Correlation analysis of deep learning methods in S-ICD screening.

BACKGROUND: Machine learning methods are used in the classification of various cardiovascular diseases through ECG data analysis. The concept of varying subcutaneous implantable cardiac defibrillator (S-ICD) eligibility, owing to the dynamicity of ECG signals, has been introduced before. There are practical limitations to acquiring longer durations of ECG signals for S-ICD screening. This study explored the potential use of deep learning methods in S-ICD screening. METHODS: This was a retrospective study. A deep learning tool was used to provide descriptive analysis of the T:R ratios over 24 h recordings of S-ICD vectors. Spearman's rank correlation test was used to compare the results statistically to those of a "gold standard" S-ICD simulator. RESULTS: A total of 14 patients (mean age: 63.7 ± 5.2 years, 71.4% male) were recruited and 28 vectors were analyzed. Mean T:R, standard deviation of T:R, and favorable ratio time (FVR)-a new concept introduced in this study-for all vectors combined were 0.21 ± 0.11, 0.08 ± 0.04, and 79 ± 30%, respectively. There were statistically significant strong correlations between the outcomes of our novel tool and the S-ICD simulator (p < .001). CONCLUSION: Deep learning methods could provide a practical software solution to analyze data acquired for longer durations than current S-ICD screening practices. This could help select patients better suited for S-ICD therapy as well as guide vector selection in S-ICD eligible patients. Further work is needed before this could be translated into clinical practice.

Role of deep learning methods in screening for subcutaneous implantable cardioverter defibrillator in heart failure.

INTRODUCTION: S-ICD eligibility is assessed at pre-implant screening where surface ECG traces are used as surrogates for S-ICD vectors. In heart failure (HF) patients undergoing diuresis, electrolytes and fluid shifts can cause changes in R and T waves. Subsequently, T:R ratio, a major predictor of S-ICD eligibility, can be dynamic. METHODS: This is a prospective study of patients with structurally normal hearts and HF patients undergoing diuresis. All patients were fitted with Holters® to record their S-ICD vectors. Our deep learning model was used to analyze the T:R ratios across the recordings. Welch two sample t-test and Mann-Whitney U were used to compare the data between the two groups. RESULTS: Twenty-one patients (age 58.43 ± 18.92, 62% male, 14 HF, 7 normal hearts) were enrolled. There was a significant difference in the T:R ratios between both groups. Mean T: R was higher in the HF group (0.18 ± 0.08 vs 0.10 ± 0.05, p < .001). Standard deviation of T: R was also higher in the HF group (0.09 ± 0.05 vs 0.07 ± 0.04, p = .024). There was no difference between leads within the same group. CONCLUSIONS: T:R ratio, a main determinant for S-ICD eligibility, is higher and has more tendency to fluctuate in HF patients undergoing diuresis. We hypothesize that our novel neural network model could be used to select HF patients eligible for S-ICD by better characterization of T:R ratio reducing the risk of T-wave over-sensing (TWO) and inappropriate shocks. Further work is required to consolidate our findings before applying to clinical practice.

Contemporary Management of Complex Ventricular Arrhythmias.

Percutaneous catheter ablation is an effective and safe therapy that can eliminate ventricular tachycardia, reducing the risks of both recurrent arrhythmia and shock therapies from a defibrillator. Successful ablation requires accurate identification of arrhythmic substrate and the effective delivery of energy to the targeted tissue. A thorough pre-procedural assessment is needed before considered 3D electroanatomical mapping can be performed. In contemporary practice, this must combine traditional electrophysiological techniques, such as activation and entrainment mapping, with more novel physiological mapping techniques for which there is an ever-increasing evidence base. Novel techniques to maximise energy delivery to the tissue must also be considered and balanced against their associated risks of complication. This review provides a comprehensive appraisal of contemporary practice and the evidence base that supports recent developments in mapping and ablation, while also considering potential future developments in the field.

Deep learning-based insights on T:R ratio behaviour during prolonged screening for S-ICD eligibility.

