Data driven feature selection and machine learning to detect misplaced V1 and V2 chest electrodes when recording the 12‑lead electrocardiogram

Rjoob, Khaled; Bond, Raymond; Finlay, Dewar; McGilligan, Victoria; Leslie, Stephen J; Iftikhar, Aleeha; Guldenring, Daniel; Rababah, Ali; Knoery, Charles; McShane, Anne; Peace, Aaron

doi:10.1016/j.jelectrocard.2019.08.017

Cited by 14 publications

(12 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 2 below shows mean sensitivity and mean specificity of each group. [25] 87.0% ±0.00 97.8% ±0.00 92.0% Han C. et al, [30] 56.1% ±27.7 99.9% ±0.04 71.8% Average =85.6% SD=±13.5 Average =98.5% SD=±2.5 B Rjoob K. et al, [23] 79.6% ±8.6 84.6% ±5.9 81.6% Rjoob K. et al, [24] 81.5% ±11.5 81.0% ±11.0 81.3% Average =80.5% SD=±0.95 Average =82.8% SD=±1.8 C Jekova I. et al, [26] 97.4% ±1.88 99.2% ±0.35 98.3% Heden B. et al, [18] 95.0% ±0.00 99.95% ±0.00 97.4% Jekova I. et al, [25] 96.8% ±0.00 97.8% ±0.00 97.3% Han C. et al, [30] 93.4% ±1.05 99.9% ±0.05 96.5% Gregg R. et al, [29] 88.1% ±3.90 99.7% ±0.20 93.5% Kors J. et al, [20] 83.7% ±21.31 98.5% ±2.07 90.4% Jan A. et al, [21] 81.5% ±31.8 99.8% ±0.18 89.7% Han C. et al, [22] 82.5% ±9.25 97.7% ±0.20 89.3% Heden B. et al, [17] 69.0% ±11.45 99.9% ±0.01 81.6% Heden B. et al, [19] 57.6% ±0.00 99.97% ±0.00 73.1% Bie J. et al, [28] 54.6% ±28.09 99.6% ±0.15 70.5% Average =81.7% SD=±14.5 Average =99.2% SD=±0.82…”

Section: Descriptive Summary Of Resultsmentioning

confidence: 99%

“…The fourteen studies used and evaluated ML based algorithms to detect electrode misplacement/interchange, and four ML models included artificial neural networks (ANNs) (n = 3) [17][18][19], decision trees (DT) (n=5) [20][21][22][23][24], correlation (n=3) [25][26][27], amplitude threshold (n=1) [28], haisty (n=1) [29]…”

Section: Study Characteristicsmentioning

confidence: 99%

“…and support vector machines (SVM) (n = 3)[23][24][30]. The plurality of the studies (n=7) focused on both limb and chest lead interchanges while other studies (n=4) focused on limb lead interchanges only, two studies considered vertical misplacement of chest electrodes and one study considered chest lead interchange only.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Machine learning techniques for detecting electrode misplacement and interchanges when recording ECGs: A systematic review and meta-analysis

Rjoob

Bond

Finlay

et al. 2020

Journal of Electrocardiology

Self Cite

View full text Add to dashboard Cite

Introduction: Electrode misplacement and interchange errors are known problems when recording the 12-lead electrocardiogram (ECG). Automatic detection of these errors could play an important role for improving clinical decision making and outcomes in cardiac care. The objectives of this systematic review and meta-analysis is to 1) study the impact of electrode misplacement on ECG signals and ECG interpretation, 2) to determine the most challenging electrode misplacements to detect using machine learning (ML), 3) to analyse the ML performance of algorithms that detect electrode misplacement or interchange according to sensitivity and specificity and 4) to identify the most commonly used ML technique for detecting electrode misplacement/interchange. This review analysed the current literature regarding electrode misplacement/interchange recognition accuracy using machine learning techniques. Method: A search of three online databases including IEEE, PubMed and ScienceDirect identified 228 articles, while 3 articles were included from additional sources from co-authors. According to the eligibility criteria, 14 articles were selected. The selected articles were considered for qualitative analysis and meta-analysis. Results: The articles showed the effect of lead interchange on ECG morphology and as a consequence on patient diagnoses. Statistical analysis of the included articles found that machine learning performance is high in detecting electrode misplacement/interchange except left arm/left leg interchange. Conclusion: This review emphasises the importance of detecting electrode misplacement detection in ECG diagnosis and the effects on decision making. Machine learning shows promise in detecting lead misplacement/interchange and highlights an opportunity for developing and operationalising deep learning algorithms such as convolutional neural network (CNN) to detect electrode misplacement/interchange.

