An arrhythmia classification system based on the RR-interval signal

Cardiologist-level interpretable knowledge-fused deep neural network for automatic arrhythmia diagnosis

BACKGROUND

Long-term monitoring of Electrocardiogram (ECG) recordings is crucial to diagnose arrhythmias. Clinicians can find it challenging to diagnose arrhythmias, and this is a particular issue in more remote and underdeveloped areas. The development of digital ECG and AI methods could assist clinicians who need to diagnose arrhythmias outside of the hospital setting.

METHODS

We constructed a large-scale Chinese ECG benchmark dataset using data from 272,753 patients collected from January 2017 to December 2021. The dataset contains ECG recordings from all common arrhythmias present in the Chinese population. Several experienced cardiologists from Shanghai First People's Hospital labeled the dataset. We then developed a deep learning-based multi-label interpretable diagnostic model from the ECG recordings. We utilized Accuracy, F1 score and AUC-ROC to compare the performance of our model with that of the cardiologists, as well as with six comparison models, using testing and hidden data sets.

RESULTS

The results show that our approach achieves an F1 score of 83.51%, an average AUC ROC score of 0.977, and 93.74% mean accuracy for 6 common arrhythmias. Results from the hidden dataset demonstrate the performance of our approach exceeds that of cardiologists. Our approach also highlights the diagnostic process.

CONCLUSIONS

Our diagnosis system has superior diagnostic performance over that of clinicians. It also has the potential to help clinicians rapidly identify abnormal regions on ECG recordings, thus improving efficiency and accuracy of clinical ECG diagnosis in China. This approach could therefore potentially improve the productivity of out-of-hospital ECG diagnosis and provides a promising prospect for telemedicine.

Artificial intelligence cloud platform improves arrhythmia detection from insertable cardiac monitors to 25 cardiac rhythm patterns through multi-label classification

BACKGROUND

Electrocardiogram (ECG) is the gold standard for the diagnosis of cardiac arrhythmias and other heart diseases. Insertable cardiac monitors (ICMs) have been developed to continuously monitor cardiac activity over long periods of time and to detect 4 cardiac patterns (atrial tachyarrhythmias, ventricular tachycardia, bradycardia, and pause). However, interpretation of ECG or ICM subcutaneous ECG (sECG) is time-consuming for clinicians. Artificial intelligence (AI) classifies ECG and sECG with high accuracy in short times.

OBJECTIVE

To demonstrate whether an AI algorithm can expand ICM arrhythmia recognition from 4 to many cardiac patterns.

METHODS

We performed an exploratory retrospective study with sECG raw data coming from 20 patients wearing a Confirm Rx™ (Abbott, Sylmar, USA) ICM. The sECG data were recorded in standard conditions and then analyzed by AI (Willem™, IDOVEN, Madrid, Spain) and cardiologists, in parallel.

RESULTS

In nineteen patients, ICMs recorded 2261 sECGs in an average follow-up of 23 months. Within these 2261 sECG episodes, AI identified 7882 events and classified them according to 25 different cardiac rhythm patterns with a pondered global accuracy of 88%. Global positive predictive value, sensitivity, and F1-score were 86.77%, 83.89%, and 85.52% respectively. AI was especially sensitive for bradycardias, pauses, rS complexes, premature atrial contractions, and inverted T waves, reducing the median time spent to classify each sECG compared to cardiologists.

CONCLUSION

AI can process sECG raw data coming from ICMs without previous training, extending the performance of these devices and saving cardiologists' time in reviewing cardiac rhythm patterns detection.

MCHeart: Multi-Channel-Based Heart Signal Processing Scheme for Heart Noise Detection Using Deep Learning

In this study, we constructed a model to predict abnormal cardiac sounds using a diverse set of auscultation data collected from various auscultation positions. Abnormal heart sounds were identified by extracting features such as peak intervals and noise characteristics during systole and diastole. Instead of using raw signal data, we transformed them into log-mel 2D spectrograms, which were employed as input variables for the CNN model. The advancement of our model involves integrating a deep learning architecture with feature extraction techniques based on existing knowledge of cardiac data. Specifically, we propose a multi-channel-based heart signal processing (MCHeart) scheme, which incorporates our proposed features into the deep learning model. Additionally, we introduce the ReLCNN model by applying residual blocks and MHA mechanisms to the LCNN architecture. By adding murmur features with a smoothing function and training the ReLCNN model, the weighted accuracy of the model increased from 79.6% to 83.6%, showing a performance improvement of approximately 4% point compared to the LCNN baseline model.