BACKGROUND: A major predictor of eligibility of subcutaneous implantable cardiac defibrillators (S-ICD) is the T:R ratio. The eligibility cut-off of the T:R ratio incorporates a safety margin to accommodate for fluctuations of ECG signal amplitudes. We introduce a deep learning-based tool that accurately measures the degree of T:R ratio fluctuations and explore its role in S-ICD screening. METHODS: Patients were fitted with Holters for 24 h to record their S-ICD vectors. Our tool was used to assess the T:R ratio over the duration of the recordings. Multiple T:R ratio cut-off values were applied, identifying patients at high risk of T-wave oversensing (TWO) at each of the proposed values. The purpose of our study is to identify the ratio that recognises patients at high risk of TWO while not inappropriately excluding true S-ICD candidates. RESULTS: Thirty-seven patients (age 54.5 + / - 21.3 years, 64.8% male) were recruited. Fourteen patients had heart-failure, 7 hypertrophic cardiomyopathy, 7 had normal hearts, 6 had congenital heart disease, and 3 had prior inappropriate S-ICD shocks due to TWO. 54% of patients passed the screening at a T: R of 1:3. All patients passed the screening at a T: R of 1:1. The only subgroup to wholly pass the screening utilising all the proposed ratios are the participants with normal hearts. CONCLUSION: We propose adopting prolonged screening to select patients eligible for S-ICD with low probability of TWO and inappropriate shocks. The appropriate T:R ratio likely lies between 1:3 and 1:1. Further studies are required to identify the optimal screening thresholds.

Short-coupled ventricular ectopics leading to cardiac arrest in a young woman.

BACKGROUND: This case report highlights the importance of recognizing that ventricular ectopy may be a cause for syncope and sudden cardiac death, through triggered disorganized arrhythmia. In the context of syncope, ventricular ectopy should be carefully assessed for coupling interval and morphology. CASE PRESENTATION: A 39-year-old woman, who had presented with recurrent syncope, had a cardiac arrest shortly after admission that required emergency defibrillation. Review of her cardiac monitoring revealed an episode of polymorphic ventricular tachycardia which had degenerated into ventricular fibrillation. The dysrhythmia had been initiated by a short-coupled (R-on-T) ventricular ectopic (VE) beat. Anti-arrhythmic therapy was initiated in the form of hydroquinidine, but the patient continued to have frequent VEs of right bundle branch block (RBBB) morphology with a relatively narrow QRS complex and a variation in frontal axis. A cardiac MRI revealed late gadolinium enhancement of the posterior papillary muscle (indicative of focal scarring). The patient underwent electrophysiological mapping and catheter ablation of her ectopy. The patient made a good recovery and was discharged from hospital with a secondary prevention implantable cardioverter-defibrillator (ICD) in situ. CONCLUSIONS: Short-couped VEs that are superimposed onto the preceding T wave (R-on-T) are indicative of electrical instability of the heart and should prompt urgent investigation. By studying the morphologies and axes of the QRS complexes produced by VEs, we can identify their likely origins and ascertain their clinical significance.

Electrocardiographic changes during haemodialysis and the potential impact on subcutaneous implantable cardioverter defibrillator eligibility.

INTRODUCTION: Haemodialysis patients who require defibrillator therapy are expected to benefit from the entirely avascular subcutaneous defibrillator (S-ICD), but haemodialysis is associated with dynamic changes in R and T wave amplitude which can impact S-ICD eligibility. A continuous assessment of S-ICD eligibility during haemodialysis has not previously been performed. MATERIAL AND METHODS: Continuous surface ECG recordings were obtained from a cohort of patients undergoing maintenance haemodialysis, but without an indication for an ICD. Automated vector screening was retrospectively performed at one-minute intervals throughout the dialysis session. Variations in S-ICD eligibility were calculated and in vectors with high degrees of variation, the underlying mechanism was identified. RESULTS: 72 vector recordings (mean duration 254.1 ± 6.0 min) were obtained from 24 patients (mean age 64.3 ± 5.5 years, 68% male). At the start of haemodialysis 47 vectors were S-ICD eligible (65.2%). At the end of session, all of these vectors had remained eligible, and an additional 6 vectors had also become eligible (73.6%). High vector score variability was observed in 7 patients and the commonest cause was a progressive change in R:T ratio (71.5%). CONCLUSION: In a haemodialysis population, a single haemodialysis session can be associated with a potential change in S-ICD eligibility in 8.4% of vectors, with up to 12.5% of vectors showing high degrees of variability, most commonly due to variations in R:T ratio. In an S-ICD population with similar characteristics S-ICD screening prior to haemodialysis would be expected to more accurately identify vectors that retain eligibility.

Personalized subcutaneous implantable cardioverter-defibrillator sensing vectors generated by mathematical rotation increase device eligibility whilst preserving device performance.