show abstract

Section: Descriptive Summary Of Resultsmentioning

confidence: 99%

Section: Study Characteristicsmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning techniques for detecting electrode misplacement and interchanges when recording ECGs: A systematic review and meta-analysis

Rjoob

Bond

Finlay

et al. 2020

Journal of Electrocardiology

Self Cite

View full text Add to dashboard Cite

show abstract

“…Machine learning (ML) approaches to the diagnosis and prediction of MI have been leveraged in a growing body of research, the preponderance of which focus on risk stratification or outcomes predictions following an MI [ 23 , 24 ]. ML approaches to assist with specific steps in the initial diagnostic process have also been investigated, including approaches to improving ECG interpretation, identifying misplacement of ECG leads, and enhancing cardiac imaging capabilities to detect acute MI [ 25 , 26 , 27 ]. However, a Machine Learning Algorithm (MLA) based clinical decision support (CDS) tool that supports rapid rule in or rule out of MI, and provides actionable estimations of risk to guide the intensity of interventions, would improve care by minimising delays to individualised, risk‐appropriate treatment.…”

Section: Introductionmentioning

confidence: 99%

Retrospective validation of a machine learning clinical decision support tool for myocardial infarction risk stratification

Panchavati

Lam

Zelin

et al. 2021

Healthc. technol. lett.

View full text Add to dashboard Cite

Diagnosis and appropriate intervention for myocardial infarction (MI) are time-sensitive but rely on clinical measures that can be progressive and initially inconclusive, underscoring the need for an accurate and early predictor of MI to support diagnostic and clinical management decisions. The objective of this study was to develop a machine learning algorithm (MLA) to predict MI diagnosis based on electronic health record data (EHR) readily available during Emergency Department assessment. An MLA was developed using retrospective patient data. The MLA used patient data as they became available in the first 3 h of care to predict MI diagnosis (defined by International Classification of Diseases, 10th revision code) at any time during the encounter. The MLA obtained an area under the receiver operating characteristic curve of 0.87, sensitivity of 87% and specificity of 70%, outperforming the comparator scoring systems TIMI and GRACE on all metrics. An MLA can synthesize complex EHR data to serve as a clinically relevant risk stratification tool for MI.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

“…Patch-based lead systems have been introduced for cardiac arrhythmia monitoring however there has been less emphasis on the development and reporting of systems designed for ischaemic heart disease [8]. Such devices are prone to placement errors, however, ML can detect misplacement [9]. We have previously introduced an SSL based on the greatest ST-segment changes across patients with ischaemic-type ECG changes [10].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Approach to Assess the Performance of Patch Based Leads in the Detection of Ischaemic Electrocardiogram Changes

Jennings

Biglarbeigi

Bond

et al. 2020

2020 Computing in Cardiology Conference (CinC)

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Data driven feature selection and machine learning to detect misplaced V1 and V2 chest electrodes when recording the 12‑lead electrocardiogram

Cited by 14 publications

References 19 publications

Machine learning techniques for detecting electrode misplacement and interchanges when recording ECGs: A systematic review and meta-analysis

Machine learning techniques for detecting electrode misplacement and interchanges when recording ECGs: A systematic review and meta-analysis

Retrospective validation of a machine learning clinical decision support tool for myocardial infarction risk stratification

Machine Learning Approach to Assess the Performance of Patch Based Leads in the Detection of Ischaemic Electrocardiogram Changes

Contact Info

Product

Resources

About