Patient-specific 12-lead ECG reconstruction from sparse electrodes using independent component analysis

AI-enhanced reconstruction of the 12-lead electrocardiogram via 3-leads with accurate clinical assessment

The 12-lead electrocardiogram (ECG) is an integral component to the diagnosis of a multitude of cardiovascular conditions. It is performed using a complex set of skin surface electrodes, limiting its use outside traditional clinical settings. We developed an artificial intelligence algorithm, trained over 600,000 clinically acquired ECGs, to explore whether fewer leads as input are sufficient to reconstruct a 12-lead ECG. Two limb leads (I and II) and one precordial lead (V3) were required to generate a reconstructed 12-lead ECG highly correlated with the original ECG. An automatic algorithm for detection of ECG features consistent with acute myocardial infarction (MI) performed similarly for original and reconstructed ECGs (AUC = 0.95). When interpreted by cardiologists, reconstructed ECGs achieved an accuracy of 81.4 ± 5.0% in identifying ECG features of ST-segment elevation MI, comparable with the original 12-lead ECGs (accuracy 84.6 ± 4.6%). These results will impact development efforts to innovate ECG acquisition methods with simplified tools in non-specialized settings.

Feasibility and validity of using deep learning to reconstruct 12-lead ECG from three‑lead signals

BACKGROUND

In the field of mobile health, portable dynamic electrocardiogram (ECG) monitoring devices often have a limited number of lead electrodes due to considerations, such as portability and battery life. This situation leads to a contradiction between the demand for standard 12‑lead ECG information and the limited number of leads collected by portable devices.

METHODS

This study introduces a composite ECG vector reconstruction network architecture based on convolutional neural network (CNN) combined with recurrent neural network by using leads I, II, and V2. This network is designed to reconstruct three‑lead ECG signals into 12‑lead ECG signals. A 1D CNN abstracts and extracts features from the spatial domain of the ECG signals, and a bidirectional long short-term memory network analyzes the temporal trends in the signals. Then, the ECG signals are inputted into the model in a multilead, single-channel manner.

RESULTS

Under inter-patient conditions, the mean reconstructed Root mean squared error (RMSE) for precordial leads V1, V3, V4, V5, and V6 were 28.7, 17.3, 24.2, 36.5, and 25.5 μV, respectively. The mean overall RMSE and reconstructed Correlation coefficient (CC) were 26.44 μV and 0.9562, respectively.

CONCLUSION

This paper presents a solution and innovative approach for recovering 12‑lead ECG information when only three‑lead information is available. After supplementing with comprehensive leads, we can analyze the cardiac health status more comprehensively across 12 dimensions.

AI-Enhanced Reconstruction of the 12-Lead Electrocardiogram via 3-Leads with Accurate Clinical Assessment

The 12-lead electrocardiogram (ECG) is an integral component to the diagnosis of a multitude of cardiovascular conditions. It is performed using a complex set of skin surface electrodes, limiting its use outside traditional clinical settings. We developed an artificial intelligence algorithm, trained over 600,000 clinically acquired ECGs, to explore whether fewer leads as input are sufficient to reconstruct a full 12-lead ECG. Two limb leads (I and II) and one precordial lead (V3) were required to generate a reconstructed synthetic 12-lead ECG highly correlated with the original ECG. An automatic algorithm for detection of acute myocardial infarction (MI) performed similarly for original and reconstructed ECGs (AUC=0.94). When interpreted by cardiologists, reconstructed ECGs achieved an accuracy of 81.4±5.0% in identifying ST elevation MI, comparable with the original 12-lead ECGs (accuracy 84.6±4.6%). These results will impact development efforts to innovate ECG acquisition methods with simplified tools in non-specialized settings.

Machine Learning Electrocardiogram for Mobile Cardiac Pattern Extraction

BACKGROUND

Internet-of-things technologies are reshaping healthcare applications. We take a special interest in long-term, out-of-clinic, electrocardiogram (ECG)-based heart health management and propose a machine learning framework to extract crucial patterns from noisy mobile ECG signals.

METHODS

A three-stage hybrid machine learning framework is proposed for estimating heart-disease-related ECG QRS duration. First, raw heartbeats are recognized from the mobile ECG using a support vector machine (SVM). Then, the QRS boundaries are located using a novel pattern recognition approach, multiview dynamic time warping (MV-DTW). To enhance robustness with motion artifacts in the signal, the MV-DTW path distance is also used to quantize heartbeat-specific distortion conditions. Finally, a regression model is trained to transform the mobile ECG QRS duration into the commonly used standard chest ECG QRS durations.

RESULTS

With the proposed framework, the performance of ECG QRS duration estimation is very encouraging, and the correlation coefficient, mean error/standard deviation, mean absolute error, and root mean absolute error are 91.2%, 0.4 ± 2.6, 1.7, and 2.6 ms, respectively, compared with the traditional chest ECG-based measurements.

