Life-threatening arrhythmia verification in ICU patients using the joint cardiovascular dynamical model and a Bayesian filter

Real-Time Arrhythmia Detection Using Hybrid Convolutional Neural Networks

Background Accurate detection of arrhythmic events in the intensive care units (ICU) is of paramount significance in providing timely care. However, traditional ICU monitors generate a high rate of false alarms causing alarm fatigue. In this work, we develop an algorithm to improve life threatening arrhythmia detection in the ICUs using a deep learning approach. Methods and Results This study involves a total of 953 independent life-threatening arrhythmia alarms generated from the ICU bedside monitors of 410 patients. Specifically, we used the ECG (4 channels), arterial blood pressure, and photoplethysmograph signals to accurately detect the onset and offset of various arrhythmias, without prior knowledge of the alarm type. We used a hybrid convolutional neural network based classifier that fuses traditional handcrafted features with features automatically learned using convolutional neural networks. Further, the proposed architecture remains flexible to be adapted to various arrhythmic conditions as well as multiple physiological signals. Our hybrid- convolutional neural network approach achieved superior performance compared with methods which only used convolutional neural network. We evaluated our algorithm using 5-fold cross-validation for 5 times and obtained an accuracy of 87.5%±0.5%, and a score of 81%±0.9%. Independent evaluation of our algorithm on the publicly available PhysioNet 2015 Challenge database resulted in overall classification accuracy and score of 93.9% and 84.3%, respectively, indicating its efficacy and generalizability. Conclusions Our method accurately detects multiple arrhythmic conditions. Suitable translation of our algorithm may significantly improve the quality of care in ICUs by reducing the burden of false alarms.

Arrhythmia detection and classification using ECG and PPG techniques: a review

Electrocardiogram (ECG) and photoplethysmograph (PPG) are non-invasive techniques that provide electrical and hemodynamic information of the heart, respectively. This information is advantageous in the diagnosis of various cardiac abnormalities. Arrhythmia is the most common cardiovascular disease, manifested as single or multiple irregular heartbeats. However, due to the continuous manual observation, it becomes troublesome for experts sometimes to identify the paroxysmal nature of arrhythmia correctly. Moreover, due to advancements in technology, there is an inclination towards wearable sensors which monitor such patients continuously. Thus, there is a need for automatic detection techniques for the identification of arrhythmia. In the presented work, ECG and PPG-based state-of-the-art methods have been described, including preprocessing, feature extraction, and classification techniques for the detection of various arrhythmias. Additionally, this review exhibits various wearable sensors used in the literature and public databases available for the evaluation of results. The study also highlights the limitations of the current techniques and pragmatic solutions to improvise the ongoing effort.

ECG Signal Modeling Using Volatility Properties: Its Application in Sleep Apnea Syndrome

This study presents and evaluates the mathematical model to estimate the mean and variance of single-lead ECG signals in sleep apnea syndrome. Our objective is to use the volatility property of the ECG signal for modeling. ECG signal is a stochastic signal whose mean and variance are time-varying. So, we propose to decompose this nonstationarity into two additive components; a homoscedastic Autoregressive Integrated Moving Average (ARIMA) and a heteroscedastic time series in terms of Exponential Generalized Autoregressive Conditional Heteroskedasticity (EGARCH), where the former captures the linearity property and the latter the nonlinear characteristics of the ECG signal. First, ECG signals are segmented into one-minute segments. The heteroskedasticity property is then examined through various tests such as the ARCH/GARCH test, kurtosis, skewness, and histograms. Next, the ARIMA model is applied to signals as a linear model and EGARCH as a nonlinear model. The appropriate orders of models are estimated by using the Bayesian Information Criterion (BIC). We assess the effectiveness of our model in terms of mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). The data in this article is obtained from the Physionet Apnea-ECG database. Results show that the ARIMA-EGARCH model performs better than other models for modeling both apneic and normal ECG signals in sleep apnea syndrome.

