基于大规模人群调查的心电数据库的构建

建立基于大规模人群调查的心电数据库是心电研究中一项重要的基础性工作。本研究依据"中国人生理常数调查研究和数据库"的心电数据,建立了一个以10s十二导联同步心电信号为主要内容的关系型数据库。该数据库包含波形数据、心电可视化图形、多类心电测量数据、诊断结果、人口学信息和基本健康资料,并提供便捷的数据查询、更新和管理服务。目前该数据库记录的样本总量已达25821人,人口覆盖我国四省15个县市,涉及多个民族。该数据库的建立为心电信息学的研究提供了丰富的资源。     

便携式心电监护中实时信号处理方法研究

针对心电信号处理过程中的心电信号数字滤波、心电波形的动态显示、心电数据存储等问题,阐述了3个可用于心电信号实时处理的方法:一是运用滤波器频谱的周期性减少了滤波器系数个数,提高了运算速度,并根据卷积公式特点实现了数字滤波的实时性;二是运用基于内存虚拟屏幕技术实现心电波形动态显示,解决了屏幕闪烁和绘图不连续问题;三是采用嵌入式数据库SQLITE实现了心电数据存储.所有方法均考虑实时性要求,并已成功用于课题组开发的便携式心电监护仪,效果较为理想,具有很强的实用价值.     

智能手机心电显示及与服务器通讯的程序设计

目的:近年来,手机与服务器的通讯在医学领域的研究已经成为热点,利用这种技术,医生可以通过手机上网读取医院服务器上的实时生理数据并给出正确的建议。方法:本文采用了智能手机客户端与服务器交互技术实现对数据远程访问,并在手机端实现了心电波形的动态实时显示。应用J2EE的Tomcat开发平台,建立心电数据库服务器,手机用户上网读取服务器上的心电数据。结合J2ME技术,通过软件编程使得手机用户能访问服务器并能调用数据库中的心电数据以动态心电图的形式显示在手机上。结果:成功建立了医院中心服务器,并在手机端实现了心电数据的读取和波形显示。结论:克服了传统ECG监测实时性差、效率低的缺点,对于预防和诊断心脏窦性疾病具有很大的临床应用价值。     

双通道心电信号长时间连续采集和实时分析系统

基于微机实现了双通道心电信号长时间连续采集和实时分析系统，使用扩展内存实现了大量数据的连续存储，可连续采集３０分钟以上的双道信号；利用中断实现了信号的实时采集和显示，可滚动显示双道信号；可实时分析心电波形，并对异常心电进行报警。该系统为建立心电数据库研究和临床心电监护等应用提供了一个良好的工具。     

基于MSP430单片机的三导联心电采集系统的研制

为获得大量的原始人体心电数据,研制了一款三导联心电采集系统.本系统主要由MSP430单片机开发而成,可以连续采集,经差分放大、功率放大,最后经A/D后存储在芯片内的flash中,并可通过LabVIEW编译的软件控制串口将数据传到计算机中进行后期的数据分析.经测试证实系统安全、稳定性好,可用于心电数据的采集和分析.     

基于80C196KC单片机的便携式家庭心/电血压监护仪的研制

应用80C196KC构成一个循环存储8小时心电数据的便携式心电／血压监护仪,其核心单元是80C196KC单片机,还包括Flash Memory（闪速存储器）存贮模块,Socket Modem通讯模块,薄膜键盘,血压数据接口,液晶显示模块和电源转换模块。其特点是集心电图采集、分析、存储和显示等功能于一体,实现动态心电分析监护及心律失常的识别和报警,并把出现病变时的心电、血压数据通过电话线传到医院中心站,接收返回医嘱。心电信号实时自动分析系统包括QRS复合波的实时检测算法和心律失常自动分析软件,可以显示心电波,心率（HR）和早搏（室早、房早）累积数;自动识别6种心律失常报警。通过对MIT心电数据库的部分数据进行测试,结果表明仪器硬件设计合理,心电分析算法和疾病判出的实时性和准确性基本满足要求,其中QRS波群检出正确率为99.9%,停搏、漏搏和心动过速过缓检出的准确率均在98％以上,而早搏（室早、房早）和R on T检出的准确率在95％以上。     