Effects of Triiodothyronine Treatment in an Animal Model of Heart Failure with Preserved Ejection Fraction

Background: Low levels of triiodothyronine (T3) are common in patients with heart failure (HF). Our aim was to evaluate the effects of supplementation with low and replacement doses of T3 in an animal model of HF with preserved ejection fraction (HFpEF). Methods: We evaluated four groups: ZSF1 Lean (n = 8, Lean-Ctrl), ZSF1 Obese (rat model of metabolic-induced HFpEF, n = 13, HFpEF), ZSF1 Obese treated with a replacement dose of T3 (n = 8, HFpEF-T3high), and ZSF1 Obese treated with a low-dose of T3 (n = 8, HFpEF-T3low). T3 was administered in drinking water from weeks 13 to 24. The animals underwent anthropometric and metabolic assessments, echocardiography, and peak effort testing with maximum O2 consumption (VO2max) determination at 22 weeks, and a terminal hemodynamic evaluation at 24 weeks. Afterwhile myocardial samples were collected for single cardiomyocyte evaluation and molecular studies. Results: HFpEF animals showed lower serum and myocardial thyroid hormone levels than Lean-Ctrl. Treatment with T3 did not normalize serum T3 levels, but increased myocardial T3 levels to normal levels in the HFpEF-T3high group. Body weight was significantly decreased in both the T3-treated groups, comparing with HFpEF. An improvement in glucose metabolism was observed only in HFpEF-T3high. Both the treated groups had improved diastolic and systolic function in vivo, as well as improved Ca2+ transients and sarcomere shortening and relaxation in vitro. Comparing with HFpEF animals, HFpEF-T3high had increased heart rate and a higher rate of premature ventricular contractions. Animals treated with T3 had higher myocardial expression of calcium transporter ryanodine receptor 2 (RYR2) and α-myosin heavy chain (MHC), with a lower expression of β-MHC. VO2max was not influenced by treatment with T3. Myocardial fibrosis was reduced in both the treated groups. Three animals died in the HFpEF-T3high group. Conclusions: Treatment with T3 was shown to improve metabolic profile, myocardial calcium handling, and cardiac function. While the low dose was well-tolerated and safe, the replacement dose was associated with increased heart rate, and increased risk of arrhythmias and sudden death. Modulation of thyroid hormones may be a potential therapeutic target in HFpEF; however, it is important to take into account the narrow therapeutic window of T3 in this condition.

Two-dimensional ECG-based cardiac arrhythmia classification using DSE-ResNet

Electrocardiogram (ECG) is mostly used for the clinical diagnosis of cardiac arrhythmia due to its simplicity, non-invasiveness, and reliability. Recently, many models based on the deep neural networks have been applied to the automatic classification of cardiac arrhythmia with great success. However, most models independently extract the internal features of each lead in the 12-lead ECG during the training phase, resulting in a lack of inter-lead features. Here, we propose a general model based on the two-dimensional ECG and ResNet with detached squeeze-and-excitation modules (DSE-ResNet) to realize the automatic classification of normal rhythm and 8 cardiac arrhythmias. The original 12-lead ECG is spliced into a two-dimensional plane like a grayscale picture. DSE-ResNet is used to simultaneously extract the internal and inter-lead features of the two-dimensional ECG. Furthermore, an orthogonal experiment method is used to optimize the hyper-parameters of DSE-ResNet and a multi-model voting strategy is used to improve classification performance. Experimental results based on the test set of China Physiological Signal Challenge 2018 (CPSC2018) show that our model has average \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$F_1= 0.817$$\end{document}F1=0.817 for classifying normal rhythm and 8 cardiac arrhythmias. Meanwhile, compared with the state-of-art model in CPSC2018, our model achieved the best \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$F_1$$\end{document}F1 in 2 sub-abnormal types. This shows that the model based on the two-dimensional ECG and DSE-ResNet has advantage in detecting some cardiac arrhythmias and has the potential to be used as an auxiliary tool to help doctors perform cardiac arrhythmias analysis.