Length of stay prediction for ICU patients using individualized single classification algorithm

BACKGROUND AND OBJECTIVE

In intensive care units (ICUs), length of stay (LOS) prediction is critical to help doctors and nurses select appropriate treatment options and predict patients' condition. Considering that most hospitals use universal models to predict patients' condition, which cannot meet the individual needs of special ICU patients. Our goal is to create a personalized model for patients to determine the number of hospital stays.

METHODS

In this study, a new combination of just-in-time learning (JITL) and one-class extreme learning machine (one-class ELM) is proposed to predict the number of days a patient stays in hospital. This combination is shortened as one-class JITL-ELM, where JITL is used to search for personalized cases for a new patient and one-class ELM is used to determine whether the patient can be discharged within 10 days.

RESULTS

The experimental results show that the one-class JITL-ELM model has an area under the curve (AUC) index of 0.8510, lift value of 2.1390, precision of 1, and G-mean is 0.7842. Its accuracy, specificity, and sensitivity were found as 0.82, 1, and 0.6150, respectively. Moreover, a novel simple mortality risk level estimation system that can determine the mortality rate of a patient by combining LOS and age is proposed. It has an accuracy rate of 66% and the miss rate of only 6.25%.

CONCLUSIONS

Overall, the one-class JITL-ELM can accurately predict hospitalization days and mortality using early physiological parameters. Moreover, a simple mortality risk level estimation system based on a combination of LOS and age is proposed; the system is simple, highly interpretable, and has strong application value.

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.

Reducing false arrhythmia alarm rates using robust heart rate estimation and cost-sensitive support vector machines

To lessen the rate of false critical arrhythmia alarms, we used robust heart rate estimation and cost-sensitive support vector machines. The PhysioNet MIMIC II database and the 2015 PhysioNet/CinC Challenge public database were used as the training dataset; the 2015 Challenge hidden dataset was for testing. Each record had an alarm labeled with asystole, extreme bradycardia, extreme tachycardia, ventricular tachycardia or ventricular flutter/fibrillation. Before alarm onsets, 300 s multimodal data was provided, including electrocardiogram, arterial blood pressure and/or photoplethysmogram. A signal quality modified Kalman filter achieved robust heart rate estimation. Based on this, we extracted heart rate variability features and statistical ECG features. Next, we applied a genetic algorithm (GA) to select the optimal feature combination. Finally, considering the high cost of classifying a true arrhythmia as false, we selected cost-sensitive support vector machines (CSSVMs) to classify alarms. Evaluation on the test dataset showed the overall true positive rate was 95%, and the true negative rate was 85%.

Reduction of false arrhythmia alarms using signal selection and machine learning

In this paper, we propose an algorithm that classifies whether a generated cardiac arrhythmia alarm is true or false. The large number of false alarms in intensive care is a severe issue. The noise peaks caused by alarms can be high and in a noisy environment nurses can experience stress and fatigue. In addition, patient safety is compromised because reaction time of the caregivers to true alarms is reduced. The data for the algorithm development consisted of records of electrocardiogram (ECG), arterial blood pressure, and photoplethysmogram signals in which an alarm for either asystole, extreme bradycardia, extreme tachycardia, ventricular fibrillation or flutter, or ventricular tachycardia occurs. First, heart beats are extracted from every signal. Next, the algorithm selects the most reliable signal pair from the available signals by comparing how well the detected beats match between different signals based on [Formula: see text]-score and selecting the best match. From the selected signal pair, arrhythmia specific features, such as heart rate features and signal purity index are computed for the alarm classification. The classification is performed with five separate Random Forest models. In addition, information on the local noise level of the selected ECG lead is added to the classification. The algorithm was trained and evaluated with the PhysioNet/Computing in Cardiology Challenge 2015 data set. In the test set the overall true positive rates were 93 and 95% and true negative rates 80 and 83%, respectively for events with no information and events with information after the alarm. The overall challenge scores were 77.39 and 81.58.

