Deep Deterministic Learning for Pattern Recognition of Different Cardiac Diseases through the Internet of Medical Things

Electrocardiography (ECG) sensors play a vital role in the Internet of Medical Things, and these sensors help in monitoring the electrical activity of the heart. ECG signal analysis can improve human life in many ways, from diagnosing diseases among cardiac patients to managing the lifestyles of diabetic patients. Abnormalities in heart activities lead to different cardiac diseases and arrhythmia. However, some cardiac diseases, such as myocardial infarction (MI) and atrial fibrillation (Af), require special attention due to their direct impact on human life. The classification of flattened T wave cases of MI in ECG signals and how much of these cases are similar to ST-T changes in MI remain an open issue for researchers. This article presents a novel contribution to classify MI and Af. To this end, we propose a new approach called deep deterministic learning (DDL), which works by combining predefined heart activities with fused datasets. In this research, we used two datasets. The first dataset, Massachusetts Institute of Technology–Beth Israel Hospital, is publicly available, and we exclusively obtained the second dataset from the University of Malaya Medical Center, Kuala Lumpur Malaysia. We first initiated predefined activities on each individual dataset to recognize patterns between the ST-T change and flattened T wave cases and then used the data fusion approach to merge both datasets in a manner that delivers the most accurate pattern recognition results. The proposed DDL approach is a systematic stage-wise methodology that relies on accurate detection of R peaks in ECG signals, time domain features of ECG signals, and fine tune-up of artificial neural networks. The empirical evaluation shows high accuracy (i.e., ≤99.97%) in pattern matching ST-T changes and flattened T waves using the proposed DDL approach. The proposed pattern recognition approach is a significant contribution to the diagnosis of special cases of MI.     

Detection of Cardiac Abnormalities from Multilead ECG using Multiscale Phase Alternation Features

The cardiac activities such as the depolarization and the relaxation of atria and ventricles are observed in electrocardiogram (ECG). The changes in the morphological features of ECG are the symptoms of particular heart pathology. It is a cumbersome task for medical experts to visually identify any subtle changes in the morphological features during 24 hours of ECG recording. Therefore, the automated analysis of ECG signal is a need for accurate detection of cardiac abnormalities. In this paper, a novel method for automated detection of cardiac abnormalities from multilead ECG is proposed. The method uses multiscale phase alternation (PA) features of multilead ECG and two classifiers, k-nearest neighbor (KNN) and fuzzy KNN for classification of bundle branch block (BBB), myocardial infarction (MI), heart muscle defect (HMD) and healthy control (HC). The dual tree complex wavelet transform (DTCWT) is used to decompose the ECG signal of each lead into complex wavelet coefficients at different scales. The phase of the complex wavelet coefficients is computed and the PA values at each wavelet scale are used as features for detection and classification of cardiac abnormalities. A publicly available multilead ECG database (PTB database) is used for testing of the proposed method. The experimental results show that, the proposed multiscale PA features and the fuzzy KNN classifier have better performance for detection of cardiac abnormalities with sensitivity values of 78.12 %, 80.90 % and 94.31 % for BBB, HMD and MI classes. The sensitivity value of proposed method for MI class is compared with the state-of-art techniques from multilead ECG.     

Fetal Electrocardiogram Extraction and Analysis Using Adaptive Noise Cancellation and Wavelet Transformation Techniques

