QTNet: Predicting Drug-Induced QT Prolongation With Artificial Intelligence-Enabled Electrocardiograms.

BACKGROUND: Prediction of drug-induced long QT syndrome (diLQTS) is of critical importance given its association with torsades de pointes. There is no reliable method for the outpatient prediction of diLQTS. OBJECTIVES: This study sought to evaluate the use of a convolutional neural network (CNN) applied to electrocardiograms (ECGs) to predict diLQTS in an outpatient population. METHODS: We identified all adult outpatients newly prescribed a QT-prolonging medication between January 1, 2003, and March 31, 2022, who had a 12-lead sinus ECG in the preceding 6 months. Using risk factor data and the ECG signal as inputs, the CNN QTNet was implemented in TensorFlow to predict diLQTS. RESULTS: Models were evaluated in a held-out test dataset of 44,386 patients (57% female) with a median age of 62 years. Compared with 3 other models relying on risk factors or ECG signal or baseline QTc alone, QTNet achieved the best (P < 0.001) performance with a mean area under the curve of 0.802 (95% CI: 0.786-0.818). In a survival analysis, QTNet also had the highest inverse probability of censorship-weighted area under the receiver-operating characteristic curve at day 2 (0.875; 95% CI: 0.848-0.904) and up to 6 months. In a subgroup analysis, QTNet performed best among males and patients ≤50 years or with baseline QTc <450 ms. In an external validation cohort of solely suburban outpatient practices, QTNet similarly maintained the highest predictive performance. CONCLUSIONS: An ECG-based CNN can accurately predict diLQTS in the outpatient setting while maintaining its predictive performance over time. In the outpatient setting, our model could identify higher-risk individuals who would benefit from closer monitoring.

Left bundle branch area pacing using a stylet-driven, retractable-helix lead: Short-term results from a prospective multicenter IDE trial (the BIO-CONDUCT study).

BACKGROUND: Left bundle branch area pacing (LBBAP) has swiftly emerged as a safe and effective alternative to right ventricular pacing. Limited data exist on the use of retractable-helix, stylet-driven leads for LBBAP. OBJECTIVE: The objective of this study was to prospectively evaluate the performance and safety of the Solia S stylet-driven pacing lead in a rigorously controlled multicenter trial to support US market application. METHODS: A multicenter, prospective, nonrandomized trial enrolled patients with standard pacing indications. Implant procedure and lead data, including threshold, sensing, impedance, and capture type, were collected through 3 months. Primary end points were freedom from LBBAP lead-related serious complications through 3 months and LBBAP implant success according to prespecified criteria. A blinded clinical events committee adjudicated all potential end point complications. RESULTS: A total of 186 patients were included from 14 US sites. LBBAP implants were successful in 95.7% (178 of 186; 95% confidence interval 91.7%-98.1%; P < .0001 for comparison to the performance goal of 88%). Through the 3-month follow-up visit, 3 patients experienced a serious LBBAP complication (all lead dislodgments), resulting in a LBBAP lead-related complication-free rate of 98.3%. A total of 13 patients (7.8%) experienced any system- or procedure-related complication. The mean threshold was 0.89 V at 0.4 ms, the sensing value was 10.8 mV, and impedance was 608 Ω. CONCLUSION: The short-term results from this prospective trial demonstrate both high implant success and freedom from LBBAP lead-related complications using this stylet-driven retractable helix lead. This trial supports the safety, use, and effectiveness of stylet-driven leads for performing contemporary physiologic pacing.

Risk of malignant ventricular arrhythmias in patients with mildly to moderately reduced ejection fraction after permanent pacemaker implantation.

BACKGROUND: Many patients with mildly to moderately reduced left ventricular ejection fraction (LVEF) who require permanent pacemaker (PPM) implantation do not have a concurrent indication for implantable cardioverter-defibrillator (ICD) therapy. However, the risk of ventricular tachycardia/ventricular fibrillation (VT/VF) in this population is unknown. OBJECTIVE: The aim of this study was to describe the risk of VT/VF after PPM implantation in patients with mildly to moderately reduced LVEF. METHODS: Retrospective analysis was performed of 243 patients with LVEF between 35% and 49% who underwent PPM placement and did not meet indications for an ICD. The primary end point was occurrence of sustained VT/VF. Competing risks regression was performed to calculate subhazard ratios for the primary end point. RESULTS: Median follow-up was 27 months; 73% of patients were male, average age was 79 ± 10 years, average LVEF was 42% ± 4%, and 70% were New York Heart Association class II or above. Most PPMs were implanted for sick sinus syndrome (34%) or atrioventricular block (50%). Of 243 total patients, 11 (4.5%) met the primary end point of VT/VF. Multivessel coronary artery disease (CAD) was associated with significantly higher rates of VT/VF, with a subhazard ratio of 5.4 (95% CI, 1.5-20.1; P = .01). Of patients with multivessel CAD, 8 of 82 (9.8%) patients met the primary end point for an annualized risk of 4.3% per year. CONCLUSION: Patients with mildly to moderately reduced LVEF and multivessel CAD undergoing PPM implantation are at increased risk for the development of malignant ventricular arrhythmias. Patients in this population may benefit from additional risk stratification for VT/VF and consideration for upfront ICD implantation.

