The VT Prediction Model: A simplified means to differentiate wide complex tachycardias

A novel way to prospectively evaluate of AI-enhanced ECG algorithms

Significant strides will be made in the field of computerized electrocardiology through the development of artificial intelligence (AI)-enhanced ECG (AI-ECG) algorithms. Yet, the scientific discourse has primarily relied upon on retrospective analyses for deriving and externally validating AI-ECG classification algorithms, an approach that fails to fully judge their real-world effectiveness or reveal potential unintended consequences. Prospective trials and analyses of AI-ECG algorithms will be crucial for assessing real-world diagnostic scenarios and understanding their practical utility and degree influence they confer onto clinicians. However, conducting such studies is challenging due to their resource-intensive nature and associated technical and logistical hurdles. To overcome these challenges, we propose an innovative approach to assess AI-ECG algorithms using a virtual testing environment. This strategy can yield critical insights into the practical utility and clinical implications of novel AI-ECG algorithms. Moreover, such an approach can enable an assessment of the influence of AI-ECG algorithms have their users. Herein, we outline a proposed randomized control trial for evaluating the diagnostic efficacy of new AI-ECG algorithm(s) specifically designed to differentiate between wide complex tachycardias into ventricular tachycardia and supraventricular wide complex tachycardia.

Mayo Clinic VT calculator: A practical tool for accurate wide complex tachycardia differentiation

The discrimination of ventricular tachycardia (VT) versus supraventricular wide complex tachycardia (SWCT) via 12-lead electrocardiogram (ECG) is crucial for achieving appropriate, high-quality, and cost-effective care in patients presenting with wide QRS complex tachycardia (WCT). Decades of rigorous research have brought forth an expanding arsenal of applicable manual algorithm methods for differentiating WCTs. However, these algorithms are limited by their heavy reliance on the ECG interpreter for their proper execution. Herein, we introduce the Mayo Clinic ventricular tachycardia calculator (MC-VTcalc) as a novel generalizable, accurate, and easy-to-use means to estimate VT probability independent of ECG interpreter competency. The MC-VTcalc, through the use of web-based and mobile device platforms, only requires the entry of computerized measurements (i.e., QRS duration, QRS axis, and T-wave axis) that are routinely displayed on standard 12-lead ECG recordings.

The emergence and destiny of automated methods to differentiate wide QRS complex tachycardias

Accurate differentiation of wide complex tachycardias (WCTs) into ventricular tachycardia (VT) or supraventricular wide complex tachycardia (SWCT) using non-invasive methods such as 12‑lead electrocardiogram (ECG) interpretation is crucial in clinical practice. Recent studies have demonstrated the potential for automated approaches utilizing computerized ECG interpretation software to achieve accurate WCT differentiation. In this review, we provide a comprehensive analysis of contemporary automated methods for VT and SWCT differentiation. Our objectives include: (i) presenting a general overview of the emergence of automated WCT differentiation methods, (ii) examining the role of machine learning techniques in automated WCT differentiation, (iii) reviewing the electrophysiology concepts leveraged existing automated algorithms, (iv) discussing recently developed automated WCT differentiation solutions, and (v) considering future directions that will enable the successful integration of automated methods into computerized ECG interpretation platforms.

Diagnostic accuracy of different ECG-based algorithms in wide QRS complex tachycardia: a systematic review and meta-analysis

OBJECTIVE

Several ECG-based algorithms have been proposed to enhance the effectiveness of distinguishing Wide QRS complex tachycardia (WCT), but a comprehensive comparison of their accuracy is still lacking. This meta-analysis aimed to assess the diagnostic precision of various non-artificial intelligence ECG-based algorithms for WCT.

DESIGN

Systematic review with meta-analysis.

DATA SOURCES

Electronic databases (PubMed, MEDLINE, the Cochrane Library, and Web of Science) are searched up to May 2022.

ELIGIBILITY CRITERIA FOR SELECTING STUDIES

All studies reporting the diagnostic accuracy of different ECG-based algorithms for WCT are included. The risk of bias in included studies is assessed using the Cochrane Collaboration's risk of bias tools.

DATA EXTRACTION AND SYNTHESIS

Two independent reviewers extracted data and assessed risk of bias. Data were pooled using random-effects model and expressed as mean differences with 95% CIs. Heterogeneity was calculated by the I² method. The Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool was applied to assess the internal validity of the diagnostic studies.

