摘要
慢性病与其相关并发症关系的研究,对患者以及医学研究都有重要意义。电子病历中记录的患者就诊数据为研究目标慢性病与其并发症的关系提供了数据基础,其中面临的挑战之一在于既需要使用临床医生的领域知识对并发症进行标注,又不希望给医生增加过多负担。设计了一种采用分组策略的基于ICD-10诊断编码的慢性病并发症半监督聚类方法,以实现在较少的医生专家参与下对慢性病并发症归类。真实糖尿病患者电子医疗记录数据集上的实验结果表明提出的算法是实用且有效的。
Study on the relationship between the chronic disease and the corresponding complications has great theoretical significance and applicable value for patients and clinical medicine. In order to utilize healthcare electronic record more reasonably, preprocessing was needed according to prior medical knowledge for chronic disease complication. The challenge of this work is that medical knowledge should be exploited to label the corresponding complications. To meet these challenges and assist physicians in labeling complications of a target chronic disease, a semi-supervised chronic disease complications clustering algorithm based on ICD-10 code for diagnoses was proposed. Experiments on a real dataset of diabetes electronic healthcare record show that the algorithms are practical and effective.
作者
王晓霞
蒋伏松
王宇
熊贇
WANG Xiaoxia;JIANG Fusong;WANG Yu;XIONG Yun(School of Computer Science, Fudan University, Shanghai 201203, China;Shanghai Key Laboratory of Data Science, Shanghai 201203, China;College of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, China;Shanghai Sixth People's Hospital, Shanghai 200233, China;Shanghai Putuo District Center for Disease Control and Prevention, Shanghai 200333, China)
出处
《大数据》
2018年第3期37-45,共9页
Big Data Research
基金
国家高技术研究发展计划("863"计划)基金资助项目(N o.2015AA020105)
上海市科技发展基金资助项目(No.16JC1400801
No.17511105502)~~
关键词
半监督学习
聚类算法
慢性病并发症
ICD-10诊断编码
semi-supervised learning
clustering algorithm
chronic disease complication
ICD-10 diagnoses code