Matrix of regularity for improving the quality of ECGs

A novel algorithm to assess the quality of 12-lead ECG recordings: validation in a real telecardiology application

Objective. Automatic detection of Electrocardiograms (ECG) quality is fundamental to minimize costs and risks related to delayed diagnosis due to low ECG quality. Most algorithms to assess ECG quality include non-intuitive parameters. Also, they were developed using data non-representative of a real-world scenario, in terms of pathological ECGs and overrepresentation of low-quality ECG. Therefore, we introduce an algorithm to assess 12-lead ECG quality, Noise Automatic Classification Algorithm (NACA) developed in Telehealth Network of Minas Gerais (TNMG).Approach. NACA estimates a signal-to-noise ratio (SNR) for each ECG lead, where 'signal' is an estimated heartbeat template, and 'noise' is the discrepancy between the template and the ECG heartbeat. Then, clinically-inspired rules based on SNR are used to classify the ECG as acceptable or unacceptable. NACA was compared with Quality Measurement Algorithm (QMA), the winner of Computing in Cardiology Challenge 2011 (ChallengeCinC) by using five metrics: sensitivity (Se), specificity (Sp), positive predictive value (PPV),F₂, and cost reduction resulting from adoption of the algorithm. Two datasets were used for validation: TestTNMG, consisting of 34 310 ECGs received by TNMG (1% unacceptable and 50% pathological); ChallengeCinC, consisting of 1000 ECGs (23% unacceptable, higher than real-world scenario).Main results. Both algorithms reached a similar performance on ChallengeCinC, although NACA performed considerably better than QMA in TestTNMG (Se = 0.89 versus 0.21; Sp = 0.99 versus 0.98; PPV = 0.59 versus 0.08;F₂= 0.76 versus 0.16 and cost reduction 2.3 ± 1.8% versus 0.3 ± 0.3%, respectively).Significance. Implementing of NACA in a telecardiology service results in evident health and financial benefits for the patients and the healthcare system.

A signal quality assessment-based ECG waveform delineation method used for wearable monitoring systems

Identifying transient and nonpersistent abnormal electrocardiogram (ECG) waveforms by continuously monitoring the high-risk populations is of great importance for the diagnosis, treatment, and prevention of cardiovascular diseases. In recent years, fabric electrodes have been widely used in wearable devices because of their non-irritating properties and better comfort than traditional AgCl electrodes. However, the motion noise caused by the relative movement between the fabric electrodes and skin affects the quality of ECGs and reduces the accuracy of diagnosis. Therefore, delineating the ECG waveforms that are recorded from wearable devices with varying levels of noise is still challenging. In this study, a signal quality assessment (SQA)-based ECG waveform delineation method that is used for wearable systems was developed. The ECG signal was first preprocessed by a bandpass filter. Five indices, including the multiscale nonlinear amplitude statistical distribution (adSQI₁, adSQI₂), the proportion of energy-related to T wave (ptSQI), and heart rates computed from R waves and T waves (rHR and tHR, respectively), were then calculated from the preprocessed ECG signal. The signals were classified as good, acceptable, and unacceptable ECGs by combining these indices through the use of a neural network. Subsequently, the R waves or/and T waves were identified for the corresponding feature interpretations based on the SQA results. ECGs that were recorded from the chest belts from 29 volunteers at different activity statuses were divided into 4-s segments. A total of 7133 manually labeled segments were used to derive (4985 segments) and validate (2148 segments) the algorithm. The adSQI₁, adSQI₂, tHR, and rHR characteristics were significantly different among the good, acceptable, and unacceptable ECGs. The ptSQI value was considerably higher in the good ECGs than in the acceptable and unacceptable ECGs. The ECG segments of different quality levels were classified with an accuracy of 96.74% by using the proposed SQA method. The R waves and T waves were identified with accuracies of 99.95% and 99.57%, respectively, for segments that were classified as acceptable and/or good. The SQA-based ECG waveform delineation method can perform reliable analysis and has the potential to be applied in wearable ECG systems for the early diagnosis and prevention of cardiovascular diseases.

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.

A model for predicting emergency physician opinion of electrocardiogram tracing data quality

BACKGROUND

Limited work has established an objective measure of ECG quality that correlates with physician opinion of the study. We seek to establish a threshold of acceptable ECG data quality for the purpose of ruling out STEMI derived from emergency physician opinion.