RESULTS

In total, 467 studies were identified, and 14 studies comprising 3966 patients were included, involving four assessable ECG-based algorithms: the Brugada algorithm, Vereckei-pre algorithm, Vereckei-aVR algorithm and R wave peak time of lead II (RWPT-II) algorithm. The overall sensitivity was 88.89% (95% CI: 85.03 to 91.86), with a specificity of 70.55% (95% CI: 62.10 to 77.79) and a diagnostic OR (DOR) of 19.17 (95% CI: 11.45 to 32.10). Heterogeneity of the DOR was 89.1%. The summary sensitivity of each algorithm was Brugada 90.25%, Vereckei-pre 94.80%, Vereckei-aVR 90.35% and RWPT-II 78.15%; the summary specificity was Brugada 64.02%, Vereckei-pre 75.40%, Vereckei-aVR 60.88% and RWPT-II 88.30% and the summary DOR was Brugada 16.48, Vereckei-pre 60.70, Vereckei-aVR 14.57 and RWPT-II 27.00.

CONCLUSIONS

ECG-based algorithms exhibit high sensitivity and moderate specificity in diagnosing WCT. A combination of Brugada or Vereckei-aVR algorithm with RWPT-II could be considered to diagnose WCT.

PROSPERO REGISTRATION NUMBER

CRD42022344996.

Comparison of two artificial intelligence-augmented ECG approaches: Machine learning and deep learning

BACKGROUND

Artificial intelligence-augmented ECG (AI-ECG) refers to the application of novel AI solutions for complex ECG interpretation tasks. A broad variety of AI-ECG approaches exist, each having differing advantages and limitations relating to their creation and application.

PURPOSE

To provide illustrative comparison of two general AI-ECG modeling approaches: machine learning (ML) and deep learning (DL).

METHOD COMPARISON

Two AI-ECG algorithms were developed to carry out two separate tasks using ML and DL, respectively. ML modeling techniques were used to create algorithms designed for automatic wide QRS complex tachycardia differentiation into ventricular tachycardia and supraventricular tachycardia. A DL algorithm was formulated for the task of comprehensive 12‑lead ECG interpretation. First, we describe the ML models for WCT differentiation, which rely upon expert domain knowledge to identify and formulate ECG features (e.g., percent monophasic time-voltage area [PMonoTVA]) that enable strong diagnostic performance. Second, we describe the DL method for comprehensive 12‑lead ECG interpretation, which relies upon the independent recognition and analysis of a virtually incalculable number of ECG features from a vast collection of standard 12‑lead ECGs.

CONCLUSION

We have showcased two different AI-ECG methods, namely ML and DL respectively. In doing so, we highlighted the strengths and weaknesses of each approach. It is essential for investigators to understand these differences when attempting to create and apply novel AI-ECG solutions.

Computerized electrocardiogram data transformation enables effective algorithmic differentiation of wide QRS complex tachycardias

BACKGROUND

Accurate automated wide QRS complex tachycardia (WCT) differentiation into ventricular tachycardia (VT) and supraventricular wide complex tachycardia (SWCT) can be accomplished using calculations derived from computerized electrocardiogram (ECG) data of paired WCT and baseline ECGs.

OBJECTIVE

Develop and trial novel WCT differentiation approaches for patients with and without a corresponding baseline ECG.

METHODS

We developed and trialed WCT differentiation models comprised of novel and previously described parameters derived from WCT and baseline ECG data. In Part 1, a derivation cohort was used to evaluate five different classification models: logistic regression (LR), artificial neural network (ANN), Random Forests [RF], support vector machine (SVM), and ensemble learning (EL). In Part 2, a separate validation cohort was used to prospectively evaluate the performance of two LR models using parameters generated from the WCT ECG alone (Solo Model) and paired WCT and baseline ECGs (Paired Model).

RESULTS

Of the 421 patients of the derivation cohort (Part 1), a favorable area under the receiver operating characteristic curve (AUC) by all modeling subtypes: LR (0.96), ANN (0.96), RF (0.96), SVM (0.96), and EL (0.97). Of the 235 patients of the validation cohort (Part 2), the Solo Model and Paired Model achieved a favorable AUC for 103 patients with (Solo Model 0.87; Paired Model 0.95) and 132 patients without (Solo Model 0.84; Paired Model 0.95) a corroborating electrophysiology procedure or intracardiac device recording.

CONCLUSION

Accurate WCT differentiation may be accomplished using computerized data of (i) the WCT ECG alone and (ii) paired WCT and baseline ECGs.

Electrocardiographic QRS axis shift, rotation and COVİD-19

Background

In patients with coronavirus disease-2019 (COVID-19), severe dyspnea is the most dramatic complication. Severe respiratory difficulties may include electrocardiographic frontal QRS axis rightward shift (Rws) and clockwise rotation (Cwr).

Aim

This study investigated the predictability of advanced lung tomography findings with QRS axis shift and rotation.