AIMS: Approximately 5.7% of potential subcutaneous implantable cardioverter-defibrillator (S-ICD) recipients are ineligible by virtue of their vector morphology, with higher rates of ineligibility observed in some at-risk groups. Mathematical vector rotation is a novel technique that can generate a personalized sensing vector, one with maximal R:T ratio, using electrocardiogram (ECG) signal recorded from the present S-ICD location. METHODS AND RESULTS: A cohort of S-ICD ineligible patients were identified through ECG screening of ICD patients with no ventricular pacing requirement and their personalized vectors were generated using ECG signal from a Holter monitor. Subcutaneous ICD eligibility in this cohort was then recalculated. In a separate cohort, episodes of arrhythmia were recorded in patients undergoing arrhythmia induction, and arrhythmia detection in standard S-ICD vectors was compared to rotated vectors using an S-ICD simulator. Ninety-two participants (mean age 64.9 ± 2.7 years) underwent screening and 5.4% were found to be S-ICD ineligible. Personalized vector generation increased the R:T ratio in these vectors from 2.21 to 7.21 (4.54-9.88, P < 0.001) increasing the cohort eligibility from 94.6% to 100%. Rotated S-ICD vectors also showed high ventricular fibrillation (VF) detection sensitivity (97.8%), low time to VF detection (6.1 s), and excellent tachycardia discrimination (sensitivity 96%, specificity 88%), with no significant differences between rotated and standard vectors. CONCLUSION: In S-ICD ineligible patients, mathematical vector rotation can generate a personalized vector that is associated with a significant increase in R:T ratio, resulting in universal device eligibility in our cohort. Ventricular fibrillation detection efficacy, time to VF detection, and tachycardia discrimination were not affected by vector rotation.

Hourly variability in outflow tract ectopy as a predictor of its site of origin.

INTRODUCTION: Before ablation, predicting the site of origin (SOO) of outflow tract ventricular arrhythmia (OTVA), can inform patient consent and facilitate appropriate procedural planning. We set out to determine if OTVA variability can accurately predict SOO. METHODS: Consecutive patients with a clear SOO identified at OTVA ablation had their prior 24-h ambulatory ECGs retrospectively analysed (derivation cohort). Percentage ventricular ectopic (VE) burden, hourly VE values, episodes of trigeminy/bigeminy, and the variability in these parameters were evaluated for their ability to distinguish right from left-sided SOO. Effective parameters were then prospectively tested on a validation cohort of consecutive patients undergoing their first OTVA ablation. RESULTS: High VE variability (coefficient of variation ≥0.7) and the presence of any hour with <50 VE, were found to accurately predict RVOT SOO in a derivation cohort of 40 patients. In a validation cohort of 29 patients, the correct SOO was prospectively identified in 23/29 patients (79.3%) using CoV, and 26/29 patients (89.7%) using VE < 50. Including current ECG algorithms, VE < 50 had the highest Youden Index (78), the highest positive predictive value (95.0%) and the highest negative predictive value (77.8%). CONCLUSION: VE variability and the presence of a single hour where VE < 50 can be used to accurately predict SOO in patients with OTVA. Accuracy of these parameters compares favorably to existing ECG algorithms.

S-ICD screening revisited: do passing vectors sometimes fail?

INTRODUCTION: Pre-implant ECG screening is performed to ensure that S-ICD recipients have at least one suitable sensing vector, yet cardiac over-sensing remains the commonest cause of inappropriate shock therapy in the S-ICD population. One explanation would be the presence of dynamic variations in ECG morphology that result in variations in vector eligibility. METHODS: Adult ICD patients had a 24-h ambulatory ECG performed using a digital Holter positioned to record all three S-ICD vectors. Using an S-ICD simulator, automated screening was then performed at one-minute intervals. In vectors with a mean vector score > 100 (the accepted value for a passing vector when screened on a single occasion), the percentage of all screening assessments that passed, eligible vector time (EVT), was calculated. EVT was compared statistically to QRS duration, corrected time to peak T (pTc) and mean vector score. RESULTS: Ambulatory monitoring was performed in 14 patients (mean age 63.7 ± 5.2 years, 71.4% male) with 42 vectors analysed. In 19 vectors the mean vector score was > 100. Within this "passing" cohort EVT varied between 42.7% and 100%. In 7/19 (37%) the EVT was <75%. A negative correlation was found between QRS duration and EVT (Pearson correlation -.60, p = .007). No correlation was found between EVT and mean vector score or pTc. CONCLUSION: Vector eligibility is dynamic. When "passing" vectors are subjected to repeated screening, 37% are found to be ineligible, more than a quarter of the time. Further investigation is required to determine the clinical significance of these findings.