Sensor fusion methods for reducing false alarms in heart rate monitoring

Automatic patient monitoring is an essential resource in hospitals for good health care management. While alarms caused by abnormal physiological conditions are important for the delivery of fast treatment, they can be also a source of unnecessary noise because of false alarms caused by electromagnetic interference or motion artifacts. One significant source of false alarms is related to heart rate, which is triggered when the heart rhythm of the patient is too fast or too slow. In this work, the fusion of different physiological sensors is explored in order to create a robust heart rate estimation. A set of algorithms using heart rate variability index, Bayesian inference, neural networks, fuzzy logic and majority voting is proposed to fuse the information from the electrocardiogram, arterial blood pressure and photoplethysmogram. Three kinds of information are extracted from each source, namely, heart rate variability, the heart rate difference between sensors and the spectral analysis of low and high noise of each sensor. This information is used as input to the algorithms. Twenty recordings selected from the MIMIC database were used to validate the system. The results showed that neural networks fusion had the best false alarm reduction of 92.5 %, while the Bayesian technique had a reduction of 84.3 %, fuzzy logic 80.6 %, majority voter 72.5 % and the heart rate variability index 67.5 %. Therefore, the proposed algorithms showed good performance and could be useful in bedside monitors.

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.

False ventricular tachycardia alarm suppression in the ICU based on the discrete wavelet transform in the ECG signal

Over the past few years, reducing the number of false positive cardiac monitor alarms (FA) in the intensive care unit (ICU) has become an issue of the utmost importance. In our work, we developed a robust methodology that, without the need for additional non-ECG waveforms, suppresses false positive ventricular tachycardia (VT) alarms without resulting in false negative alarms. Our approach is based on features extracted from the ECG signal 20 seconds prior to a triggered alarm. We applied a multi resolution wavelet transform to the ECG data 20seconds prior to the alarm trigger, extracted features from appropriately chosen scales and combined them across all available leads. These representations are presented to a L1-regularized logistic regression classifier. Results are shown in two datasets of physiological waveforms with manually assessed cardiac monitor alarms: the MIMIC II dataset, where we achieved a false alarm (FA) suppression of 21% with zero true alarm (TA) suppression; and a dataset compiled by UCSF and General Electric, where a 36% FA suppression was achieved with a zero TA suppression. The methodology described in this work could be implemented to reduce the number of false monitor alarms in other arrhythmias.

Utility of a nonlinear joint dynamical framework to model a pair of coupled cardiovascular signals

We have recently proposed a correlated model to provide a Gaussian mixture representation of the cardiovascular signals, with promising results in identifying rhythm disturbances. The approach provides a transformation of the data into a set of integrable Gaussians distributed over time. Looking into the model from a new joint modeling perspective, it is capable of assembling a filtered estimation, and can be used to derive temporal information of the waveforms. In this paper, we present a step-by-step derivation of the joint model putting correlation assumptions together to conclude a minimal joint description for a pair of ECG-ABP signals. We then probe novel applications of this model, including Kalman filter based denoising and fiducial point detection. In particular, we use the joint model for denoising and employ the denoised signals for pulse transit time (PTT) estimation. We analyzed more than 70 h of data from 76 patients from the MIMIC database to illustrate the accuracy of the algorithm. We have found that this method can be effectively used for robust joint ECG-ABP noise suppression, with mean signal-to-noise ratio (SNR) improvement up to 23.2 (12.0) dB and weighted diagnostic distortion measures as low as 2.1 (3.3)% for artificial (real) noises, respectively. In addition, we have estimated the error distributions for QT interval, systolic and diastolic blood pressure before and after filtering to demonstrate the maximal preservation of morphological features (ΔQT: mean ± std = 2.2 ± 6.1 ms; ΔSBP: mean ± std = 2.3 ± 1.9 mmHg; ΔDBP: mean ± std = 1.9 ± 1.4 mmHg). Finally, we have been able to present a systematic approach for robust PTT estimation (r = 0.98, p <; 0.001, mean ± std of error = -0.26 ± 2.93 ms). These findings may have important implications for reliable monitoring and estimation of clinically important features in clinical settings. In conclusion, the proposed framework opens the door to the possibility of deploying a hybrid system that integrates these algorithmic approaches for index estimation and filtering scenarios with high output SNRs and low distortion.