Patients and Methods

This was a retrospective analysis of 160 patients. Patients were divided into the following two groups: normal (n = 80) and low (n = 80) oxygen saturation. These groups were further divided into four groups according to the rightward and leftward axis shift (Lws) on the electrocardiographic follow-up findings. These groups were compared in terms of electrocardiographic rotation (Cwr, counterclockwise rotation, or normal transition), tomographic stage (CO-RADS5(advanced)/CO-RADS1-4), electrocardiographic intervals, and laboratory findings.

Results

In patients with low oxygen saturation, the amount of QRS axis shift, Cwr, and tomographic stage were significantly higher in the Rws group than in the Lws group. There were no differences in the above parameters between the Rws and Lws groups in patients with normal oxygen saturation. Logistic regression analysis revealed that the presence of Cwr and Rws independently increased the risk of CO-RADS5 by 18.9 and 4.6 fold, respectively, in patients with low oxygen saturation.

Conclusion

In COVID-19 patients who have dyspnea with low oxygen saturation, electrocardiographically clockwise rotation with a rightward axis shift demonstrated good sensitivity (80% [0.657-0.943]) and specificity (80% [0.552->1]) for predicting advanced lung tomographic findings.

ClinicalTrialsgov Identifier

NCT04698083.

Wide complex tachycardia discrimination tool improves physicians' diagnostic accuracy

BACKGROUND

Timely and accurate discrimination of wide complex tachycardias (WCTs) into ventricular tachycardia (VT) or supraventricular WCT (SWCT) is critically important. Previously we developed and validated an automated VT Prediction Model that provides a VT probability estimate using the paired WCT and baseline 12-lead ECGs. Whether this model improves physicians' diagnostic accuracy has not been evaluated.

OBJECTIVE

We sought to determine whether the VT Prediction Model improves physicians' WCT differentiation accuracy.

METHODS

Over four consecutive days, nine physicians independently interpreted fifty WCT ECGs (25 VTs and 25 SWCTs confirmed by electrophysiological study) as either VT or SWCT. Day 1 used the WCT ECG only, Day 2 used the WCT and baseline ECG, Day 3 used the WCT ECG and the VT Prediction Model's estimation of VT probability, and Day 4 used the WCT ECG, baseline ECG, and the VT Prediction Model's estimation of VT probability.

RESULTS

Inclusion of the VT Prediction Model data increased diagnostic accuracy versus the WCT ECG alone (Day 3: 84.2% vs. Day 1: 68.7%, p 0.009) and WCT and baseline ECGs together (Day 3: 84.2% vs. Day 2: 76.4%, p 0.003). There was no further improvement of accuracy with addition of the baseline ECG comparison to the VT Prediction Model (Day 3: 84.2% vs. Day 4: 84.0%, p 0.928). Overall sensitivity (Day 3: 78.2% vs. Day 1: 67.6%, p 0.005) and specificity (Day 3: 90.2% vs. Day 1: 69.8%, p 0.016) for VT were superior after the addition of the VT Prediction Model.

CONCLUSION

The VT Prediction Model improves physician ECG diagnostic accuracy for discriminating WCTs.

Automatic wide complex tachycardia differentiation using mathematically synthesized vectorcardiogram signals

BACKGROUND

Automated wide complex tachycardia (WCT) differentiation into ventricular tachycardia (VT) and supraventricular wide complex tachycardia (SWCT) may be accomplished using novel calculations that quantify the extent of mean electrical vector changes between the WCT and baseline electrocardiogram (ECG). At present, it is unknown whether quantifying mean electrical vector changes within three orthogonal vectorcardiogram (VCG) leads (X, Y, and Z leads) can improve automated VT and SWCT classification.

METHODS

A derivation cohort of paired WCT and baseline ECGs was used to derive five logistic regression models: (i) one novel WCT differentiation model (i.e., VCG Model), (ii) three previously developed WCT differentiation models (i.e., WCT Formula, VT Prediction Model, and WCT Formula II), and (iii) one "all-inclusive" model (i.e., Hybrid Model). A separate validation cohort of paired WCT and baseline ECGs was used to trial and compare each model's performance.

RESULTS

The VCG Model, composed of WCT QRS duration, baseline QRS duration, absolute change in QRS duration, X-lead QRS amplitude change, Y-lead QRS amplitude change, and Z-lead QRS amplitude change, demonstrated effective WCT differentiation (area under the curve [AUC] 0.94) for the derivation cohort. For the validation cohort, the diagnostic performance of the VCG Model (AUC 0.94) was similar to that achieved by the WCT Formula (AUC 0.95), VT Prediction Model (AUC 0.91), WCT Formula II (AUC 0.94), and Hybrid Model (AUC 0.95).

