基于协同过滤的医疗临床路径智能推荐系统  

Medical clinical pathway intelligent recommendation system based on collaborative filtering

作　　者：臧彬 ZANG Bin(School of Computer Science and Engineering,Nanjing University of Science and Technology,Nanjing 210094,China)

机构地区：[1]南京理工大学计算机科学与工程学院,江苏南京210094

出　　处：《现代电子技术》2023年第4期75-78,共4页Modern Electronics Technique

摘　　要：在信息技术的推动下,很多医院开始应用医疗临床路径系统,并取得了一定的效果。但目前市面上的一些医疗临床路径系统还不完善,特别是临床路径的制定和执行过程中依赖专家的主观判断,缺乏客观性和准确性。基于此,文中提出一种基于协同过滤的临床路径推荐算法。首先提取系统中的患者临床诊断数据,通过余弦相似度算法对具有相似临床诊断指标的患者进行相似度计算;然后构建患者-路径影响矩阵,并根据计算结果进行关联度排序,最终形成一个Top-N的推荐路径列表,从而为医生推荐符合患者病种特征的临床路径。与其他方法的比较测试结果表明,所提方法能够较好地解决当前临床路径推荐方法存在的缺陷,从而提高临床路径推荐的精度,具有明显的优越性,可为医疗临床路径系统的设计提供参考。With the promotion of information technology,many hospitals have begun to apply the medical clinical pathway system and achieved a certain results. However,some medical clinical pathway systems on the market are not perfect at present,especially the formulation and executive process of clinical pathway depend on the subjective judgment of experts,lacking objectivity and accuracy. On this basis, a clinical pathway recommendation algorithm based on collaborative filtering is proposed. The clinical diagnosis data of patients in the system are extracted,and the patients′ similarity with similar clinical diagnosis indicators is calculated by means of the cosine similarity algorithm. The patient-pathway influence matrix is constructed,the relevancy ranking is performed according to the calculated results,and a top-N recommended pathway list is formed finally,so as to recommend the clinical pathway that conforms to the patient′ s disease characteristics to doctors. The testing results show that,in comparison with other methods,the proposed method can make up the deficiency of the current clinical pathway recommendation methods, and improve the accuracy of clinical pathway recommendation. It has obvious advantages,and can provide a reference for the design of medical clinical pathway system.

关 键 词：临床路径推荐 相似度计算 路径制定 关联度排序 数据采集 对比测试 

分 类 号：TN915-34[电子电信—通信与信息系统]