CONCLUSIONS

Promising experimental results are demonstrated to indicate the effectiveness of the framework. This study will greatly advance machine-learning-enabled ECG data mining towards smart medical decision support.

New ECG Compression Method for Portable ECG Monitoring System Merged with Binary Convolutional Auto-Encoder and Residual Error Compensation

In the past few years, deep learning-based electrocardiogram (ECG) compression methods have achieved high-ratio compression by reducing hidden nodes. However, this reduction can result in severe information loss, which will lead to poor quality of the reconstructed signal. To overcome this problem, a novel quality-guaranteed ECG compression method based on a binary convolutional auto-encoder (BCAE) equipped with residual error compensation (REC) was proposed. In traditional compression methods, ECG signals are compressed into floating-point numbers. BCAE directly compresses the ECG signal into binary codes rather than floating-point numbers, whereas binary codes take up fewer bits than floating-point numbers. Compared with the traditional floating-point number compression method, the hidden nodes of the BCAE network can be artificially increased without reducing the compression ratio, and as many hidden nodes as possible can ensure the quality of the reconstructed signal. Furthermore, a novel optimization method named REC was developed. It was used to compensate for the residual between the ECG signal output by BCAE and the original signal. Complemented with the residual error, the restoration of the compression signal was improved, so the reconstructed signal was closer to the original signal. Control experiments were conducted to verify the effectiveness of this novel method. Validated by the MIT-BIH database, the compression ratio was 117.33 and the root mean square difference (PRD) was 7.76%. Furthermore, a portable compression device was designed based on the proposed algorithm using Raspberry Pi. It indicated that this method has attractive prospects in telemedicine and portable ECG monitoring systems.

Efficient on-site confirmatory testing for atrial fibrillation with derived 12-lead ECG in a wireless body area network

Smartphones that can support and assist the screening of various cardiovascular diseases are gaining popularity in recent years. The timely detection, diagnosis, and treatment of atrial fibrillation (AF) are critical, especially for those who are at risk of stroke. AF detection via screening with wearable devices should always be confirmed by a standard 12-lead electrocardiogram (ECG). However, the inability to perform on-site AF confirmatory testing results in increased patient anxiety, followed by unnecessary diagnostic procedures and treatments. Also, the delay in confirmation procedure may conclude the condition as non-AF while it was indeed present at the time of screening. To overcome these challenges, we propose an efficient on-site confirmatory testing for AF with 12-lead ECG derived from the reduced lead set (RLS) in a wireless body area network (WBAN) environment. The reduction in the number of leads enhances the comfort level of patients as well as minimizes the hurdles associated with continuous telemonitoring applications such as data transmission, storage, and bandwidth of the overall system. The proposed method is characterized by segment-wise regression and a lead selection algorithm, facilitating improved P-wave reconstruction. Further, an efficient AF detection algorithm is proposed by incorporating a novel three-level P-wave evidence score with an RR irregularity evidence score. The proposed on-site AF confirmation test reduces false positives and false negatives by 88% and 53% respectively, compared to single lead screening. In addition, the proposed lead derivation method improves accuracy, F 1 -score, and Matthews correlation coefficient (MCC) for the on-site AF detection compared to existing related methods.

The Reconstruction of a 12-Lead Electrocardiogram from a Reduced Lead Set Using a Focus Time-Delay Neural Network

BACKGROUND

The 12-lead electrocardiogram (ECG) is the gold-standard ECG method used by cardiologists. However, accurate electrode placement is difficult and time consuming, and can lead to incorrect interpretation.

OBJECTIVES

The objective of this study was to accurately reconstruct a full 12-lead ECG from a reduced lead set.

METHODS

Five-electrode placement was used to generate leads I, II, III, aVL, aVR, aVF and V2. These seven leads served as inputs to the focus time-delay neural network (FTDNN) which derived the remaining five precordial leads (V1, V3-V6). An online archived medical database containing 549 cases of ECG recordings was used to train, validate and test the FTDNN.

RESULTS

After removing outliers, the reconstructed leads exhibited correlation values of between 0.8609 and 0.9678 as well as low root mean square error values of between 123 μV and 245 μV across all cases, for both healthy controls and cardiovascular disease subgroups except the bundle branch block disease subgroup. The results of the FTDNN method compared favourably to those of prior lead reconstruction methods.

CONCLUSIONS

A standard 12-lead ECG was successfully reconstructed with high quantitative correlations from a reduced lead set using only five electrodes, of which four were placed on the limbs. Less reliance on precordial leads will aid in the reduction of electrode placement errors, ultimately improving ECG lead accuracy and reduce the number of cases that are incorrectly diagnosed.