A new algorithm to reduce T-wave over-sensing based on phase space reconstruction in S-ICD system.

BACKGROUND AND OBJECTIVE: The subcutaneous implantable cardioverter defibrillator (S-ICD) reduces mortality in individuals at high risk of sudden arrhythmic death, by rapid defibrillation of life-threatening arrhythmia. Unfortunately, S-ICD recipients are also at risk of inappropriate shock therapies, which themselves are associated with increased rates of mortality and morbidity. The commonest cause of inappropriate shock therapies is T wave oversensing (TWOS), where T waves are incorrectly counted as R waves leading to an overestimation of heart rate. It is important to develop a method to reduce TWOS and improve the accuracy of R-peak detection in S-ICD system. METHODS: This paper introduces a novel algorithm to reduce TWOS based on phase space reconstruction (PSR); a common method used to analyse the chaotic characteristics of non-linear signals. RESULTS: The algorithm was evaluated against 34 records from University Hospital Southampton (UHS) and all 48 records from the MIT-BIH arrhythmia database. In the UHS analysis we demonstrated a sensitivity of 99.88%, a positive predictive value of 99.99% and an accuracy of 99.88% with reductions in TWOS episodes (from 166 to 0). Whilst in the MIT-BIH analysis we demonstrated a sensitivity of 99.87%, a positive predictive value of 99.99% and an accuracy of 99.91% for R wave detection. The average processing time for 1 min ECG signals from all records is 2.9 s. CONCLUSIONS: Our algorithm is sensitive for R-wave detection and can effectively reduce the TWOS with low computational complexity, and it would therefore have the potential to reduce inappropriate shock therapies in S-ICD recipients, which would significantly reduce shock related morbidity and mortality, and undoubtedly improving patient's quality of life.

Bipolar Radiofrequency Ablation of Septal Ventricular Tachycardia Facilitated by an Intramural Catheter.

Intramural septal substrate presents a challenge in patients undergoing ventricular tachycardia ablation, in terms of both accurate mapping and ablation with unipolar radiofrequency energy. We present the first use of the novel 2-F octapolar catheter in accurately defining intramural septal scar and facilitating bipolar ablation. (Level of Difficulty: Advanced.).

Deep learning methods for screening patients' S-ICD implantation eligibility.

Subcutaneous Implantable Cardioverter-Defibrillators (S-ICDs) are used for prevention of sudden cardiac death triggered by ventricular arrhythmias. T Wave Over Sensing (TWOS) is an inherent risk with S-ICDs which can lead to inappropriate shocks. A major predictor of TWOS is a high T:R ratio (the ratio between the amplitudes of the T and R waves). Currently, patients' Electrocardiograms (ECGs) are screened over 10 s to measure the T:R ratio to determine the patients' eligibility for S-ICD implantation. Due to temporal variations in the T:R ratio, 10 s is not a long enough window to reliably determine the normal values of a patient's T:R ratio. In this paper, we develop a convolutional neural network (CNN) based model utilising phase space reconstruction matrices to predict T:R ratios from 10-second ECG segments without explicitly locating the R or T waves, thus avoiding the issue of TWOS. This tool can be used to automatically screen patients over a much longer period and provide an in-depth description of the behavior of the T:R ratio over that period. The tool can also enable much more reliable and descriptive screenings to better assess patients' eligibility for S-ICD implantation.

A Systematic Review of the Incidence of Arrhythmias in Hemodialysis Patients Undergoing Long-Term Monitoring With Implantable Loop Recorders.

INTRODUCTION: Establishing the frequency and nature of arrhythmias in hemodialysis (HD) is an important step in improving outcomes of these patients. We undertook this systematic review and meta-analysis to characterize arrhythmia frequency in maintenance HD patients. METHODS: We identified studies on arrhythmias in adult patients on maintenance HD detected via implantable loop recorders (ILRs). Studies included were in English and reported ILR-detected arrhythmia incidence in HD patients. Data were extracted by one author using electronic spreadsheets and verified by a second author. Random effects models were used for pooled inferences. The I 2 statistic was used to quantify heterogeneity. RESULTS: Five studies qualified for inclusion (317 patients). The overall estimates for the annualized rate of death and sudden cardiac death (SCD) was 0.14 (95% confidence interval [CI]: 0.11-0.18) and 0.06 (95% CI: 0.03-0.10), respectively. Across all 5 studies, the combined annualized rate of patients experiencing at least 1 bradycardia/asystole event was 0.19 (95% CI: 0.11-0.33) but heterogeneity was high (I 2 = 79.8%). The average annualized rate of sustained ventricular tachycardia (VT) or ventricular fibrillation (VF) episodes (0.02, 95% CI: 0.01-0.05) was significantly lower (P < 0.001) than the rate of bradycardia/asystole reported in the same patients. Incidence of atrial fibrillation (AF) varied significantly across the studies (from 0.07 to 0.83 patients per year) reflecting variable definitions (new-onset vs. total number of episodes). CONCLUSION: The incidence of arrhythmias among chronic HD patients is high, with bradycardia/asystole occurring more frequently than ventricular arrhythmias. Additional studies to refine estimates particularly of AF are needed.