A Heartbeat Classifier for Continuous Prediction Using a Wearable Device

Heartbeat monitoring may play an essential role in the early detection of cardiovascular disease. When using a traditional monitoring system, an abnormal heartbeat may not appear during a recording in a healthcare facility due to the limited time. Thus, continuous and long-term monitoring is needed. Moreover, the conventional equipment may not be portable and cannot be used at arbitrary times and locations. A wearable sensor device such as Polar H10 offers the same capability as an alternative. It has gold-standard heartbeat recording and communication ability but still lacks analytical processing of the recorded data. An automatic heartbeat classification system can play as an analyzer and is still an open problem in the development stage. This paper proposes a heartbeat classifier based on RR interval data for real-time and continuous heartbeat monitoring using the Polar H10 wearable device. Several machine learning and deep learning methods were used to train the classifier. In the training process, we also compare intra-patient and inter-patient paradigms on the original and oversampling datasets to achieve higher classification accuracy and the fastest computation speed. As a result, with a constrain in RR interval data as the feature, the random forest-based classifier implemented in the system achieved up to 99.67% for accuracy, precision, recall, and F1-score. We are also conducting experiments involving healthy people to evaluate the classifier in a real-time monitoring system.

Classification of ECG signals using multi-cumulants based evolutionary hybrid classifier

Every human being has a different electro-cardio-graphy (ECG) waveform that provides information about the well being of a human heart. Therefore, ECG waveform can be used as an effective identification measure in biometrics and many such applications of human identification. To achieve fast and accurate identification of human beings using ECG signals, a novel robust approach has been introduced here. The databases of ECG utilized during the experimentation are MLII, UCI repository arrhythmia and PTBDB databases. All these databases are imbalanced; hence, resampling techniques are helpful in making the databases balanced. Noise removal is performed with discrete wavelet transform (DWT) and features are obtained with multi-cumulants. This approach is mainly based on features extracted from the ECG data in terms of multi-cumulants. The multi-cumulants feature based ECG data is classified using kernel extreme learning machine (KELM). The parameters of multi-cumulants and KELM are optimized using genetic algorithm (GA). Excellent classification rate is achieved with 100% accuracy on MLII and UCI repository arrhythmia databases, and 99.57% on PTBDB database. Comparison with existing state-of-art approaches has also been performed to prove the efficacy of the proposed approach. Here, the process of classification in the proposed approach is named as evolutionary hybrid classifier.

Heartbeat Classification Based on Multifeature Combination and Stacking-DWKNN Algorithm

Arrhythmia is one of the most common abnormal symptoms that can threaten human life. In order to distinguish arrhythmia more accurately, the classification strategy of the multifeature combination and Stacking-DWKNN algorithm is proposed in this paper. The method consists of four modules. In the preprocessing module, the signal is denoised and segmented. Then, multiple different features are extracted based on single heartbeat morphology, P length, QRS length, T length, PR interval, ST segment, QT interval, RR interval, R amplitude, and T amplitude. Subsequently, the features are combined and normalized, and the effect of different feature combinations on heartbeat classification is analyzed to select the optimal feature combination. Finally, the four types of normal and abnormal heartbeats were identified using the Stacking-DWKNN algorithm. This method is performed on the MIT-BIH arrhythmia database. The result shows a sensitivity of 89.42% and a positive predictive value of 94.90% of S-type beats and a sensitivity of 97.21% and a positive predictive value of 97.07% of V-type beats. The obtained average accuracy is 99.01%. Compared to other models with the same features, this method can improve accuracy and has a higher positive predictive value and sensitivity, which is important for clinical decision-making.

Investigating Feature Selection and Random Forests for Inter-Patient Heartbeat Classification

Finding an optimal combination of features and classifier is still an open problem in the development of automatic heartbeat classification systems, especially when applications that involve resource-constrained devices are considered. In this paper, a novel study of the selection of informative features and the use of a random forest classifier while following the recommendations of the Association for the Advancement of Medical Instrumentation (AAMI) and an inter-patient division of datasets is presented. Features were selected using a filter method based on the mutual information ranking criterion on the training set. Results showed that normalized beat-to-beat (R–R) intervals and features relative to the width of the ventricular depolarization waves (QRS complex) are the most discriminative among those considered. The best results achieved on the MIT-BIH Arrhythmia Database were an overall accuracy of 96.14% and F1-scores of 97.97%, 73.06%, and 90.85% in the classification of normal beats, supraventricular ectopic beats, and ventricular ectopic beats, respectively. In comparison with other state-of-the-art approaches tested under similar constraints, this work represents one of the highest performances reported to date while relying on a very small feature vector.

