Refine
Document Type
Language
- English (10)
Publication reviewed
- begutachtet (10)
Keywords
- ECG (5)
- Elektrokardiogramm (5)
- Biomedizinische Signalverarbeitung (4)
- Biomedical Signal Processing (2)
- Computergestützte Elektrokardiographie (2)
- EKG (2)
- Artificial intelligence in medicine (1)
- Biomedizin (1)
- Digitale Signalverarbeitung (1)
- Elektrokardiogramm, Biomedizinische Signalverarbeitung, ECG, EKG (1)
Institute
Linear ECG-lead transformations (LELTs) are used to estimate unrecorded target leads by applying a number of recorded basis leads to a LELT matrix. Such LELT matrices are commonly developed using training datasets that are composed of ECGs that belong to different diagnostic classes (DCs). The aim of our research was to assess the influence of the training set composition on the estimation performance of LELTs that estimate target leads V1, V3, V4 and V6 from basis leads I, II, V2 and V5 of the 12-lead ECG. Our assessment was performed using ECGs from the three DCs left ventricular hypertrophy, right bundle branch block and normal (ECGs without abnormalities). Training sets with different DC compositions were used for the development of LELT matrices. These matrices were used to estimate the target leads of different test sets. The estimation performance of the developed matrices was quantified using root mean square error values calculated between derived and recorded target leads. Our findings indicate that unbalanced training sets can lead to LELTs that show large estimation performance variability across different DCs. Balanced training sets were found to produce LELTs that performed well across multiple DCs. We recommend balanced training sets for the development of LELTs.
Background: Electrocardiogram (ECG) signals are often contaminated by noise. Manual review of large ECG databases to identify noisy signals is time-consuming. Traditional signal quality assessment algorithms often do not generalize well or are computationally expensive. This study developed a Temporal Convolutional Neural Network (TCNN) to estimate the signal-to-noise ratio (SNR) of ECG signals. Method: We trained a TCNN on a proprietary database of 134,019 12-lead ECGs without any machine or human-added noise labels. Assuming that this data had high SNR, we randomly selected a single lead from each ECG and added random Gaussian noise. We then scaled the signals and added noise to give a negatively skewed normal distribution of true SNR values. We trained a TCNN to regress low- and high-frequency pseudo-SNR values from the raw noisy input signals. Results: On the testing dataset, the TCNN achieved a mean error of 0.31±1.80 dB and a Pearson correlation coefficient of 0.96 for low-frequency pseudo-SNR. Similarly, for high-frequency pseudo-SNR, the mean error was 0.29±1.63 dB and the Pearson correlation coefficient was 0.97. Conclusion: A Temporal Convolutional Neural Network can accurately estimate the SNR of unseen ECGs.
This study assessed the performance of a deep neural network (PulseAI, Belfast, United Kingdom) used in conjunction with a dry-electrode ECG sensor device (RhythmPad, D&FT, United Kingdom) to detect AF automatically. Simultaneous pairs of 12-lead ECGs and single-lead dry-electrode ECGs were collected from 622 patients. The 12-lead ECGs were manually overread and used as reference diagnoses. Twenty-two patients were confirmed with AF and had an interpretable 12-lead and single-lead dry-electrode ECG recording. The deep neural network analysed the dry-electrode ECGs, and performance was compared to the 12-lead interpretation. Overall, the deep neural network algorithm yielded a sensitivity of 96% (95% CI, 87%-100%), specificity of 99% (95% CI, 98%-100%) and positive predictive value of 81% (95% CI, 66%-96%) for detection of AF episodes. When coupled with dry-electrode ECG sensors, the PulseAI neural network allows for large-scale and low-cost screening for AF. Widespread implementation of this technology may allow for earlier detection, treatment, and management of patients with AF.