British Heart Rhythm Society Clinical Practice Guidelines on the Management of Patients Developing QT Prolongation on Antipsychotic Medication.

The British Heart Rhythm Society's Clinical Practice Guidelines on the Management of Patients Developing QT Prolongation on Antipsychotic Medication are written for heart rhythm consultants, primary care physicians, specialist registrars, nurses and physiologists who may be requested to review ECGs or advise on cases where antipsychotic-induced QT prolongation is suspected or proven. The guidance is adapted from the latest Maudsley Prescribing Guidelines in Psychiatry, published in 2018.

Design and evaluation of the Micra Transcatheter Pacing System for bradyarrhythmia management.

Permanent cardiac pacemakers have traditionally comprised a surgically implanted subcutaneous pulse generator affixed to at least one transvenous pacing lead. Despite technological advances, implant-related complications and transvenous-lead failure rates have remained high. The Micra Transcatheter Pacing System is a miniaturized single chamber pacemaker that is implanted directly into the right ventricle, eliminating the subcutaneous pocket and creating a leadless pacemaker system. Registry data show an extremely high implant success rate, significantly lower major complication rates than transvenous pacemakers, stable pacing parameters and reliable battery performance. In this review we summarize the available clinical literature and highlight the promising efficacy and safety of the Micra Transcatheter Pacing System.

A tertiary centre experience of thoracic CT and cardiac MRI scanning in the presence of a reveal LINQ insertable cardiac monitoring system: a case series review of artefact, patient safety and data preservation.

OBJECTIVE: At our tertiary cardiothoracic centre, cardiac MRI and thoracic CT scans are performed in patients with implanted LINQ devices. The degree of foreign body artefact associated with the LINQ device, and its clinical importance, has not previously been assessed. A case series review was therefore performed with a simultaneous review of patient safety and data loss events, secondary to the MRI environment. METHODS: A local database search identified LINQ device patients who underwent thoracic CT or cardiac MRI scans between March 2014 and December 2016. Images were reviewed by two radiologists, recording the presence of subcutaneous and intrathoracic artefact, and its clinical significance. Furthermore a specialist in cardiac rhythm management reviewed all LINQ data downloads undertaken before and after MRI scanning, and a search of the trust incident reporting system was performed. RESULTS: Minor subcutaneous artefact was present on all scans. Intrathoracic artefact was observed in 25.6% of thoracic CT scans and 33.3% of cardiac MRIs; however no clinically significant artefact was observed. Device downloads were only performed by 53.8% of patients prior to their MRI scan and 56.5% after their MRI scan. No adverse patient safety or data loss events were noted. CONCLUSION: The LINQ device does not produce clinically significant artefact, even when artefact extends into the intrathoracic space, which occurs in a third of MRIs and a quarter of CTs. MRI scanning of the LINQ device is safe with no evidence of inappropriate data loss. Advances in knowledge: This is the first published case series of CT and MRI scanning in LINQ patients and the first performed quantification of artefact related to the LINQ device.

Keeping up appearances: the radiographic evolution of cardiovascular implantable electronic devices.

In recent years, there has been a significant evolution in the field of cardiovascular implantable electronic devices (CIEDs). Pacemakers can now be leadless, implantable cardioverter defibrillators can be entirely subcutaneous and implantable loop recorders have become miniaturized. Driven by technological advances and an ageing population implant numbers have also steadily increased. These highly prevalent systems are all radio-opaque and are frequently observed on chest radiographs, yet the devices are neither well recognized nor understood. We present a pictorial review of CIEDs; describing the chest radiograph appearances of both newer generation systems and their traditional predecessors. Furthermore, we discuss the clinical role of chest radiography in both CIED implantation and follow up, with the aim of improving understanding in this important and expanding field. Finally, we present a collection of interesting and challenging radiographs, where multiple CIED systems have been implanted.