the National Natural Science Foundation of China (72071152, 71571090 and 81774218); the Xi'an Science and Technology Projects(XA2020-RKXYJ-0086); the Youth Innovation Team of Shaanxi Universities(2019);Fund Project of Guangdong Provincial Department of Education (2018GWQNCX050)
辅助诊疗是未来推荐系统在医疗领域的主要应用，其通过分析患者数据与历史病例库进而推荐检查项目等辅助医生诊疗。在临床实践中，医疗推荐可能存在数据多源异构和推荐项目多准则的问题，考虑到医疗推荐的这些特征，本文定义了异构信息系统上不同数据类型的距离测度，实现了多源异构数据的有效处理。同时根据两个对象之间的混合距离得到异构信息系统中的二元关系，并构建了异构信息粗糙集模型。接着将多准则推荐与多准则决策方法（multiple criteria decision making MCDM）相结合，运用灰色关联分析（grey relational analysis GRA）聚合每个项目下多准则评分将其转化为单评分推荐。最后在异构信息粗糙集模型的基础上引入三支决策，同时基于协同过滤方法实现三支推荐，考虑了推荐过程中的决策成本。在医疗应用部分采用临床数据实验，验证了本文提出的模型能够为临床诊断提供知识支持，有效降低推荐决策成本，提高推荐的准确性。
Auxiliary diagnosis and treatment are the main applications of recommendation system in the medical field in the future, which assist doctors in diagnosis and treatment by analyzing data of patient and the database of historical cases and recommend examination items. Medical recommendation may have the problems of multi-source heterogeneous data and multi-criteria of recommendation items in clinical practice. Considering the characteristics of medical recommendation, this paper defines the distance measure of different types of data in heterogeneous information systems and the effective processing of multi-source heterogeneous data is realized. Meanwhile the binary relationship in heterogeneous information systems is obtained according to the hybrid distance between two objects and the heterogeneous information rough set model is constructed subsequently. Then the multi-criteria recommendation is combined with multi-criteria decision-making method(MCDM). And the multi-criteria rating of each item is aggregated by grey relational analysis(GRA) to transform multi-criteria recommendation into single-rating recommendation. Finally, three-way decision-making is presented on the basis of the heterogeneous information rough set model, and three-way recommendation is achieved based on the collaborative filtering method, which considers the cost of decision-making in the process of recommendation. Clinical practice data in the part of medical application is used to verify that the model proposed in this paper can provide knowledge support for clinical diagnosis. And it effectively reduces the cost of recommendation and improves the accuracy of recommendation.