Birth defect-related demise is mainly due to congenital heart defects. In the earlier stage of pregnancy, fetus problem can be identified by finding information about the fetus to avoid stillbirths. The gold standard used to monitor the health status of the fetus is by Cardiotachography(CTG), cannot be used for long durations and continuous monitoring. There is a need for continuous and long duration monitoring of fetal ECG signals to study the progressive health status of the fetus using portable devices. The non-invasive method of electrocardiogram recording is one of the best method used to diagnose fetal cardiac problem rather than the invasive methods.The monitoring of the fECG requires development of a miniaturized hardware and a efficient signal processing algorithms to extract the fECG embedded in the mother ECG. The paper discusses a prototype hardware developed to monitor and record the raw mother ECG signal containing the fECG and a signal processing algorithm to extract the fetal Electro Cardiogram signal. We have proposed two methods of signal processing, first is based on the Least Mean Square (LMS) Adaptive Noise Cancellation technique and the other method is based on the Wavelet Transformation technique. A prototype hardware was designed and developed to acquire the raw ECG signal containing the mother and fetal ECG and the signal processing techniques were used to eliminate the noises and extract the fetal ECG and the fetal Heart Rate Variability was studied. Both the methods were evaluated with the signal acquired from a fetal ECG simulator, from the Physionet database and that acquired from the subject. Both the methods are evaluated by finding heart rate and its variability, amplitude spectrum and mean value of extracted fetal ECG. Also the accuracy, sensitivity and positive predictive value are also determined for fetal QRS detection technique. In this paper adaptive filtering technique uses Sign-sign LMS algorithm and wavelet techniques with Daubechies wavelet, employed along with de noising techniques for the extraction of fetal Electrocardiogram.Both the methods are having good sensitivity and accuracy. In adaptive method the sensitivity is 96.83, accuracy 89.87, wavelet sensitivity is 95.97 and accuracy is 88.5. Additionally, time domain parameters from the plot of heart rate variability of mother and fetus are analyzed.     

Novel Approach to Fuzzy-Wavelet ECG Signal Analysis for a Mobile Device

This paper describes a signal processing technique for ECG signal analysis based upon the combination of wavelet analysis and fuzzy c-means clustering. The signal analysis technique is implemented into a biomedical signal diagnostic unit that is the carry on device for the Wireless Nano-Bios Diagnostic System (WNBDS) developed at National Taiwan University. The WNBDS integrates mobile devices and remote data base servers to conduct online monitoring and remote healthcare applications. The signal analysis and diagnostic algorithms in this paper are implemented in an embedded mobile device to conduct mobile biomedical signal diagnostics. At this stage, the Electrocardiogram (ECG or EKG) is analyzed for patient health monitoring. The ECG signal processing is based on the wavelet analysis, and the diagnosis is based on fuzzy clustering. The embedded system is realized with the Windows CE operating system.     

预激综合征合并急性心肌梗死心电图分析

预激综合征掩盖心肌梗死,预激综合征合并心肌梗死是心电图诊断的难点.本文分析1例预激综合征合并急性心肌梗死、预激波一度消失的心电图演变,讨论预激综合征并心肌梗死的心电图诊断和心肌梗死对预激综合征心电图的影响.     

小波变换在心电图ST段识别中的应用

目的:探讨基于小波变换的心电图ST段形态的识别算法.方法:首先利用二次样条小波对心电信号进行分解,并根据信号奇异点与其小波变换模极大值的对应关系,提出了在不同尺度下进行心电信号中关键特征点的提取策略;然后对ST段进行直线拟合,识别出ST段的形态;最后采用MIT/BIH标准心电数据库的数据进行检验.结果:利用作者所提算法编制的自动诊断软件能较准确地提取心电信号的特征点,成功识别了ST段的形态.结论:该自动分析算法可以提高ST段分析的准确性和可靠性,为临床诊断冠心病提供更准确的依据.     

Frontal Plane Vectorcardiograms: Theory and Graphics Visualization of Cardiac Health Status