Patient-Specific Prediction of Abdominal Aortic Aneurysm Expansion Using Bayesian Calibration

Translating recent advances in abdominal aortic aneurysm (AAA) growth and remodeling (G&R) knowledge into a predictive, patient-specific clinical treatment tool requires a major paradigm shift in computational modeling. The objectives of this study are to develop a prediction framework that first calibrates the physical AAA G&R model using patient-specific serial computed tomography (CT) scan images, predicts the expansion of an AAA in the future, and quantifies the associated uncertainty in the prediction. We adopt a Bayesian calibration method to calibrate parameters in the G&R computational model and predict the magnitude of AAA expansion. The proposed Bayesian approach can take different sources of uncertainty; therefore, it is well suited to achieve our aims in predicting the AAA expansion process as well as in computing the propagated uncertainty. We demonstrate how to achieve the proposed aims by solving the formulated Bayesian calibration problems for cases with the synthetic G&R model output data and real medical patient-specific CT data. We compare and discuss the performance of predictions and computation time under different sampling cases of the model output data and patient data, both of which are simulated by the G&R computation. Furthermore, we apply our Bayesian calibration to real patient-specific serial CT data and validate our prediction. The accuracy and efficiency of the proposed method is promising, which appeals to computational and medical communities.

A novel ECG signal compression method using spindle convolutional auto-encoder

BACKGROUND AND OBJECTIVES

With rapid development of telehealth system and cloud platform, traditional 12-ECG signals with high resolution generate heavy burdens in data storage and transmission. This problem is increasingly addressed with various ECG compression methods. The important objective of compression method is to achieve a high-ratio and quality guaranteed compression. Consequently, to achieve this objective, this work presents a deep-learning-based spindle convolutional auto-encoder. The spindle structure achieves the high-ratio compression by reducing the dimension and guarantees the quality by increasing the dimension and end-to-end framework.

METHODS

The spindle convolutional auto-encoder provides a high-ratio and quality-guaranteed ECG compression. It is composed of two parts as convolutional encoder and convolutional decoder with functional layers. By convolutional operation, the local information can be extracted. The spindle structure is increasing dimension in first few layers to obtain sufficient information to guarantee compression quality. And it is reducing dimension in last few layers to merge the information into a code for high-ratio compression. Meanwhile, the end-to-end framework is to obtain the optimum encoding for compression to improve the reconstruction performance.

RESULTS

Compression performance is validated with records from MIT-BIH database. The proposed method achieves high compression ratio of 106.45 and low percentage root mean square difference of 8.00%. Compared with basic convolutional auto-encoder, the spindle structure improves the compression quality with lower losses.

CONCLUSIONS

The spindle convolutional auto-encoder performs a high-ratio and quality-guaranteed compression. It can be considered as a promising compression technique used in tele-transmission and data storage.

Robust Methods for Automated Selection of Cardiac Signals After Blind Source Separation

OBJECTIVE

Novel minimum-contact vital signs monitoring techniques like textile or capacitive electrocardiogram (ECG) provide new opportunities for health monitoring. These techniques are sensitive to artifacts and require handling of unstable signal quality. Spatio-temporal blind source separation (BSS) is capable of processing suchlike multichannel signals. However, BSS's permutation indeterminacy requires the selection of the cardiac signal (i.e., the component resembling the electric cardiac activity) after its separation from artifacts. This study evaluates different concepts for solving permutation indeterminacy.

METHODS

Novel automated component selection routines based on heartbeat detections are compared with standard concepts, as using higher order moments or frequency-domain features, for solving permutation indeterminacy in spatio-temporal BSS. BSS was applied to a textile and a capacitive ECG dataset of healthy subjects performing a motion protocol, and to the MIT-BIH Arrhythmia Database. The performance of the subsequent component selection was evaluated by means of the heartbeat detection accuracy (ACC) using an automatically selected single component.

RESULTS

The proposed heartbeat-detection-based selection routines significantly outperformed the standard selectors based on Skewness, Kurtosis, and frequency-domain features, especially for datasets containing motion artifacts. For arrhythmia data, beat analysis by sparse coding outperformed simple periodicity tests of the detected heartbeats.

CONCLUSION

Component selection routines based on heartbeat detections are capable of reliably selecting cardiac signals after spatio-temporal BSS in case of severe motion artifacts and arrhythmia.

SIGNIFICANCE

The availability of robust cardiac component selectors for solving permutation indeterminacy facilitates the usage of spatio-temporal BSS to extract cardiac signals in artifact-sensitive minimum-contact vital signs monitoring techniques.