Study on forced degradation behaviour of dofetilide by LC-PDA and Q-TOF/MS/MS: Mechanistic explanations of hydrolytic, oxidative and photocatalytic rearrangement of degradation products

A solution and solid state forced decomposition study was carried on dofetilide under diverse stress conditions of hydrolysis, oxidation, photolysis and thermal as per International Council for Harmonisation guidelines (ICH) Q1A(R2) to understand its degradation behaviour. A total of eight degradation products (DPs) were identified and separated on reversed phase kromasil 100 C8 column (4.6 mm x 250 mm x5 μm) using gradient elution with ammonium acetate (10 mM, pH 6.2) and acetonitrile as mobile phase. The detection wavelength was selected as 230 nm. The high performance liquid chromatography (HPLC) study found that the drug was susceptible to hydrolytic stress condition, but it was highly unstable to photolytic and oxidative conditions. The solid drug was stable in thermal and photolytic conditions. Initially comprehensive mass fragmentation pattern of the drug was accomplished with the LC/ESI/QTOF/MS/MS studies in positive ionization mode. The same was followed for all the eight degradation products to characterise their structure. The DP4 was N-oxide and the structure was confirmed by LC/APCI/QTOF/MS/MS in positive ionization mode. The complete mass fragmentation pattern of the drug and its DPs were established which in turn helped the characterisation of their structures. The mechanistic pathway for the formation of all the DPs was explained.

A Wearable Electrocardiogram Telemonitoring System for Atrial Fibrillation Detection

In this paper we proposed a wearable electrocardiogram (ECG) telemonitoring system for atrial fibrillation (AF) detection based on a smartphone and cloud computing. A wearable ECG patch was designed to collect ECG signals and send the signals to an Android smartphone via Bluetooth. An Android APP was developed to display the ECG waveforms in real time and transmit every 30 s ECG data to a remote cloud server. A machine learning (CatBoost)-based ECG classification method was proposed to detect AF in the cloud server. In case of detected AF, the cloud server pushed the ECG data and classification results to the web browser of a doctor. Finally, the Android APP displayed the doctor's diagnosis for the ECG signals. Experimental results showed the proposed CatBoost classifier trained with 17 selected features achieved an overall F1 score of 0.92 on the test set (n = 7,270). The proposed wearable ECG monitoring system may potentially be useful for long-term ECG telemonitoring for AF detection.

Noninvasive Cardiorespiratory Signals Analysis for Asthma Evolution Monitoring in Preschool Children

OBJECTIVE

Despite its increasing prevalence, diagnosis of asthma in children remains problematic due to their difficulties in producing repeatable spirometric maneuvers. Moreover, low adherence to inhaled corticosteroids (ICS) treatment could result in permanent airway remodeling. The growing interest in a noninvasive and objective way for monitoring asthma, together with the apparent role of autonomic nervous system (ANS) in its pathogenesis, have attracted interest towards heart rate variability (HRV) and cardiorespiratory coupling (CRC) analyses.

METHODS

HRV and CRC were analyzed in 68 children who were prescribed ICS treatment due to recurrent obstructive bronchitis. They underwent three different electrocardiogram and respiratory signals recordings, during and after treatment period. After treatment completion, they were followed up during 6 months and classified attending to their current asthma status.

RESULTS

Vagal activity, as measured from HRV, and CRC, were reduced after treatment in those children at lower risk of asthma, whereas it kept unchanged in those with a worse prognosis.

CONCLUSION

Results suggest that HRV analysis could be useful for the continuous monitoring of ANS anomalies present in asthma, thus contributing to evaluate the evolution of the disease, which is especially challenging in young children.

SIGNIFICANCE

Noninvasive ANS assessment using HRV analysis could be useful in the continuous monitoring of asthma in children.

