摘要目的 急诊科面临的诸多挑战之一是在有限的人力资源和急救资源范围内以最高效率和最佳质量对病情复杂多变的患者进行及时处置.本研究尝试结合大数据和小波变换方程组,从急诊外科患者入院数据中解析出疾病谱及频率的多尺(multiple scales)度时间序列变迁模式,从而为优化急诊急救资源配置提供一种智能化解决方案.方法 利用数据管理工具(DataChief Avaintec,Helsinki,Finland)导入四川省人民医院2005-2014年所有急诊外科入院患者数据,进行整理、清洗和辅助定义后,以9h为单位对入院患者进行序列累加,形成连续波谱.采用计算数学软件平台(MATLAB)小波变换函数进行分解,分解层数5层,对每一层波谱高度及其分布进行分段计数统计,并利用K-mean算法找出分解尺度系数间关系.最后利用aprori算法进行频繁模式挖掘(frequent patterns mining),挖出患者入院疾病谱及频率分布模式.结果 纳入23 795例患者,疾病种类分布以急腹症占比最高,同时发现,急外患者入院变化是复杂的渐升波谱.小波分解后,信号波A反映了特定时间尺度下整个波动数据的趋势性变化.而噪声波D则反映了波动在特定时间尺度下的细节特征.如A1主波尺度代表以16 d为周期的波动.相应的D1,反映了16 d周期波动下的变化剧烈程度.以D1始,D1-D5代表波谱分解的噪音部分.以研究期间发生的5·12特大地震为例,在D3层出现了明显的噪声波,提示波动周期为4d,其临床解释为:4d内患者入院激增.结论 急诊外科的疾病发病受到多个时间尺度的影响,这种影响是一种典型的多尺度现象.利用小波分析可以方便的根据不同的时间尺度把急诊入院的病案信息的变化趋势分解出来,这种方法有助于合理分配急诊资源.

abstractsObjective One of the major challenges to emergency department is to provide high quality and time sensitive service under limitation of human/material resources,along with patients population with extremely complex conditions.We presented a study that based on a big data got from real world and used wavelet transform technique to analyze time-dependent diseases spectrum patterns and evolution patterns,which will provide solid methodological support for optimizing resources configuration for acute care surgery service.Methods Record data of patients admitted to acute care surgery from 2007-2014 were collected by using data management tool (Avaintec,Helsinki,Finland).The data were cleansed and were transformed to continuing spectrum according to time series of admission time points (per 9 hours).Matlab was used for wavelet transform,and applied five levels of wavelet decomposition and calculated the best decomposition levels by K-mean algorithm for each level.Then we used aprori algorithm for data mining (frequent patterns mining).Results A total of 23 795 cases were enrolled and acute abdomens were made up biggest proportion of admission.Meanwhile,it is found that the spectrum of acute care surgery admission frequency was a complex rising sequence.After wavelet decomposition,signal wave A reflexed trends evolution in a given time scale,and noise wave D reflexed minutia at relevant time scale.In another words,a principal wave A1 represented fluctuation at a cycle of 16 days.Noise wave D1 reflected intensity level in this 16 days' cycle.For example,the 5 · 12 episodes of massive earthquake in 2008 were included in the study,it is found that a significant noise wave at D3 level that indicated a 4 days' cycle.Clinically,it indicated explosive admissions to acute care surgery in 4 days.Conclusions The admission spectrum to acute care surgery is a phenomenon of multi-scale.Based on wavelet decomposing,we can easily analyze the rule of admission spectrum from electronic records of patients and can be used for optimization the emergency medicine resources.