SDMU心律失常心电数据库的建立

本研究包括研制心电数据库生成系统与ＳＤＭＵ心律失常心电数据库的建立。从１５００名确诊的心脏病人中筛选了４８例３０分钟心电数据入库。参照ＭＩＴ－ＢＩＨ心电数据库与美国医用仪器改进协会（ＡＡＭＩ）推荐标准，结合我国国情，聘全国知名心电专家对心电数据分３５类进行了注释。用Ｃ语言与汇编语言编制了服务程序系统，可对用户心电分析软件进行自动检测并打印出检测结果，也可对心电分析类仪器进行质量检测，应用效果良好     

FastICA在心电信号降噪中的应用

目的研究基于峭度和负熵的Fast ICA的模型特点,分析两种算法在心电信号去噪中的应用,对ICA在信噪分离中的特点加以分析研究。方法首先利用心电数据库MIH-BIT中单独的心电信号和噪声混合对Fast ICA进行降噪测试,通过降噪后心电信号和原信号对比测试基于峭度和负熵的Fast ICA的降噪效果,然后对Da ISy数据库中的真实含噪心电信号进行降噪,分析其在真实环境中的降噪效果。结果通过多组合成混合含噪心电信号和真实含噪心电信号对两种Fast ICA进行分离测试,发现两种Fast ICA都可成功地分离心电信号和噪声,其中基于峭度的Fast ICA的降噪速度较快,而基于负熵的Fast ICA的精确度较高。结论基于峭度和负熵的Fast ICA可以应用于心电信号的降噪中,并且能够有效降低信号噪声。     

面向应急医疗救援的智能网关系统的设计与实现

为能及时获取救援现场中伤员的生理参数与救援舱信息,本研究采用5G蜂窝移动通信、WiFi、卫星通信和北斗短报文通信等手段,设计了一款用于传输救援现场各类数据的多制式智能网关。网关采用树莓派4B作为主控单元,通过WiFi收集前端传感器发送的数据,然后将其存储于MySQL数据库,并实现可视化显示。网关可根据当前通信链路状态选取合适的通信方式,再根据通信方式的带宽对数据进行计算和筛选,然后发送至后台服务器。通过对心电波形、呼吸波形和救援设备等各项数据的传输进行测试,结果表明,该网关系统可在不同网络环境下稳定、可靠地传输数据。该系统操作便捷,工作稳定,可有效提高应急医疗救援能力。     

基于虚拟仪器的12导同步心电数据库的建立

介绍了基于虚拟仪器的12导同步心电数据库生成系统的构建过程。其中硬件系统包括同步心电放大器、12位数据采集卡及便携式电脑等,软件程序采用虚拟仪器编程语言Lab Windows／CVI编写。数据库共收入180例同步心电数据。     

A DYNAMIC ECG MONITORING AND RECORDING SYSTEM

ＡＤＹＮＡＭＩＣＥＣＧＭＯＮＩＴＯＲＩＮＧＡＮＤＲＥＣＯＲＤＩＮＧＳＹＳＴＥＭＬｉｊｕｎＴｉａｎ，ＺｏｎｇｚｈａｎＤｕ，ＤｏｎｇｑｉｎｇＷａｎｇ（ＤｅｐａｒｔｍｅｎｔｏｆＥｌｅｃｔｒｉｃａｌＰｏｗｅｒＳｈａｎｄｏｎｇＰｏｌｙｔｅｃｈｎｉｃＵｎｉｖｅｒ...     

‘Big data’, Hadoop and cloud computing in genomics

Since the completion of the Human Genome project at the turn of the Century, there has been an unprecedented proliferation of genomic sequence data. A consequence of this is that the medical discoveries of the future will largely depend on our ability to process and analyse large genomic data sets, which continue to expand as the cost of sequencing decreases. Herein, we provide an overview of cloud computing and big data technologies, and discuss how such expertise can be used to deal with biology’s big data sets. In particular, big data technologies such as the Apache Hadoop project, which provides distributed and parallelised data processing and analysis of petabyte (PB) scale data sets will be discussed, together with an overview of the current usage of Hadoop within the bioinformatics community.     