Usefulness of Trends in Continuous Electrocardiographic Telemetry Monitoring to Predict In-Hospital Cardiac Arrest

Survival from in-hospital cardiac arrest (IHCA) due to pulseless electrical activity/asystole remains poor. We aimed to evaluate whether electrocardiographic changes provide predictive information for risk of IHCA from pulseless electrical activity/asystole. We conducted a retrospective case-control study, utilizing continuous electrocardiographic data from case and control patients. We selected 3 consecutive 3-hour blocks (block 3, 2, and 1 in that order); block 1 immediately preceded cardiac arrest in cases, whereas block 1 was chosen at random in controls. In each block, we measured dominant positive and negative trends in electrocardiographic parameters, evaluated for arrhythmias, and compared these between consecutive blocks. We created random forest and logistic regression models, and tested them on differentiating case versus control patients (case block 1 vs control block 1), and temporal relation to cardiac arrest (case block 2 vs case block 1). Ninety-one cases (age 63.0 ± 17.6, 58% male) and 1,783 control patients (age 63.5 ± 14.8, 67% male) were evaluated. We found significant differences in electrocardiographic trends between case and control block 1, particularly in QRS duration, QTc, RR, and ST. New episodes of atrial fibrillation and bradyarrhythmias were more common before IHCA. The optimal model was the random forest, achieving an area under the curve of 0.829, 63.2% sensitivity, 94.6% specificity at differentiating case versus control block 1 on a validation set, and area under the curve 0.954, 91.2% sensitivity, 83.5% specificity at differentiating case block 1 versus case block 2. In conclusion, trends in electrocardiographic parameters during the 3-hour window immediately preceding IHCA differ significantly from other time periods, and provide robust predictive information.

A deep neural network learning algorithm outperforms a conventional algorithm for emergency department electrocardiogram interpretation

BACKGROUND

Cardiologs® has developed the first electrocardiogram (ECG) algorithm that uses a deep neural network (DNN) for full 12‑lead ECG analysis, including rhythm, QRS and ST-T-U waves. We compared the accuracy of the first version of Cardiologs® DNN algorithm to the Mortara/Veritas® conventional algorithm in emergency department (ED) ECGs.

METHODS

Individual ECG diagnoses were prospectively mapped to one of 16 pre-specified groups of ECG diagnoses, which were further classified as "major" ECG abnormality or not. Automated interpretations were compared to blinded experts'. The primary outcome was the performance of the algorithms in finding at least one "major" abnormality. The secondary outcome was the proportion of all ECGs for which all groups were identified, with no false negative or false positive groups ("accurate ECG interpretation"). Additionally, we measured sensitivity and positive predictive value (PPV) for any abnormal group.

RESULTS

Cardiologs® vs. Veritas® accuracy for finding a major abnormality was 92.2% vs. 87.2% (p < 0.0001), with comparable sensitivity (88.7% vs. 92.0%, p = 0.086), improved specificity (94.0% vs. 84.7%, p < 0.0001) and improved positive predictive value (PPV 88.2% vs. 75.4%, p < 0.0001). Cardiologs® had accurate ECG interpretation for 72.0% (95% CI: 69.6-74.2) of ECGs vs. 59.8% (57.3-62.3) for Veritas® (P < 0.0001). Sensitivity for any abnormal group for Cardiologs® and Veritas®, respectively, was 69.6% (95CI 66.7-72.3) vs. 68.3% (95CI 65.3-71.1) (NS). Positive Predictive Value was 74.0% (71.1-76.7) for Cardiologs® vs. 56.5% (53.7-59.3) for Veritas® (P < 0.0001).

CONCLUSION

Cardiologs' DNN was more accurate and specific in identifying ECGs with at least one major abnormal group. It had a significantly higher rate of accurate ECG interpretation, with similar sensitivity and higher PPV.

A topological approach to delineation and arrhythmic beats detection in unprocessed long-term ECG signals

BACKGROUND AND OBJECTIVE

Arrhythmias are one of the most common symptoms of cardiac failure. They are usually diagnosed using ECG recordings, particularly long ambulatory recordings (AECG). These recordings are tedious to interpret by humans due to their extent (up to 48 h) and the relative scarcity of arrhythmia events. This makes automated systems for detecting various AECG anomalies indispensable. In this work we present a novel procedure based on topological principles (Morse theory) for detecting arrhythmic beats in AECG. It works in nearly real-time (delayed by a 14 s window), and can be applied to raw (unprocessed) ECG signals.

