Journal of Frontiers of Computer Science and Technology ›› 2020, Vol. 14 ›› Issue (1): 30-39.DOI: 10.3778/j.issn.1673-9418.1812031

Previous Articles     Next Articles

Extended Topic Model Based Abnormal Medical Prescription Detection Method

LIU Shaoqin, TANG Shuang, ZHAO Junfeng, WANG Yasha, ZHUO Lin   

  1. 1.School of Electronics Engineering and Computer Science, Peking University, Beijing 100871, China
    2.Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing 100871, China
    3.Peking University Information Technology Institute (Tianjin Binhai), Tianjin 300450, China
    4.Department of Epidemiology and Bio-Statistics, School of Public Health, Peking University, Beijing 100871, China
  • Online:2020-01-01 Published:2020-01-09

基于扩展主题模型的异常医疗处方检测方法

刘少钦唐爽赵俊峰王亚沙卓琳   

  1. 1.北京大学 信息科学技术学院,北京 100871
    2.高可信软件技术教育部重点实验室,北京 100871
    3.北京大学(天津滨海)新一代信息技术研究院,天津 300450
    4.北京大学 公共卫生学院 流行病与卫生统计学系,北京 100871

Abstract: Abnormal prescriptions refer to abnormal prescriptions prescribed by doctors for patients. Abnormalities in medical prescription, such as drug abuse and incorrect medicine, will affect the efficiency of treatment and even result in serious consequence. Because of some subjective or objective reasons, there exist more or less abnormal prescriptions. The detection of the abnormal prescriptions can improve the efficiency of the patient's medical treat-ment and reduce the cost of the medical treatment. It is of great significance to drug abuse, polypharmacy and incorrect medicine. For this reason, this paper proposes an extended topic model based abnormal medical prescri-ption detection method, which can automatically detect the abnormal prescription from a large number of prescri-ption data. In addition, for each new prescription, this method can determine whether its diagnose and medicine match, and then determine whether it is normal or not. Compared with other abnormal detection algorithms, this method has a wider range of applications, not only can be used to detect abnormal prescriptions, but also can be used to detect the matching relations between other features. This method has been implemented and its validity has been verified in a real prescription dataset.

Key words: rational use of drugs, abnormal detection, topic model, multi-view topic model

摘要: 异常处方指的是医生为患者所开具的存在异常的处方。医疗处方中出现异常,如滥用药或者开错药等,会影响患者的治疗效率,甚至造成严重的后果。由于一些主观或者客观原因,医生总会开具一些异常处方。检测出这些异常处方能够提升患者就医效率,减少社会医疗成本,并且对药物滥用、多开药、错开药的有效管理等都有着重要意义。为此,提出了一种基于扩展主题模型的异常处方检测方法。该方法能够自动地从大量处方数据中检测出异常处方,并且对于每一个新的处方,该方法都能够判断其诊断和用药是否匹配,进而判断其是否正常。与其他异常检测算法相比,该方法具有更广泛的应用,不仅可以在医疗领域中使用,以检测异常处方,还可以在其他领域中使用,以检测其他特征之间的匹配关系异常。该方法已经得到了实现,并在真实的处方数据集中得到了验证。

关键词: 合理用药, 异常检测, 主题模型, 多视图主题模型