical data
integration. Nature Biotechnology, 2007,25(11):1251–1255. [doi: 10.1038/nbt1346]
[9] Licata G. Employing fuzzy logic in the diagnosis of a clinical case. Health, 2010,2(3):211–224. [doi: 10.4236/health.2010.23031]
[10] Köhler S, Schulz MH, Krawitz P, et al. Clinical diagnostics in human genetics with semantic similarity searches in ontologies.
American Journal of Human Genetics, 2009,85(4):457–64. [doi: 10.1016/j.ajhg.2009.09.003]
[11] Bodenreider O. Disease ontology. In: Encyclopedia of Systems Biology. 2013. 578–581.
[12] Alfonse M, Aref MM, Salem ABM. An ontology-based cancer diseases diagnostic methodology. In: Recent Advances in
Information Science. 2013. 95–99.
[13] Jayaratne L. Ontology based approach for diagnosis in personalized medicine. In: Proc. of the Int’l Conf. on Computer Games,
Multimedia and Allied Technology. 2015.
[14] Mathur S. Ontology-based methods for disease similarity estimation and drug repositioning [Ph.D. Thesis]. Kansas City: Computer
Science and Mathematics, University of Missouri-Kansas City, 2012.
[15] Izumi S, Dai K, Itabashi G, et al. An ontology-based advice system for health and exercise. In: Proc. of the 10th Iasted Int’l Conf.
on Internet and Multimedia Systems and Applications. DBLP, 2006. 95–100.
[16] Cantais J, Dominguez D, Gigante V, et al. An example of food ontology for diabetes control. In: Proc. of the Int’l Semantic Web
Conf. Workshop on Ontology Patterns for the Semantic Web. 2005.
[17] Kostopoulos K, Chouvarda I, Koutkias V, et al. An ontology-based framework aiming to support personalized exercise prescription:
Application in cardiac rehabilitation. IEEE Engineering in Medicine and Biology Magazine, 2011,2011(4):1567–1570.
[18] Manola F, Miller E, McBride B. RDF 1.1 Primer. W3C, 20140225, 2014. https://www.w3.org/TR/2014/NOTE-rdf11-primer-
20140225/
[19] Hebeler J, Fisher M, Blace R, Perez-Lopez A. Semantic Web Programming. Indianapolis: Wiley Publishing, 2009.