METHODS

The procedure is based on a subject-specific adaptation of the one-dimensional discrete Morse theory (ADMT), which represents the signal as a sequence of its most important extrema. The ADMT algorithm is applied twice; for low-amplitude, high-frequency noise removal, and for detection of the characteristic waves of individual ECG beats. The waves are annotated using the ADMT algorithm and template matching. The annotated beats are then compared to the adjacent beats with two measures of similarity: the distance between two beats, and the difference in shape between them. The two measures of similarity are used as inputs to a decision tree algorithm that classifies the beats as normal or abnormal. The classification performance is evaluated with the leave-one-record-out cross-validation method.

RESULTS

Our approach was tested on the MIT-BIH database, where it exhibited a classification accuracy of 92.73%, a sensitivity of 73.35%, a specificity of 96.70%, a positive predictive value of 88.01%, and a negative predictive value of 95.73%.

CONCLUSIONS

Compared to related studies, our algorithm requires less preprocessing while retaining the capability to detect and classify beats in almost real-time. The algorithm exhibits a high degree of accuracy in beats detection and classification that are at least comparable to state-of-the-art methods.

Novel methods of testing and calibration of oscillometric blood pressure monitors

We present a robust method for testing and calibrating the performance of oscillometric non-invasive blood pressure (NIBP) monitors, using an industry standard NIBP simulator to determine the characteristic ratios used, and to explore differences between different devices. Assuming that classical auscultatory sphygmomanometry provides the best approximation to intra-arterial pressure, the results obtained from oscillometric measurements for a range of characteristic ratios are compared against a modified auscultatory method to determine an optimum characteristic ratio, Rs for systolic blood pressure (SBP), which was found to be 0.565. We demonstrate that whilst three Chinese manufactured NIBP monitors we tested used the conventional maximum amplitude algorithm (MAA) with characteristic ratios Rs = 0.4624±0.0303 (Mean±SD) and Rd = 0.6275±0.0222, another three devices manufactured in Germany and Japan either do not implement this standard protocol or used different characteristic ratios. Using a reference database of 304 records from 102 patients, containing both the Korotkoff sounds and the oscillometric waveforms, we showed that none of the devices tested used the optimal value of 0.565 for the characteristic ratio Rs, and as a result, three of the devices tested would underestimate systolic pressure by an average of 4.8mmHg, and three would overestimate the systolic pressure by an average of 6.2 mmHg.

Nocturnal Heart Rate Variability Spectrum Characterization in Preschool Children With Asthmatic Symptoms

Asthma is a chronic lung disease that usually develops during childhood. Despite that symptoms can almost be controlled with medication, early diagnosis is desirable in order to reduce permanent airway obstruction risk. It has been suggested that abnormal parasympathetic nervous system (PSNS) activity might be closely related with the pathogenesis of asthma, and that this PSNS activity could be reflected in cardiac vagal control. In this work, an index to characterize the spectral distribution of the high frequency (HF) component of heart rate variability (HRV), named peakness ($\wp$), is proposed. Three different implementations of $\wp$, based on electrocardiogram (ECG) recordings, impedance pneumography (IP) recordings and a combination of both, were employed in the characterization of a group of preschool children classified attending to their risk of developing asthma. Peakier components were observed in the HF band of those children classified as high-risk ( $p < 0.005$), who also presented reduced sympathvoagal balance. Results suggest that high-risk of developing asthma might be related with a lack of adaptability of PSNS.

Irregular heartbeat classification using Kronecker Product Equations

Cardiac arrhythmia or irregular heartbeats are an important feature to assess the risk on sudden cardiac death and other cardiac disorders. Automatic classification of irregular heartbeats is therefore an important part of ECG analysis. We propose a tensor-based method for single- and multi-channel irregular heartbeat classification. The method tensorizes the ECG data matrix by segmenting each signal beat-by-beat and then stacking the result into a third-order tensor with dimensions channel × time × heartbeat. We use the multilinear singular value decomposition to model the obtained tensor. Next, we formulate the classification task as the computation of a Kronecker Product Equation. We apply our method on the INCART dataset, illustrating promising results.