Electrocardiogram pattern recognition and analysis based on artificial neural networks and support vector machines: a review

Computer systems for Electrocardiogram (ECG) analysis support the clinician in tedious tasks (e.g., Holter ECG monitored in Intensive Care Units) or in prompt detection of dangerous events (e.g., ventricular fibrillation). Together with clinical applications (arrhythmia detection and heart rate variability analysis), ECG is currently being investigated in biometrics (human identification), an emerging area receiving increasing attention. Methodologies for clinical applications can have both differences and similarities with respect to biometrics. This paper reviews methods of ECG processing from a pattern recognition perspective. In particular, we focus on features commonly used for heartbeat classification. Considering the vast literature in the field and the limited space of this review, we dedicated a detailed discussion only to a few classifiers (Artificial Neural Networks and Support Vector Machines) because of their popularity; however, other techniques such as Hidden Markov Models and Kalman Filtering will be also mentioned.

Semi-supervised detection of intracranial pressure alarms using waveform dynamics

Patient monitoring systems in intensive care units (ICU) are usually set to trigger alarms when abnormal values are detected. Alarms are generated by threshold-crossing rules that lead to high false alarm rates. This is a recognized issue that causes alarm fatigue, waste of human resources, and increased patient risks. Recently developed smart alarm models require alarms to be validated by experts during the training phase. The manual annotation process involved is time-consuming and virtually impossible to achieve for the thousands of alarms recorded in the ICU every week. To tackle this problem, we investigate in this study if the use of semi-supervised learning methods, that can naturally integrate unlabeled data samples in the model, can be used to improve the accuracy of the alarm detection. As a proof of concept, the detection system is evaluated on intracranial pressure (ICP) signal alarms. Specific morphological and trending features are extracted from the ICP signal waveform to capture the dynamic of the signal prior to alarms. This study is based on a comprehensive dataset of 4791 manually labeled alarms recorded from 108 neurosurgical patients. A comparative analysis is provided between kernel spectral regression (SR-KDA) and support vector machine (SVM) both modified for the semi-supervised setting. Results obtained during the experimental evaluations indicate that the two models can significantly reduce false alarms using unlabeled samples; especially in the presence of a restrained number of labeled examples. At a true alarm recognition rate of 99%, the false alarm reduction rates improved from 9% (supervised) to 27% (semi-supervised) for SR-KDA, and from 3% (supervised) to 16% (semi-supervised) for SVM.

Signal quality and data fusion for false alarm reduction in the intensive care unit

Due to a lack of integration between different sensors, false alarms (FA) in the intensive care unit (ICU) are frequent and can lead to reduced standard of care. We present a novel framework for FA reduction using a machine learning approach to combine up to 114 signal quality and physiological features extracted from the electrocardiogram, photoplethysmograph, and optionally the arterial blood pressure waveform. A machine learning algorithm was trained and evaluated on a database of 4107 expert-labeled life-threatening arrhythmias, from 182 separate ICU visits. On the independent test data, FA suppression results with no true alarm (TA) suppression were 86.4% for asystole, 100% for extreme bradycardia and 27.8% for extreme tachycardia. For the ventricular tachycardia alarms, the best FA suppression performance was 30.5% with a TA suppression rate below 1%. To reduce the TA suppression rate to zero, a reduction in FA suppression performance to 19.7% was required.

Monitoring in cardiovascular disease patients by nonlinear biomedical signal processing

Due to recent advances in technology extensive cardiovascular monitoring is widely introduced today. An essential component of cardiovascular monitoring is the analysis of several biosignals as electrocardiogram, blood pressure and other vital signs. This manuscript provides an overview about several application fields of cardiovascular monitoring with the main focus on nonlinear dynamics analysis.