The electrocardiogram (ECG) is a representative signal containing information about the condition of the heart. The shape and size of the P-QRS-T wave, the time intervals between its various peaks, may contain useful information about the nature of disease afflicting the heart. However, these subtle details cannot be directly monitored by the human observer. Besides, these signals are highly subjective, and the symptoms may appear at random in the time scale. It is very taxing and time-consuming to decipher cardiac abnormalities based on these ECG signals. The Vectorcardiogram (VCG) is the vector loop in the 2-D frontal plane, indicating the magnitude and direction of the instantaneous heart electrical activity vector (HAV), which represents the sum of the dipole vectors located along the instantaneous depolarization wavefront. The HAV is constructed from the monitored 3-lead ECG signals, placed at the three vertices of the modified Einthoven triangle formed by the 3-lead system in the frontal plane of the torso. The VCG examines the electrical activities within the heart, using the ECG signals along the three sides of the modified Einthoven triangle, and displays electrical events in the 2-dimensional frontal plane. This study demonstrates the development of the heart-depolarisation vector-locus cardiogram (using modified Einthoven’s triangle), as a diagnostic measure of the left ventricular depolarisation strength. Our work involves the reconstruction of the “equivalent heart vector” for the QRS complex from limb lead voltages of a sample ECG, and plotting the progression of the cardiac vector during the QRS complex. We have demonstrated the construction of the frontal plane heart-depolarization vector cardiogram (HDVC), as the path of the locus of the tip of the heart electrical activity vector, with initial and terminal points at the origin. In this work, we have shown characteristic patterns of HDVC for cardiac states namely, normal, bundle branch block, ventricular hypertrophy and myocardial infarction. We have demonstrated how HDVC can be diagnostically employed to characterize cardiac disorders, such as ventricular hypertrophy bundle branch block and inferior myocardial infarction.     

Detection and Localization of Myocardial Infarction using K-nearest Neighbor Classifier

This paper presents automatic detection and localization of myocardial infarction (MI) using K-nearest neighbor (KNN) classifier. Time domain features of each beat in the ECG signal such as T wave amplitude, Q wave and ST level deviation, which are indicative of MI, are extracted from 12 leads ECG. Detection of MI aims to classify normal subjects without myocardial infarction and subjects suffering from Myocardial Infarction. For further investigation, Localization of MI is done to specify the region of infarction of the heart. Total 20,160 ECG beats from PTB database available on Physio-bank is used to investigate the performance of extracted features with KNN classifier. In the case of MI detection, sensitivity and specificity of KNN is found to be 99.9% using half of the randomly selected beats as training set and rest of the beats for testing. Moreover, Arif-Fayyaz pruning algorithm is used to prune the data which will reduce the storage requirement and computational cost of search. After pruning, sensitivity and specificity are dropped to 97% and 99.6% respectively but training is reduced by 93%. Myocardial Infarction beats are divided into ten classes based on the location of the infarction along with one class of normal subjects. Sensitivity and Specificity of above 90% is achieved for all eleven classes with overall classification accuracy of 98.8%. Some of the ECG beats are misclassified but interestingly these are misclassified to those classes whose location of infarction is near to the true classes of the ECG beats. Pruning is done on the training set for eleven classes and training set is reduced by 70% and overall classification accuracy of 98.3% is achieved. The proposed method due to its simplicity and high accuracy over the PTB database can be very helpful in correct diagnosis of MI in a practical scenario.     

Internet of Things with Maximal Overlap Discrete Wavelet Transform for Remote Health Monitoring of Abnormal ECG Signals

In this paper, MODWT is used to decompose the Electrocardiography (ECG) signals and to identify the changes of R waves in the noisy input ECG signal. The MODWT is used to handle the arbitrary changes in the input signal. The R wave’s detctected by the proposed framework is used by the doctors and careholders to take necessary action for the patients. MATLAB simulink model is used to develop the simulation model for the MODWT method. The performance of the MODWT based remote health monitoring system method is comparatively analyzed with other ECG monitoring approaches such as Haar Wavelet Transformation (HWT) and Discrete Wavelet Transform (DWT). Sensitivity, specificity, and Receiver Operating Characteristic (ROC) curve are calculated to evaluate the proposed Internet of Things with MODWT based ECG monitoring system. We have used MIT-BIH Arrythmia Database to perform the experiments.     