Linear ECG-lead transformations (LELTs) are used to estimate unrecorded leads by applying a number of recorded leads to a LELT matrix. Such LELT matrices are commonly developed using a training dataset and linear regression analysis. An important performance metric of LELTs is the subject-to-subject variability (SSV) of their estimation performance. In this research, we assess the relationship between an increasing training set size (from n=10 to n=370 subjects) and the SSV of LELTs. A total of 200 LELT matrices were developed for each training sets size. The developed LELT matrices and 12-lead ECG data of a testing dataset (n=123 subjects) were used for the estimation of Frank VCGs. Root-mean-squared-error (RMSE) values between recorded and estimated Frank VCG leads were used for the quantification of the estimation performance. The SSV associated with each LELT matrix was quantified as the standard deviation of the corresponding RMSE values. This was followed by an analysis of the relationship between the training set size and the associated SSV values. Increasing the training set size from 10 to 180, to 160 and to 200 subjects, for Frank VCG leads X,Y and Z respectively, was associated with a reduction of the observed SSV. Further increases in training set size were found to only have a marginal effect on the observed SSV.
Deep Convolutional Neural Networks (DCNNs) have been shown to provide improved performance over traditional heuristic algorithms for the detection of arrhythmias from ambulatory ECG recordings. However, these DCNNs have primarily been trained and tested on device-specific databases with standardized electrode positions and uniform sampling frequencies. This work explores the possibility of training a DCNN for Atrial Fibrillation (AF) detection on a database of single‑lead ECG rhythm strips extracted from resting 12‑lead ECGs. We then test the performance of the DCNN on recordings from ambulatory ECG devices with different recording leads and sampling frequencies.
We developed an extensive proprietary resting 12‑lead ECG dataset of 549,211 patients. This dataset was randomly split into a training set of 494,289 patients and a testing set of the remaining 54,922 patients. We trained a 34-layer convolutional DCNN to detect AF and other arrhythmias on this dataset. The DCNN was then validated on two Physionet databases commonly used to benchmark automated ECG algorithms (1) MIT-BIH Arrhythmia Database and (2) MIT-BIH Atrial Fibrillation Database. Validation was performed following the EC57 guidelines, with performance assessed by gross episode and duration sensitivity and positive predictive value (PPV). Finally, validation was also performed on a selection of rhythm strips from an ambulatory ECG patch that a committee of board-certified cardiologists annotated.
On MIT-BIH, The DCNN achieved a sensitivity of 100% and 84% PPV in detecting episodes of AF. and 100% sensitivity and 94% PPV in quantifying AF episode duration. On AFDB, The DCNN achieved a sensitivity of 94% and PPV of 98% in detecting episodes of AF, and 98% sensitivity and 100% PPV in quantifying AF episode duration. On the patch database, the DCNN demonstrated performance that was closely comparable to that of a cardiologist.
The results indicate that DCNN models can learn features that generalize between resting 12‑lead and ambulatory ECG recordings, allowing DCNNs to be device agnostic for detecting arrhythmias from single‑lead ECG recordings and enabling a range of clinical applications.
Linear electrocardiographic lead transformations (LELTs) are used to estimate unrecorded ECG leads by applying a number of recorded leads to a LELT matrix. Such matrices are commonly developed using a training dataset. The size of the training dataset has an influence on the estimation performance of a LELT matrix. However, an estimate of the minimal size required for the development of LELTs has previously not been reported.
The aim of this research was to determine such an estimate. We generated LELT matrices from differently sized (from n = 10 to n = 540 subjects in steps of 10 subjects) training datasets. The LELT matrices and the 12-lead ECG data of a testing dataset (n = 186 subjects) were used for the estimation of Frank VCGs. Root-mean-squared-error values between recorded and estimated Frank leads of the testing dataset were used for the quantification of the estimation performance associated with a given size of the training dataset.
The performance of the LELTs was, after an initial phase of improvement, found to only marginally improve with additional increases in the size of the training dataset. Our findings suggest that the training dataset should have
a minimal size of 170 subjects when developing LELTs that utilise the 12-lead ECG for the estimation of unrecorded
ECG leads.
Automated interpretation of the 12-lead ECG has remained an underpinning interest in decades of research that has seen a diversity of computing applications in cardiology.