Premature ventricular contraction detection combining deep neural networks and rules inference

Premature ventricular contraction (PVC), which is a common form of cardiac arrhythmia caused by ectopic heartbeat, can lead to life-threatening cardiac conditions. Computer-aided PVC detection is of considerable importance in medical centers or outpatient ECG rooms. In this paper, we proposed a new approach that combined deep neural networks and rules inference for PVC detection. The detection performance and generalization were studied using publicly available databases: the MIT-BIH arrhythmia database (MIT-BIH-AR) and the Chinese Cardiovascular Disease Database (CCDD). The PVC detection accuracy on the MIT-BIH-AR database was 99.41%, with a sensitivity and specificity of 97.59% and 99.54%, respectively, which were better than the results from other existing methods. To test the generalization capability, the detection performance was also evaluated on the CCDD. The effectiveness of the proposed method was confirmed by the accuracy (98.03%), sensitivity (96.42%) and specificity (98.06%) with the dataset over 140,000 ECG recordings of the CCDD.

Use of self-gated radial cardiovascular magnetic resonance to detect and classify arrhythmias (atrial fibrillation and premature ventricular contraction)

BACKGROUND

Arrhythmia can significantly alter the image quality of cardiovascular magnetic resonance (CMR); automatic detection and sorting of the most frequent types of arrhythmias during the CMR acquisition could potentially improve image quality. New CMR techniques, such as non-Cartesian CMR, can allow self-gating: from cardiac motion-related signal changes, we can detect cardiac cycles without an electrocardiogram. We can further use this data to obtain a surrogate for RR intervals (valley intervals: VV). Our purpose was to evaluate the feasibility of an automated method for classification of non-arrhythmic (NA) (regular cycles) and arrhythmic patients (A) (irregular cycles), and for sorting of common arrhythmia patterns between atrial fibrillation (AF) and premature ventricular contraction (PVC), using the cardiac motion-related signal obtained during self-gated free-breathing radial cardiac cine CMR with compressed sensing reconstruction (XD-GRASP).

METHODS

One hundred eleven patients underwent cardiac XD-GRASP CMR between October 2015 and February 2016; 33 were included for retrospective analysis with the proposed method (6 AF, 8 PVC, 19 NA; by recent ECG). We analyzed the VV, using pooled statistics (histograms) and sequential analysis (Poincaré plots), including the median (medVV), the weighted mean (meanVV), the total number of VV values (VVval), and the total range (VVTR) and half range (VVHR) of the cumulative frequency distribution of VV, including the median to half range (medVV/VVHR) and the half range to total range (VVHR/VVTR) ratios. We designed a simple algorithm for using the VV results to differentiate A from NA, and AF from PVC.

RESULTS

Between NA and A, meanVV, VVval, VVTR, VVHR, medVV/VVHR and VVHR/VVTR ratios were significantly different (p values = 0.00014, 0.0027, 0.000028, 5×10-9, 0.002, respectively). Between AF and PVC, meanVV, VVval and medVV/VVHR ratio were significantly different (p values = 0.018, 0.007, 0.044, respectively). Using our algorithm, sensitivity, specificity, and accuracy were 93 %, 95 % and 94 % to discriminate between NA and A, and 83 %, 71 %, and 77 % to discriminate between AF and PVC, respectively; areas under the ROC curve were 0.93 and 0.89.

CONCLUSIONS

Our study shows we can reliably detect arrhythmias and differentiate AF from PVC, using self-gated cardiac cine XD-GRASP CMR.