Medical Decision Support System for Diagnosis of Heart Arrhythmia using DWT and Random Forests Classifier

In this study, Random Forests (RF) classifier is proposed for ECG heartbeat signal classification in diagnosis of heart arrhythmia. Discrete wavelet transform (DWT) is used to decompose ECG signals into different successive frequency bands. A set of different statistical features were extracted from the obtained frequency bands to denote the distribution of wavelet coefficients. This study shows that RF classifier achieves superior performances compared to other decision tree methods using 10-fold cross-validation for the ECG datasets and the obtained results suggest that further significant improvements in terms of classification accuracy can be accomplished by the proposed classification system. Accurate ECG signal classification is the major requirement for detection of all arrhythmia types. Performances of the proposed system have been evaluated on two different databases, namely MIT-BIH database and St. -Petersburg Institute of Cardiological Technics 12-lead Arrhythmia Database. For MIT-BIH database, RF classifier yielded an overall accuracy 99.33 % against 98.44 and 98.67 % for the C4.5 and CART classifiers, respectively. For St. -Petersburg Institute of Cardiological Technics 12-lead Arrhythmia Database, RF classifier yielded an overall accuracy 99.95 % against 99.80 % for both C4.5 and CART classifiers, respectively. The combined model with multiscale principal component analysis (MSPCA) de-noising, discrete wavelet transform (DWT) and RF classifier also achieves better performance with the area under the receiver operating characteristic (ROC) curve (AUC) and F-measure equal to 0.999 and 0.993 for MIT-BIH database and 1 and 0.999 for and St. -Petersburg Institute of Cardiological Technics 12-lead Arrhythmia Database, respectively. Obtained results demonstrate that the proposed system has capacity for reliable classification of ECG signals, and to assist the clinicians for making an accurate diagnosis of cardiovascular disorders (CVDs).     

Wavelet Transformation Based Watermarking Technique for Human Electrocardiogram (ECG)

Nowadays, watermarking has become a technology of choice for a broad range of multimedia copyright protection applications. Watermarks have also been used to embed prespecified data in biomedical signals. Thus, the watermarked biomedical signals being transmitted through communication are resistant to some attacks. This paper investigates discrete wavelet transform based watermarking technique for signal integrity verification in an Electrocardiogram (ECG) coming from four ECG classes for monitoring application of cardiovascular diseases. The proposed technique is evaluated under different noisy conditions for different wavelet functions. Daubechies (db2) wavelet function based technique performs better than those of Biorthogonal (bior5.5) wavelet function. For the beat-to-beat applications, all performance results belonging to four ECG classes are highly moderate.     

压力负荷型慢性心衰大鼠的心电图特征

目的采用心电图检测压力负荷型慢性心衰大鼠并分析其特点。方法 20只雄性SD大鼠随机分成假手术组(S组)和心衰组(HF组)。心衰组采用腹主动脉缩窄法制备模型,假手术组只穿线不缩窄。Ⅱ导联心电图检测肢体导联并统计分析数据。结果术后10周,心电图检测显示几个特点:心衰组(HF组):1心率、P波振幅和P波时限都明显增加(P0.05);2R波振幅明显大于S组大鼠(P0.05);3心电图的J点位移明显抬高(P0.05),而ST高度则明显降低(P0.05)。结论压力负荷型心衰大鼠的心电图特征明显,心电图检测作为一种无创的方法可以有效的评价大鼠压力负荷型心力衰竭。     

Field Programmable Gate Array Based Fuzzy Neural Signal Processing System for Differential Diagnosis of QRS Complex Tachycardia and Tachyarrhythmia in Noisy ECG Signals

The paper reports of a Field Programmable Gate Array (FPGA) based embedded system for detection of QRS complex in a noisy electrocardiogram (ECG) signal and thereafter differential diagnosis of tachycardia and tachyarrhythmia. The QRS complex has been detected after application of entropy measure of fuzziness to build a detection function of ECG signal, which has been previously filtered to remove power line interference and base line wander. Using the detected QRS complexes, differential diagnosis of tachycardia and tachyarrhythmia has been performed. The entire algorithm has been realized in hardware on an FPGA. Using the standard CSE ECG database, the algorithm performed highly effectively. The performance of the algorithm in respect of QRS detection with sensitivity (Se) of 99.74% and accuracy of 99.5% is achieved when tested using single channel ECG with entropy criteria. The performance of the QRS detection system has been compared and found to be better than most of the QRS detection systems available in literature. Using the system, 200 patients have been diagnosed with an accuracy of 98.5%.     