穿戴式随行监护系统心电信号质量评价研究

穿戴式生理参数监测技术是一种新型的生理监护技术,代表未来监护技术的发展方向,但该类技术应用于临床尚有许多问题亟待解决。本文针对自主研发的穿戴式随行监护系统(SensEcho-5B)的心电信号质量评价问题开展了探索性研究。首先基于模板匹配法开发出一种心电信号质量评价算法,用于心电信号的自动、定量评价,在100名受试者(15名健康人和85名心血管疾病患者)随机抽取的100 h心电信号数据集上进行了算法性能测试。在此基础上使用SensEcho-5B与心电Holter同步采集了30名受试者(7名健康人和23名心血管疾病患者)的24 h心电数据,使用心电信号质量评价算法对两个系统同步记录的心电信号质量进行评价。算法性能测试结果:敏感度为100%,特异度为99.51%,准确率为99.99%。30名受试者的对照试验结果:SensEcho-5B所检测到的心电信号,信号质量较差时间的中位数(Q1,Q3)为8.93(0.84,32.53)min,Holter所检测到的心电信号,信号质量较差时间的中位数(Q1,Q3)为14.75(4.39,35.98)min(秩和检验P=0.133)。研究结果表明,本文提出的心电信号质量评价算法能够对穿戴式随行监护系统的心电信号质量进行有效评价;随行监护系统SensEcho-5B与对照Holter相比,心电信号质量相当。后续研究将进一步在真实临床环境中采集大样本量的随行监护生理数据,并对心电信号质量进行分析和评价,从而使监护系统的性能得到持续优化。     

Analysis of microarray leukemia data using an efficient MapReduce-based K-nearest-neighbor classifier

Microarray-based gene expression profiling has emerged as an efficient technique for classification, prognosis, diagnosis, and treatment of cancer. Frequent changes in the behavior of this disease generates an enormous volume of data. Microarray data satisfies both the veracity and velocity properties of big data, as it keeps changing with time. Therefore, the analysis of microarray datasets in a small amount of time is essential. They often contain a large amount of expression, but only a fraction of it comprises genes that are significantly expressed. The precise identification of genes of interest that are responsible for causing cancer are imperative in microarray data analysis. Most existing schemes employ a two-phase process such as feature selection/extraction followed by classification. In this paper, various statistical methods (tests) based on MapReduce are proposed for selecting relevant features. After feature selection, a MapReduce-based K-nearest neighbor (mrKNN) classifier is also employed to classify microarray data. These algorithms are successfully implemented in a Hadoop framework. A comparative analysis is done on these MapReduce-based models using microarray datasets of various dimensions. From the obtained results, it is observed that these models consume much less execution time than conventional models in processing big data.     

基于无线局域网的心电监护终端的设计

本文设计了一种基于医院无线局域网的新型医疗监护终端。该终端应用了移动通信技术、嵌入式应用技术等先进技术,以ARM内核的S3C2410微处理器为基础,移植了嵌入式Linux操作系统和Qtopia作为图形用户界面。通过设计的心电信号采集电路与微处理器的数模转换接口连接,利用Qt编写界面程序,实现了对人体心电信号的实时采集、处理、存储和在LCD(液晶显示器)上显示。通过移植USB无线网卡驱动,利用无线局域网技术与医院监护中心连接,将病患的心电信号及时传输到中心服务器上,这样在医院监护中心就可以对各个病房病患进行实时监护,提高了工作人员的工作效率。文中给出了监护终端的软、硬件设计,结果表明终端设备具有体积小、功耗低、操作简单等优点。     

