健康医疗领域是一个知识密集型的领域，临床诊断的质量主要依赖于医生所掌握的健康医疗知识以及临床经验.然而，单个医生的能力仍然非常有限，所以目前临床诊断的质量并不高.为此，提出一种基于领域语义知识库的疾病辅助诊断方法，基于Freebase中medicine主题域的知识建立了领域语义知识库，提出计算知识库中症状于疾病诊断的权重、计算与患者输入症状集相关的疾病的相关度和基于患者输入症状集推荐相关症状的算法.最后，基于随机选取的6种常见疾病的临床病历数据对所提出的方法与现有方法进行了对比评价，评价结果一方面表明了所提方法对已有方法存在的问题和不足的改进效果，另一方面也表明所提方法可以避免“冷启动”问题，可以快速支撑对大量常见疾病的辅助诊断.基于所提方法，有望为基层全科医生提供大量常见疾病的辅助诊断服务，或者为患者提供疾病自诊服务.

The health care domain is a knowledge-intensive domain. The quality of clinical diagnosis depends mainly on the knowledge of health care and clinical experience held by doctors. However, the ability of a single doctor is very limited, so the quality of clinical diagnosis is not high. To this end, this study proposes an aided diagnosis method based on the domain semantic knowledge base. Firstly, based on the knowledge of the medicine subject matter domain in Freebase, a domain semantic knowledge base is established. Then, based on the semantic knowledge base, the algorithms for calculating the weights of the symptoms in the knowledge base, the relevancy of the diseases related to the input symptom set from a patient, and the related symptom set related to the input symptom set from the patient are proposed. Finally, based on the clinical data of 6 kinds of common diseases randomly selected, the method proposed in this study is compared with the existing methods. On the one hand, the evaluation results show that the method of this paper improves the problems and deficiencies of the existing methods. On the other hand, it shows that the method can avoid the “cold start” problem and can quickly support the aided diagnosis of a large number of common diseases. Using the method presented in this paper, it is expected to provide a comprehensive diagnosis service for a large number of common diseases for the general practitioners at the grassroots level, or provide patients with self-diagnosis services for diseases.

国家自然科学基金（61232015）；国家高技术研究发展计划（2015AA020103）；国家重点研发计划（2016YFC1303000）；沈阳东软智能医疗科技研究院有限公司开放课题基金（NRIHTOP1802）