Refine
Document Type
Language
- English (24)
Publication reviewed
- begutachtet (24)
Keywords
- Biomedizinische Signalverarbeitung (10)
- ECG (9)
- EKG (7)
- Biomedical Signal Processing (6)
- Elektrokardiogramm (4)
- Computergestützte Elektrokardiographie (3)
- Biomedizin (2)
- Biomedizinische Signalverarbeitung; EKG; ECG (2)
- Elektrokardiogramm, Biomedizinische Signalverarbeitung, ECG, EKG (2)
- Maschinelles Lernen (2)
Institute
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.
There are limited datasets available to facilitate the evaluation of patch-based lead systems, so the leads must be derived from existing data, mainly the 12-lead ECG. We have previously introduced a short spaced lead (SSL) system consisting of two leads with the largest ST segment changes during ischaemic-type episodes. In this study, we aim to evaluate the derivation of this patch-based lead system from the 12-lead ECG.
Method: Thoracic body surface potential maps (BSPM) were recorded from n=734 patients. Using Laplacian interpolation, each recording was expanded to the 352-node Dalhousie torso. The eight independent channels of the 12-lead ECG were extracted (I, II, V1-V6) with the two leads of the SSL patch Coefficients were derived using linear regression from the 12-lead ECG to the SSL patch.
Results: The median Pearson correlation coefficients (CC) and root mean square error (RMSE) for each lead were calculated as follows (CC/RMSE): 0.986/74.3 µV (ST monitoring lead); 0.976/65.3 µV (spatially orthogonal lead).
Conclusion: We have developed coefficients that allow the derivation of a patch-based lead system from the 12-lead ECG. Given the high correlation, it is possible to generate short spaced lead systems from existing diagnostic lead systems, however, amplitude errors are introduced in the process.
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.
Introduction: Interpretation of the 12‑lead Electrocardiogram (ECG) is normally assisted with an automated diagnosis (AD), which can facilitate an ‘automation bias’ where interpreters can be anchored. In this paper, we studied, 1) the effect of an incorrect AD on interpretation accuracy and interpreter confidence (a proxy foruncertainty), and 2) whether confidence and other interpreter features can predict interpretation accuracy using machine learning. Methods: This study analysed 9000 ECG interpretations from cardiology and non-cardiology fellows (CFs and non-CFs). One third of the ECGs involved no ADs, one third with ADs (half as incorrect) and one third had multiple ADs. Interpretations were scored and interpreter confidence was recorded for each interpretation and subsequently standardised using sigma scaling. Spearman coefficients were used for correlation analysis and C5.0 decision trees were used for predicting interpretation accuracy using basic interpreter features such as confidence, age, experience and designation. Results: Interpretation accuracies achieved by CFs and non-CFs dropped by 43.20% and 58.95% respectively when an incorrect AD was presented (p b 0.001). Overall correlation between scaled confidence and interpretation accuracy was higher amongst CFs. However, correlation between confidence and interpretation accuracy decreased for both groups when an incorrect AD was presented. We found that an incorrect AD disturbs the reliability of interpreter confidence in predicting accuracy. An incorrect AD has a greater effect on the confidence of nonCFs (although this is not statistically significant it is close to the threshold, p = 0.065). The best C5.0 decision tree achieved an accuracy rate of 64.67% (p b 0.001), however this is only 6.56% greater than the noinformation-rate. Conclusion: Incorrect ADs reduce the interpreter's diagnostic accuracy indicating an automation bias. Non-CFs tend to agree more with the ADs in comparison to CFs, hence less expert physicians are more effected by automation bias. Incorrect ADs reduce the interpreter's confidence and also reduces the predictive power of confidence for predicting accuracy (even more so for non-CFs). Whilst a statistically significant model was developed, it is difficult to predict interpretation accuracy using machine learning on basic features such as interpreter confidence, age, reader experience and designation.
Body surface potential maps (BSPMs) are typically recorded from a large number of ECG leads that cover the entire thorax. This improves diagnostic accuracy and is required in Electrocardiographic imaging (ECGi). BSPMs recorded in the clinical setting may have some leads that are noisy due to poor skin electrode contact. We analyzed 117 lead BSPMs recorded from 360 subjects. We successively simulated the removal of ECG leads at various locations and tested the ability of our algorithm to accurately reconstruct the missing information. When seven electrodes were removed, the algorithm could reconstruct BSPM patterns from QRS segments with median RMSE of 6.24µV and 12.15µV and CC of 0.999 and 0.997 when Laplacian method and PCA based method were used respectively. This work shows that noisy BSPM leads, which often manifest in the clinical setting, can be more accurately reconstructed using our Laplacian based interpolation
algorithm, when low number of missed electrodes in regions where electrodes are organised in a well distributed and tight mesh.
Heart rate variability analysis (HRVA) gives valuable insight to the cardiovascular system. Electrocardiogram (ECG) based HRVA has been assessment gold standard but eavesdropping of wearable technology requires the comparison of its surrogacy to an accepted standard. In this study, optical and mechanical measures at distal artery waveform are compared to the electrical signal of the heart. The sensor data of the six healthy volunteers are collated and compared at fiducial points in various time, frequency and non-linear domains for HRVA. We have found that during early systole fiducial location on waveforms can be surrogate to ECG standard and mechanical sensor 2nd derivative proved to be the best among them. Also, the comparative technology shows enormous potential for cardiovascular diagnostic.
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.
Background: The 12-lead ECG is spatially limited in diagnosing cardiac abnormalities. Additional leads (right sided and posterior leads) are inconvenient in a clinical setting, however, they can be derived. In this paper we report on the development of coefficients to allow derivation of right sided and posterior leads.
Method: Analysis was performed using body surface potential maps (BSPM) recorded from 910 patients in two centres. Recordings were made up of healthy controls (n=314), peak balloon inflation during elective percutaneous coronary angioplasty (n=88), myocardial infarction (n=271) and left-ventricular hypertrophy (n=237). All recordings were expanded to the 352-node Dalhousie torso. Coefficients to allow derivation of right sided and posterior leads were generated by linear regression. Further coefficients from a previously reported study were used for performance comparisons.
Results: Correlation coefficients between recorded and derived leads were significantly improved using the new coefficients (p<0.05) in leads V7-V12.
Conclusion: We have developed coefficients that allow the derivation of 10 additional leads from the 12-lead ECG.