Unstructured medical image query using big data – An epilepsy case study

Big data technologies are critical to the medical field which requires new frameworks to leverage them. Such frameworks would benefit medical experts to test hypotheses by querying huge volumes of unstructured medical data to provide better patient care. The objective of this work is to implement and examine the feasibility of having such a framework to provide efficient querying of unstructured data in unlimited ways. The feasibility study was conducted specifically in the epilepsy field. The proposed framework evaluates a query in two phases. In phase 1, structured data is used to filter the clinical data warehouse. In phase 2, feature extraction modules are executed on the unstructured data in a distributed manner via Hadoop to complete the query. Three modules have been created, volume comparer, surface to volume conversion and average intensity. The framework allows for user-defined modules to be imported to provide unlimited ways to process the unstructured data hence potentially extending the application of this framework beyond epilepsy field. Two types of criteria were used to validate the feasibility of the proposed framework – the ability/accuracy of fulfilling an advanced medical query and the efficiency that Hadoop provides. For the first criterion, the framework executed an advanced medical query that spanned both structured and unstructured data with accurate results. For the second criterion, different architectures were explored to evaluate the performance of various Hadoop configurations and were compared to a traditional Single Server Architecture (SSA). The surface to volume conversion module performed up to 40 times faster than the SSA (using a 20 node Hadoop cluster) and the average intensity module performed up to 85 times faster than the SSA (using a 40 node Hadoop cluster). Furthermore, the 40 node Hadoop cluster executed the average intensity module on 10,000 models in 3 h which was not even practical for the SSA. The current study is limited to epilepsy field and further research and more feature extraction modules are required to show its applicability in other medical domains. The proposed framework advances data-driven medicine by unleashing the content of unstructured medical data in an efficient and unlimited way to be harnessed by medical experts.     

A review of ECG storage formats

Introduction

The interoperability of the Electrocardiogram (ECG) between heterogeneous systems has been facilitated by not one, but a number of predefined open storage formats. To improve the techniques currently used, it is important to define the similarities and the differences between these ECG storage formats.

Methods

This paper presents a review of 9 formats used to store the ECG. Three of the predominant formats, namely, SCP-ECG, DICOM-ECG, and HL7 aECG are reviewed in detail along with the undertaking of a SWOT analysis. The remaining formats have been examined to a lesser extent as they are not as predominant in the literature.

Discussion

This study suggests that a plethora of open ECG formats, all aiming to promote interoperability has the opposite effect of adding more complexity. This paper discusses whether a format supporting a variety of diagnostic modalities is more advantageous than a format that only supports the ECG. It is conclusive that a general purpose format such as DICOM solves more interoperability issues, however, no general purpose format currently exists that fulfils the requirements of all users. As a result, the healthcare industry has been bombarded with custom storage formats, i.e., a format for storing the resting ECG, a format for storing the ambulatory ECG, a format for storing the ECG in clinical trials, a format for storing ECG data on mobile devices etc. This study then examines which implementation method is more suited to encode ECG data, i.e. binary or XML. Binary encoding has been used in the past to store the ECG, however, unlike binary, XML files are human readable, searchable and provide a better form of semantics. Based on analysis within this work it is speculated that XML may overtake binary as the preferred implementation method for encoding ECG data since it has already made a huge impact in the healthcare industry.

Conclusion

It can be concluded that there is a wide range of vastly different techniques used to store the ECG. Although the specifications of these formats are openly available, neither has been internationally adopted to be used with all ECG machines. Therefore, there remains a lack of global interoperability of ECG information.     

穿戴式心电:发展历程、核心技术与未来挑战

随着物联网、大数据、云计算、人工智能等先进科技的迅猛发展,动态心电监测近年来朝着可穿戴、智能化、便捷化的方向快速发展。穿戴式心电设备能够实现心电数据的个体化、实时、长程、连续监护,可为智慧医疗新模式提供重要载体和技术手段。回顾穿戴式心电的基本概念和发展历程,综述其信号感知和处理等方面的核心技术和当前代表性的穿戴式心电设备,并对穿戴式心电未来发展趋势和面临挑战进行剖析和展望。