Alexander fractional differential window filter for ECG denoising

The electrocardiogram (ECG) non-invasively monitors the electrical activities of the heart. During the process of recording and transmission, ECG signals are often corrupted by various types of noises. Minimizations of these noises facilitate accurate detection of various anomalies. In the present paper, Alexander fractional differential window (AFDW) filter is proposed for ECG signal denoising. The designed filter is based on the concept of generalized Alexander polynomial and the R-L differential equation of fractional calculus. This concept is utilized to formulate a window that acts as a forward filter. Thereafter, the backward filter is constructed by reversing the coefficients of the forward filter. The proposed AFDW filter is then obtained by averaging of the forward and backward filter coefficients. The performance of the designed AFDW filter is validated by adding the various type of noise to the original ECG signal obtained from MIT-BIH arrhythmia database. The two non-diagnostic measure, i.e., SNR, MSE, and one diagnostic measure, i.e., wavelet energy based diagnostic distortion (WEDD) have been employed for the quantitative evaluation of the designed filter. Extensive experimentations on all the 48-records of MIT-BIH arrhythmia database resulted in average SNR of 22.014 ± 3.806365, 14.703 ± 3.790275, 13.3183 ± 3.748230; average MSE of 0.001458 ± 0.00028, 0.0078 ± 0.000319, 0.01061 ± 0.000472; and average WEDD value of 0.020169 ± 0.01306, 0.1207 ± 0.061272, 0.1432 ± 0.073588, for ECG signal contaminated by the power line, random, and the white Gaussian noise respectively. A new metric named as morphological power preservation measure (MPPM) is also proposed that account for the power preservance (as indicated by PSD plots) and the QRS morphology. The proposed AFDW filter retained much of the original (clean) signal power without any significant morphological distortion as validated by MPPM measure that were 0.0126, 0.08493, and 0.10336 for the ECG signal corrupted by the different type of noises. The versatility of the proposed AFDW filter is also validated by its application on the ECG signal from MIT-BIH database corrupted by the combination of the noises as well as on the real noisy ECG signals are taken from MIT-BIH ID database. Furthermore, the comparative study has also been done between the proposed AFDW filter and existing state of the art denoising algorithms. The results clearly prove the supremacy of our proposed AFDW filter.

Energy-efficient Compressed Sensing for ambulatory ECG monitoring

Advances in Compressed Sensing (CS) are enabling promising low-energy implementation solutions for wireless Body Area Networks (BAN). While studies demonstrate the potential of CS in terms of overall energy efficiency compared to state-of-the-art lossy compression techniques, the performance of CS remains limited. The aim of this study is to improve the performance of CS-based compression for electrocardiogram (ECG) signals. This paper proposes a CS architecture that combines a novel redundancy removal scheme with quantization and Huffman entropy coding to effectively extend the Compression Ratio (CR). Reconstruction is performed using overcomplete sparse dictionaries created with Dictionary Learning (DL) techniques to exploit the highly structured nature of ECG signals. Performance of the proposed CS implementation is evaluated by analyzing energy-based distortion metrics and diagnostic metrics including QRS beat-detection accuracy across a range of CRs. The proposed CS approach offers superior performance to the most recent state-of-the-art CS implementations in terms of signal reconstruction quality across all CRs tested. Furthermore, QRS detection accuracy of the technique is compared with the well-known lossy Set Partitioning in Hierarchical Trees (SPIHT) compression technique. The proposed CS approach outperforms SPIHT in terms of achievable CR, using the area under the receiver operator characteristic (ROC) curve (AUC). For an application where a minimum AUC performance threshold of 0.9 is required, the proposed technique extends the CR from 64.6 to 90.45 compared with SPIHT, ensuring a 40% saving on wireless transmission costs. Therefore, the results highlight the potential of the proposed technique for ECG computer-aided diagnostic systems.

Reconstruction of Precordial Lead Electrocardiogram From Limb Leads Using the State-Space Model

A new electrocardiogram (ECG) reconstruction method based on a state-space model is presented. This method was applied to reconstruct precordial leads from limb leads (lead I, II, III) for its validity verification. The system matrices of the state-space model were estimated at the model estimation stage by considering the limb lead signals as the input of the system and precordial lead signals as the output. To evaluate the performance of the proposed method, all of the 549 records of the Physikalisch Technische Bundesanstalt diagnostic ECG database were used, and the correlation coefficients (CC) and root-mean-square errors between reconstructed ECG and measured ECG were calculated. For a more objective evaluation, the results were compared with those of linear regression model that has been typically used for ECG reconstruction. The mean and median values of CCs were higher than 0.988 and 0.995, respectively, for healthy subject data, and also higher than 0.981 and 0.993, respectively, for cardiac patient data and comparable to those by linear regression model. In addition, it was found that the reconstruction performance depended on the type of disease rather than lead type. Among cardiac patient data, hypertrophy, myocarditis, valvular heart disease, and stable heart angina showed higher CC (>0.990), while unstable angina and heart failure showed lower CC of 0.932 and 0.914, respectively. Moreover, when ECG contaminated with the noise was used for reconstruction, the proposed method demonstrated better performance than linear regression model in general.