METHODS

A panel of three emergency physicians rated 240 12-Lead ECGs as being acceptable or unacceptable data quality. Each lead of the ECG had the following measurements recorded: baseline wander, QRS signal amplitude, and artifact amplitude. A lasso regression technique was used to create the model.

RESULTS

The area under the curve for the model using all 36 elements is 1.0, indicating a perfect fit. A simplified model using 22 terms has an area under the curve of 0.994.

CONCLUSIONS

This study demonstrated that emergency physician opinion of ECG quality for the purpose of ruling out STEMI can be predicted through a regression model.

Cardiodynamicsgram: a novel tool for monitoring cardiac function in exercise training

This study evaluated the feasibility of cardiodynamicsgram (CDG) for monitoring the cardiac functions of athletes and exercisers. CDG could provide an effective, simple, and economical tool for exercise training. Seventeen middle-distance race athletes aged 14-28 years old were recruited. CDG tests and blood test including creatine kinase (CK), CK-MB isoenzyme, and high-sensitivity troponin I (hsTnI) were performed before a high-intensity prolonged training, as well as 2 and 14 h after training, respectively. The CDG test result was unsatisfactory when the CK test result was used as standard. However, the accuracy of CDG test was about 80% when CK-MB and hsTnI were used as standards. Thus, CDG offers a noninvasive, simple, and economical approach for monitoring the cardiac function of athletes and exercisers during exercise training. Nonetheless, the applicability of CDG needs further investigation.

Quality estimation of the electrocardiogram using cross-correlation among leads

Background

Fast and accurate quality estimation of the electrocardiogram (ECG) signal is a relevant research topic that has attracted considerable interest in the scientific community, particularly due to its impact on tele-medicine monitoring systems, where the ECG is collected by untrained technicians. In recent years, a number of studies have addressed this topic, showing poor performance in discriminating between clinically acceptable and unacceptable ECG records.

Methods

This paper presents a novel, simple and accurate algorithm to estimate the quality of the 12-lead ECG by exploiting the structure of the cross-covariance matrix among different leads. Ideally, ECG signals from different leads should be highly correlated since they capture the same electrical activation process of the heart. However, in the presence of noise or artifacts the covariance among these signals will be affected. Eigenvalues of the ECG signals covariance matrix are fed into three different supervised binary classifiers.

Results and conclusion

The performance of these classifiers were evaluated using PhysioNet/CinC Challenge 2011 data. Our best quality classifier achieved an accuracy of 0.898 in the test set, while having a complexity well below the results of contestants who participated in the Challenge, thus making it suitable for implementation in current cellular devices.

A machine learning approach to multi-level ECG signal quality classification

Current electrocardiogram (ECG) signal quality assessment studies have aimed to provide a two-level classification: clean or noisy. However, clinical usage demands more specific noise level classification for varying applications. This work outlines a five-level ECG signal quality classification algorithm. A total of 13 signal quality metrics were derived from segments of ECG waveforms, which were labeled by experts. A support vector machine (SVM) was trained to perform the classification and tested on a simulated dataset and was validated using data from the MIT-BIH arrhythmia database (MITDB). The simulated training and test datasets were created by selecting clean segments of the ECG in the 2011 PhysioNet/Computing in Cardiology Challenge database, and adding three types of real ECG noise at different signal-to-noise ratio (SNR) levels from the MIT-BIH Noise Stress Test Database (NSTDB). The MITDB was re-annotated for five levels of signal quality. Different combinations of the 13 metrics were trained and tested on the simulated datasets and the best combination that produced the highest classification accuracy was selected and validated on the MITDB. Performance was assessed using classification accuracy (Ac), and a single class overlap accuracy (OAc), which assumes that an individual type classified into an adjacent class is acceptable. An Ac of 80.26% and an OAc of 98.60% on the test set were obtained by selecting 10 metrics while 57.26% (Ac) and 94.23% (OAc) were the numbers for the unseen MITDB validation data without retraining. By performing the fivefold cross validation, an Ac of 88.07±0.32% and OAc of 99.34±0.07% were gained on the validation fold of MITDB.