牡荆素对大鼠实验性心肌缺血损伤的保护作用及其机制

目的 研究牡荆素对实验性心肌缺血大鼠心肌损伤的保护作用及对其能量代谢的影响。方法 采用在体结扎大鼠心脏冠状动脉前降支法及舌下iv给予垂体后叶素（Pit）法建立大鼠心肌缺血损伤模型。在体大鼠缺血再灌注模型上,TTC染色法检测大鼠心肌梗死面积,并测定大鼠血清乳酸脱氢酶（LDH）和肌酸激酶（CK）活性;Pit致大鼠心肌缺血损伤模型上,检测大鼠心电图（ECG）、血清中LDH、CK、超氧化物歧化酶（SOD）、谷胱甘肽过氧化物酶（GSH-Px）活性及大鼠心肌组织中ATP酶活性,并观察大鼠心肌组织病理学改变。结果 牡荆素6、3、1.5 mg/kg可显著降低大鼠心肌梗死面积（P＜0.05、0.01）,并能不同程度地降低血清中LDH和CK的活性。注射Pit后,模型组大鼠各时间点ECG的ST段变化值与对照组比较显著升高（P＜0.01）;葛根素与牡荆素（6、3 mg/kg）能显著降低Pit致大鼠心肌缺血升高的ST段（P＜0.05、0.01）。牡荆素（6、3 mg/kg）降低血清中LDH和CK的活性（P＜0.05、0.01）,同时升高血清中SOD及GSH-Px的活性（P＜0.05、0.01）;牡荆素6、3、1.5 mg/kg和葛根素能明显升高缺血心肌组织中Na⁺, K^＋-ATP酶,Ca²⁺, Mg²⁺-ATP酶及总ATP酶的活性（P＜0.05、0.01）。牡荆素（6、3 mg/kg）可明显改善缺血心肌的病理损伤程度。结论 牡荆素对大鼠急性心肌缺血损伤具有明显保护作用,其作用与提高心肌组织抗氧化能力,改善心肌能量代谢有关。     

Reaction to Cold of Patients with Coronary Insufficiency

Twenty six patients with angina pectoris and coronary insufficiency as judged by an exercise ECG test were examined. About half of the patients had more pronounced ECG changes in a cold room at ?15°C than at room temperature. They worked less, their subjective rating of exertion during exercise was higher and the heart performed less work, expressed as the heart rate blood pressure product. The other half of the patients was not much influenced by cold.

During an exercise test in the supine position almost all patients got more pronounced ECG changes, worked less and the heart performed less work than in the sitting position.

It is suggested that cold exposure as well as a supine body position may to a considerable part exert their effect, i.e. lower the anginal threshold and increase ECG changes, by increasing the central blood volume and the diastolic volume of the left heart and thus ceteres paribus the myocardial oxygen consumption.     

A New QRS Detection Method Using Wavelets and Artificial Neural Networks

We present a new method for detection and classification of QRS complexes in ECG signals using continuous wavelets and neural networks. Our wavelet method consists of four wavelet basis functions that are suitable in detection of QRS complexes within different QRS morphologies in the signal and thresholding technique for denoising and feature extraction. The results demonstrate that the proposed method is not only efficient for normal ECG signal analysis but also for various types of arrhythmic cardiac signals embedded in noise. For the classification stage, a feedforward neural network was trained with standard backpropagation algorithm. The classifier input features consisted of compact wavelet coefficients of QRS complexes that resulted in higher classification rates. We demonstrate the efficiency of our method with the average accuracy 97.2% in classification of normal and abnormal QRS complexes.     