Proposition of novel classification approach and features for improved real-time arrhythmia monitoring

Arrhythmia refers to a group of conditions in which the heartbeat is irregular, fast, or slow due to abnormal electrical activity in the heart. Some types of arrhythmia such as ventricular fibrillation may result in cardiac arrest or death. Thus, arrhythmia detection becomes an important issue, and various studies have been conducted. Additionally, an arrhythmia detection algorithm for portable devices such as mobile phones has recently been developed because of increasing interest in e-health care. This paper proposes a novel classification approach and features, which are validated for improved real-time arrhythmia monitoring. The classification approach that was employed for arrhythmia detection is based on the concept of ensemble learning and the Taguchi method and has the advantage of being accurate and computationally efficient. The electrocardiography (ECG) data for arrhythmia detection was obtained from the MIT-BIH Arrhythmia Database (n=48). A novel feature, namely the heart rate variability calculated from 5s segments of ECG, which was not considered previously, was used. The novel classification approach and feature demonstrated arrhythmia detection accuracy of 89.13%. When the same data was classified using the conventional support vector machine (SVM), the obtained accuracy was 91.69%, 88.14%, and 88.74% for Gaussian, linear, and polynomial kernels, respectively. In terms of computation time, the proposed classifier was 5821.7 times faster than conventional SVM. In conclusion, the proposed classifier and feature showed performance comparable to those of previous studies, while the computational complexity and update interval were highly reduced.

False alarm reduction in BSN-based cardiac monitoring using signal quality and activity type information

False alarms in cardiac monitoring affect the quality of medical care, impacting on both patients and healthcare providers. In continuous cardiac monitoring using wireless Body Sensor Networks (BSNs), the quality of ECG signals can be deteriorated owing to several factors, e.g., noises, low battery power, and network transmission problems, often resulting in high false alarm rates. In addition, body movements occurring from activities of daily living (ADLs) can also create false alarms. This paper presents a two-phase framework for false arrhythmia alarm reduction in continuous cardiac monitoring, using signals from an ECG sensor and a 3D accelerometer. In the first phase, classification models constructed using machine learning algorithms are used for labeling input signals. ECG signals are labeled with heartbeat types and signal quality levels, while 3D acceleration signals are labeled with ADL types. In the second phase, a rule-based expert system is used for combining classification results in order to determine whether arrhythmia alarms should be accepted or suppressed. The proposed framework was validated on datasets acquired using BSNs and the MIT-BIH arrhythmia database. For the BSN dataset, acceleration and ECG signals were collected from 10 young and 10 elderly subjects while they were performing ADLs. The framework reduced the false alarm rate from 9.58% to 1.43% in our experimental study, showing that it can potentially assist physicians in diagnosing a vast amount of data acquired from wireless sensors and enhance the performance of continuous cardiac monitoring.

Home telemonitoring of vital signs--technical challenges and future directions

The telemonitoring of vital signs from the home is an essential element of telehealth services for the management of patients with chronic conditions, such as congestive heart failure (CHF), chronic obstructive pulmonary disease (COPD), diabetes, or poorly controlled hypertension. Telehealth is now being deployed widely in both rural and urban settings, and in this paper, we discuss the contribution made by biomedical instrumentation, user interfaces, and automated risk stratification algorithms in developing a clinical diagnostic quality longitudinal health record at home. We identify technical challenges in the acquisition of high-quality biometric signals from unsupervised patients at home, identify new technical solutions and user interfaces, and propose new measurement modalities and signal processing techniques for increasing the quality and value of vital signs monitoring at home. We also discuss use of vital signs data for the automated risk stratification of patients, so that clinical resources can be targeted to those most at risk of unscheduled admission to hospital. New research is also proposed to integrate primary care, hospital, personal genomic, and telehealth electronic health records, and apply predictive analytics and data mining for enhancing clinical decision support.

An android-based heart monitoring system for the elderly and for patients with heart disease

The current trend in health monitoring systems is to move from the hospital to portable personal devices. This work shows how consumer devices like heart rate monitors can be used not only for applications in sports, but also for medical research and diagnostic purposes. The goal pursued by our group was to develop a simple, accurate, and inexpensive system that would use a few pieces of data acquired by the heart rate monitor and process them on a smartphone to (i) provide detailed test reports about the user's health state; (ii) store report records; (iii) generate emergency calls or SMSs; and (iv) connect to a remote telemedicine portal to relay the data to an online database. The system developed by our team uses sophisticated algorithms to detect stress states, detect and classify arrhythmia events, and calculate energy consumption. It is suitable for use by elderly subjects and by patients with heart disease (e.g., those recovering from myocardial infarction) or neurological conditions such as Parkinson's disease. Easy, immediate, and economical remote health control can therefore be achieved without the need for expensive hospital equipment, using only portable consumer devices.