Real-time electrocardiogram P-QRS-T detection-delineation algorithm based on quality-supported analysis of characteristic templates

The main objective of this study is to introduce a simple, low-latency, and accurate algorithm for real-time detection of P-QRS-T waves in the electrocardiogram (ECG) signal. In the proposed method, real-time signal preprocessing, which includes high frequency noise filtering and baseline wander reduction, is performed by applying discrete wavelet transform (DWT). A method based on signal first-order derivative and adaptive threshold adjustment is employed for real-time detection of the QRS complex. Moreover, detection and delineation of P- and T-waves are achieved by correlation analysis conducted between signal and their templates. Besides, signal quality is investigated online, and if the quality of the analysis window is unacceptable, then the algorithm will guess (estimate) the locations of P- and T-waves. The operating characteristics of the proposed algorithm are evaluated by its implementation to an artificially generated ECG signal whose quality is adjustable from the best (Quality, 100%) to the worst (Quality, ≤40%) cases based on the random-walk noise theory. The algorithm was applied to the MIT-BIH arrhythmia database, QT database, and Physionet/CinC challenge 2011competition database. The obtained results, which were based on the QT database, showed sensitivity and positive predictivity of Se=99.63% and P+=99.83%, Se=99.83% and P+=99.98%, and Se=99.74% and P+=99.89% for the detection of P-, QRS-, and T-waves, respectively, and the obtained results, which were based on the MIT-BIH arrhythmia database, showed Se=99.81% and P+=99.70% for the detection of the QRS complex. Moreover, it will be shown that the results of the proposed method are reliable for a minimum signal quality value of 70%. According to numerical assessments, 8-ms after the occurrence of R-wave, its location will be identified by the computer code of the proposed algorithm. This parameter is 198-ms and 177-ms for P- and T-waves, respectively.

Electrocardiogram signal quality assessment using an artificially reconstructed target lead

In real applications, even the most accurate electrocardiogram (ECG) analysis algorithm, based on research databases, might breakdown completely if a quality measurement technique is not applied precisely before the analysis. The major concentration of this study is to describe and develop a reliable ECG signal quality assessment technique. The proposed algorithm includes three major stages: preprocessing, energy-concavity index (ECI) analysis and a correlation-based examination subroutine. The preprocessing step includes the removal of baseline wanders and high-frequency disturbances. The quality measurement based on ECI includes two separate stages according to the energy and concavity of the ECG signal. The correlation-based quality measurement step is mainly established by using the correlation between ECG leads estimated by applying a suitably trained neural network. The operating characteristics of the proposed ECI are sensitivity (Se) of 77.04% with a positive predictive value (PPV) of 90.53% for detecting high-energy noise. The correlation-based technique achieved the best scores (Se = 100%; PPV = 98.92%) for detecting high-energy noise and for recognising any other kind of disturbances (Se = 92.36%; PPV = 94.77%). Although ECI analysis acts effectively against high-energy disturbances, very poor performance is obtained in cases where the energy of the disturbances is not considerable. However, the correlation-based method is able to find all kinds of disturbances. For officially evaluating the proposed algorithm, an entry was sent to the Computing-in-Cardiology Challenge 2011 on 27 February 2012; a final score (accuracy) of 93.60% was achieved.

Cloud-ECG for real time ECG monitoring and analysis

Recent advances in mobile technology and cloud computing have inspired numerous designs of cloud-based health care services and devices. Within the cloud system, medical data can be collected and transmitted automatically to medical professionals from anywhere and feedback can be returned to patients through the network. In this article, we developed a cloud-based system for clients with mobile devices or web browsers. Specially, we aim to address the issues regarding the usefulness of the ECG data collected from patients themselves. Algorithms for ECG enhancement, ECG quality evaluation and ECG parameters extraction were implemented in the system. The system was demonstrated by a use case, in which ECG data was uploaded to the web server from a mobile phone at a certain frequency and analysis was performed in real time using the server. The system has been proven to be functional, accurate and efficient.

An expert electrocardiogram quality evaluation algorithm based on signal mobility factors

The major concentration of this study is to describe and to develop a new electrocardiogram (ECG) signal measurement binary quality assessment (accept-reject) technique. The proposed algorithm is composed of three major stages: pre-processing, signal mobility-based quality measurement and advanced post-evaluation. The pre-processing step includes baseline wander and high-frequency disturbances removal. The signal mobility-based quality measurement routine includes two separate stages based on energy and concavity of the ECG signal. The post-evaluation quality measurement step is mainly based on the six features inferenced from heuristic experiences and human thinking models. The proposed technique was applied to the test dataset provided by the PhysioNet Computing in Cardiology (CinC) challenge 2011 and accuracy 93.40% was achieved which shows the marginal improvement in this field.