The application of computers in cardiology began in the 1960s with early research focusing on the conversion of analogue ECG signals (voltages) to digital samples. Alongside this, software techniques that automated the extraction of wave measurements and provided basic diagnostic statements, began to emerge. In the years since then there have been many significant milestones which include the widespread commercialisation of 12-lead ECG interpretation software, associated clinical utility and the development of the related regulatory frameworks to promote standardised development.
In the past few years, the research community has seen a significant rejuvenation in the development of ECG interpretation programs. This is evident in the research literature where a large number of studies have emerged tackling a variety of automated ECG interpretation problems. This is largely due to two factors. Specifically, the technical advances, both software and hardware, that have facilitated the broad adoption of modern artificial intelligence (AI) techniques, and, the increasing availability of large datasets that support modern AI approaches.
In this article we provide a very high-level overview of the operation of and approach to the development of early 12-lead ECG interpretation programs and we contrast this to the approaches that are now seen in emerging AI approaches. Our overview is mainly focused on highlighting differences in how input data are handled prior to generation of the diagnostic statement.
Linear ECG-lead transformations estimate or derive unrecorded target leads by applying a number of recorded basis leads to a so-called linear ECG-lead transformation matrix. The inverse transform of such a linear ECG-lead transformation performs a transformation in the opposite direction (from the target leads to the basis leads). The pseudo-inverse of a given transformation matrix can be used to perform such an inverse transformation. Linear regression based inverse transformation matrices are, provided that sufficient
training data for their development is available, an alternative to pseudo-inverse matrices. The aim of this research was to compare the estimation performance of pseudo-inverse and linear regression based inverse transformations. This comparison was performed for two example inverse transformations. The performance of the different transformations was assessed using root-meansquared-error (RMSE) values between the QRS-T complexes of recorded and derived leads. Typical mean RMSE values associated with the regression based
approach were found to be approximately two thirds to half of the mean RMSE values achieved by the approach based upon the pseudo-inverse. Provided that sufficient data are available, linear regression should be used for the development of inverse ECG-lead transformation matrices.
The magnitude of the spatial ventricular gradient (MSVG) is an attractive parameter in electrocardiogram (ECG)monitoring applications. The MSVG is most commonlyobtained from150 Hz low-pass filtered resting ECGs. However, monitoring applications typically utilize 40 Hz low-pass filtered ECG data. The extend to which the value of the MSVG is affected by the utilization of 40 Hz low-pass monitoring ECG filters over the commonly used 150 Hz low-pass resting ECG filters has not previously been reported. The aim of this research was to quantify the differences between MSVG values computed using 40 Hz low-pass filtered ECG data (MSVG40) and 150 Hz low-pass filtered ECG data (MSVG150). The differences between the MSVG40 and the MSVG150 were quantified as systematic error (mean difference) and random error (span of Bland-Altman 95% limits of agreement) using a study population of 726 subjects. The systematic error was found to be 0.013 mV ms [95% confidence interval: 0.008 mV ms to 0.018 mV ms]. The random error was quantified as 0.282 mV ms [95% confidence interval: 0.266 mV ms to 0.298 mV ms]. Our findings suggest that it is possible to record accurate MSVG values using 40 Hz low-pass filtered ECG data.
Background: We have previously reported on the potential of patch-based ECG leads to observe changes typical during ischaemia. In this study we aim to assess the utility of patch-based leads in the detection of these changes.
Method: Body surface potential maps (BSPM) from subjects (n=45) undergoing elective percutaneous coronary angioplasty (PTCA) were used. The short spaced lead (SSL), that was previously identified as having the greatest ST-segment change between baseline and peak balloon inflation (PBI), was selected as the basis for a patch based lead system. A feature set of J-point amplitudes for all bipolar leads available within the same 100 mm region were included (n=6). Current 12-lead ECG criteria were applied to 12-lead ECGs for the same subjects to benchmark performance.
Results: The previously identified single SSL achieved sensitivity and specificity of 87% and 71% respectively using a Naive Bayes classifier. Adding other combinations of leads to this did not improve performance significantly. The 12-lead ECG performance was 62/93% (sensitivity/specificity).
Conclusion: This study suggests that short spaced leads can be sensitive to ischaemic ECG changes. However, due to the short distance between leads, they lack the specificity of the 12-lead ECG.