Variable Threshold Method for ECG R-peak Detection

In this paper, a wearable belt-type ECG electrode worn around the chest by measuring the real-time ECG is produced in order to minimize the inconvenient in wearing. ECG signal is detected using a potential instrument system. The measured ECG signal is transmits via an ultra low power consumption wireless data communications unit to personal computer using Zigbee-compatible wireless sensor node. ECG signals carry a lot of clinical information for a cardiologist especially the R-peak detection in ECG. R-peak detection generally uses the threshold value which is fixed. There will be errors in peak detection when the baseline changes due to motion artifacts and signal size changes. Preprocessing process which includes differentiation process and Hilbert transform is used as signal preprocessing algorithm. Thereafter, variable threshold method is used to detect the R-peak which is more accurate and efficient than fixed threshold value method. R-peak detection using MIT-BIH databases and Long Term Real-Time ECG is performed in this research in order to evaluate the performance analysis.     

Human Identification Using Compressed ECG Signals

As a result of the increased demand for improved life styles and the increment of senior citizens over the age of 65, new home care services are demanded. Simultaneously, the medical sector is increasingly becoming the new target of cybercriminals due the potential value of users’ medical information. The use of biometrics seems an effective tool as a deterrent for many of such attacks. In this paper, we propose the use of electrocardiograms (ECGs) for the identification of individuals. For instance, for a telecare service, a user could be authenticated using the information extracted from her ECG signal. The majority of ECG-based biometrics systems extract information (fiducial features) from the characteristics points of an ECG wave. In this article, we propose the use of non-fiducial features via the Hadamard Transform (HT). We show how the use of highly compressed signals (only 24 coefficients of HT) is enough to unequivocally identify individuals with a high performance (classification accuracy of 0.97 and with identification system errors in the order of 10^?2).     

GPRS移动式心电监护系统的QRS波实时检测算法

目的探讨GPRS移动式心电监护系统ECG信号QRS波的实时检测算法.方法采用四点平均对CM5导联的ECG信号进行滤波,再对ECG信号的一、二阶差分值进行平滑处理,利用ECG信号的二阶差分值极小值和一阶差分过零点在较短的时间窗内实现QRS波精确定位,并设计了具有自学习和自适应功能的信号检测门限.结果算法能抑止多种噪声对ECG信号的影响,将搜索的时间窗宽度缩小到0.02 s以下,且算法只具有多项式的复杂度;经过临床测试,动态ECG信号进QRS波检测准确率可达99.8%以上.结论该算法适合于移动心电监护系统QRS波的实时检测和分析.     

胎儿心电信号的无创提取：基于时间卷积编解码网络

目的 实现从孕妇腹壁混合心电信号中提取微弱的胎儿心电信号,为准确估计胎儿心率、分析胎儿心电波形等提供基础。方法 利用深度卷积网络（deep CNN）优越的非线性映射能力,本文提出了一种基于时间卷积编解码网络的非线性自适应噪声消除（nonlinear ANC）提取框架,以实现胎儿心电信号的有效提取。首先构建适用于处理胎儿心电信号的深度时间卷积网络（TCED-Net）模型作为非线性映射工具;然后以孕妇胸部心电信号为参考,利用该模型估计孕妇腹壁混合心电信号中的母体心电成分;最后从腹壁混合信号中减去所估计的母体心电成分,以得到完整的胎儿心电信号。实验利用合成心电数据（FECGSYNDB）和临床心电数据（NIFECGDB、PCDB）对方法性能进行测试与对比。结果 本文方法在FECGSYNDB上的胎儿R峰检测精度（[F1]值）、均方误差（MSE）和质量信噪比（qSNR）分别达到98.89 %,0.20和7.84;在NIFECGDB上的[F1]值达到99.1%;在 PCDB 上的[F1]值达到 98.61%。在不同数据集中较之 EKF（[F1=]93.84%）、ES-RNN([F1] =97.20% )和 AECG-DecompNet（[F1]=95.43%）等现有性能最佳的算法,本文方法的R峰检测精度指标分别高出5.05%、1.9%和3.18%,均优于现有最佳方法。结论 与现有算法相比,本文方法可以提取出更为清晰的胎儿心电信号,对孕期进行有效的胎儿健康监护具有一定的应用价值。