论文部分内容阅读
随着信息系统尤其是电子病历系统在医院中越来越普及,由此产生的临床数据成为一个非常可观的“潜在数据宝库”。如某三级甲等综合医院2013年的门急诊量达到341.2万人次,住院收容量达到14.7万人次,手术量达到8.5万台次。这些数据符合大数据“3V”标准:Volume(海量),数据容量越来越大;Velocity(速度),数据量增长越来越快,需要对数据的处理响应速度也越来越快;Variety(多样性),数据来源以及格式多样,结构化与非结构化数据并存,文本、图片、视频、甚至基因序列数据并存。
With the increasing popularity of information systems, especially electronic medical record systems, in hospitals, the resulting clinical data becomes a significant “treasure trove of potential data.” For instance, the number of outpatient and emergency services in some Grade III A general hospitals reached 3,412,000 in 2013, the hospital admission volume reached 147,000 and the number of operations reached 85,000. These data are in line with big data “3V ” standard: Volume, the data capacity is getting bigger and bigger; Velocity, the data volume grows faster and faster, the response to the data needs to be faster and faster; Variety, data sources and formats, structured and unstructured data, text, images, video, and even gene sequence data co-exist.