CONCLUSION

Custom calculations derived from mathematically synthesized VCG signals may be used to formulate an effective means to differentiate WCTs automatically.

Conceptual and literature basis for wide complex tachycardia and baseline ECG comparison

Accurate wide QRS complex tachycardia (WCT) differentiation into either ventricular tachycardia or supraventricular wide complex tachycardia using 12‑lead electrocardiogram (ECG) interpretation is essential for diagnostic, therapeutic, and prognostic reasons. There is an ever-expanding variety of WCT differentiation methods and criteria available to clinicians. However, only a few make use of the diagnostic value of comparing the ECG during WCT to that of the patient's baseline ECG. Therefore, we highlight the conceptual rationale and scientific literature supporting the diagnostic value of WCT and baseline ECG comparison.

Differentiating wide complex tachycardias: A historical perspective

One of the most critical and challenging skills is the distinction of wide complex tachycardias into ventricular tachycardia or supraventricular wide complex tachycardia. Prompt and accurate differentiation of wide complex tachycardias naturally influences short- and long-term management decisions and may directly affect patient outcomes. Currently, there are many useful electrocardiographic criteria and algorithms designed to distinguish ventricular tachycardia and supraventricular wide complex tachycardia accurately; however, no single approach guarantees diagnostic certainty. In this review, we offer an in-depth analysis of available methods to differentiate wide complex tachycardias by retrospectively examining its rich literature base - one that spans several decades.

Utility of Inferior Lead Q-waveforms in diagnosing Ventricular Tachycardia

Background

Electrocardiogram (ECG) differentiation of wide complex tachycardia (WCT) into ventricular tachycardia (VT) and supraventricular tachycardia with aberration (SVT-A) is often challenging.

Objective

To determine if the presence of Q-waveforms (QS, Qr, QRs) in the inferior leads (II, III, aVF) can differentiate VT from SVT-A in a WCT compared to Brugada algorithm. We studied 2 inferior lead criteria namely QWC-A where all the inferior leads had a similar Q wave pattern and QWC-B where only lead aVF had a Q-waveform.

Methods

A total of 181 consecutive cases of WCT were identified, digitally separated into precordial leads and inferior leads and independently reviewed by 2 electrophysiologists. An electrocardiographic diagnosis of VT or SVT-A was assigned based on Brugada and inferior lead algorithms. Results were compared to the final clinical diagnosis.

Results

VT was the final clinical diagnosis in 24.9% of ECG cohort (45/181); 75.1% (136/181) were SVT-A. QWC-A and QWC-B had a high specificity (93.3% and 82.8%) and accuracy (78.2% and 71.0%), but low sensitivity (33.3% and 35.6%) in differentiating VT from SVT-A. The Brugada algorithm yielded a sensitivity of 82.2% and specificity of 68.4%. Area under the curve in ROC analysis was highest with Brugada algorithm (0.75, 95% CI 0.69-0.81) followed by QWC-A (0.63, 95% CI 0.56-0.70) and QWC-B (0.59, 95% CI 0.52-0.67).

Conclusion

QWC-A and QWC-B criteria had poor sensitivity but high specificity in diagnosing VT in patients presenting with WCT. Further research combining this simple criterion with other newer diagnostic algorithms can potentially improve the accuracy of the overall diagnostic algorithm.

Wide Complex Tachycardia Differentiation: A Reappraisal of the State-of-the-Art

The primary goal of the initial ECG evaluation of every wide complex tachycardia is to determine whether the tachyarrhythmia has a ventricular or supraventricular origin. The answer to this question drives immediate patient care decisions, ensuing clinical workup, and long‐term management strategies. Thus, the importance of arriving at the correct diagnosis cannot be understated and has naturally spurred rigorous research, which has brought forth an ever‐expanding abundance of manually applied and automated methods to differentiate wide complex tachycardias. In this review, we provide an in‐depth analysis of traditional and more contemporary methods to differentiate ventricular tachycardia and supraventricular wide complex tachycardia. In doing so, we: (1) review hallmark wide complex tachycardia differentiation criteria, (2) examine the conceptual and structural design of standard wide complex tachycardia differentiation methods, (3) discuss practical limitations of manually applied ECG interpretation approaches, and (4) highlight recently formulated methods designed to differentiate ventricular tachycardia and supraventricular wide complex tachycardia automatically.

The ventricular tachycardia prediction model: Derivation and validation data

In a recent publication [1], we introduced and described a novel means (i.e. VT Prediction Model) to correctly categorize wide complex tachycardias (WCTs) into ventricular tachycardia (VT) and supraventricular wide complex tachycardia (SWCT) using routine measurements shown on electrocardiogram (ECG) paper recordings. In this article, we summarize data components relating to the derivation and validation of the VT Prediction Model.