Conduction velocity is reduced in the posterior wall of hypertrophic cardiomyopathy patients with normal bipolar voltage undergoing ablation for paroxysmal atrial fibrillation.

OBJECTIVES: We investigated characteristics of left atrial conduction in patients with HCM, paroxysmal AF and normal bipolar voltage. BACKGROUND: Patients with hypertrophic cardiomyopathy (HCM) exhibit abnormal cardiac tissue arrangement. The incidence of atrial fibrillation (AF) is increased fourfold in patients with HCM and confers a fourfold increased risk of death. Catheter ablation is less effective in HCM, with twofold increased risk of AF recurrence. The mechanisms of AF perpetuation in HCM are poorly understood. METHODS: We analyzed 20 patients with HCM and 20 controls presenting for radiofrequency ablation of paroxysmal AF normal left atrial voltage(> 0.5 mV). Intracardiac electrograms were extracted from the CARTO mapping system and analyzed using Matlab/Python code interfacing with Core OpenEP software. Conduction velocity maps were calculated using local activation time gradients. RESULTS: There were no differences in baseline demographics, atrial size, or valvular disease between HCM and control patients. Patients with HCM had significantly reduced atrial conduction velocity compared to controls (0.44 ± 0.17 vs 0.56 ± 0.10 m/s, p = 0.01), despite no significant differences in bipolar voltage amplitude (1.23 ± 0.38 vs 1.20 ± 0.41 mV, p = 0.76). There was a statistically significant reduction in conduction velocity in the posterior left atrium in HCM patients relative to controls (0.43 ± 0.18 vs 0.58 ± 0.10 m/s, p = 0.003), but not in the anterior left atrium (0.46 ± 0.17 vs 0.55 ± 0.10 m/s, p = 0.05). There was a significant association between conduction velocity and interventricular septal thickness (slope = -0.013, R2 = 0.13, p = 0.03). CONCLUSIONS: Atrial conduction velocity is significantly reduced in patients with HCM and paroxysmal AF, possibly contributing to arrhythmia persistence after catheter ablation.

Point-of-Care Chemistry-Guided Dialysate Adjustment to Reduce Arrhythmias: A Pilot Trial.

Introduction: Excessive dialytic potassium (K) and acid removal are risk factors for arrhythmias; however, treatment-to-treatment dialysate modification is rarely performed. We conducted a multicenter, pilot randomized study to test the safety, feasibility, and efficacy of 4 point-of-care (POC) chemistry-guided protocols to adjust dialysate K and bicarbonate (HCO3) in outpatient hemodialysis (HD) clinics. Methods: Participants received implantable cardiac loop monitors and crossed over to four 4-week periods with adjustment of dialysate K or HCO3 at each treatment according to pre-HD POC values: (i) K-removal minimization, (ii) K-removal maximization, (iii) Acidosis avoidance, and (iv) Alkalosis avoidance. The primary end point was percentage of treatments adhering to the intervention algorithm. Secondary endpoints included pre-HD K and HCO variability, adverse events, and rates of clinically significant arrhythmias (CSAs). Results: Nineteen subjects were enrolled in the study. HD staff completed POC testing and correctly adjusted the dialysate in 604 of 708 (85%) of available HD treatments. There was 1 K ≤3, 29 HCO3 <20 and 2 HCO3 >32 mEq/l and no serious adverse events related to study interventions. Although there were no significant differences between POC results and conventional laboratory measures drawn concurrently, intertreatment K and HCO3 variability was high. There were 45 CSA events; most were transient atrial fibrillation (AF), with numerically fewer events during the alkalosis avoidance period (8) and K-removal maximization period (3) compared to other intervention periods (17). There were no significant differences in CSA duration among interventions. Conclusion: Algorithm-guided K/HCO3 adjustment based on POC testing is feasible. The variability of intertreatment K and HCO3 suggests that a POC-laboratory-guided algorithm could markedly alter dialysate-serum chemistry gradients. Definitive end point-powered trials should be considered.

Explainable SHAP-XGBoost models for in-hospital mortality after myocardial infarction.

Background: A lack of explainability in published machine learning (ML) models limits clinicians' understanding of how predictions are made, in turn undermining uptake of the models into clinical practice. Objective: The purpose of this study was to develop explainable ML models to predict in-hospital mortality in patients hospitalized for myocardial infarction (MI). Methods: Adult patients hospitalized for an MI were identified in the National Inpatient Sample between January 1, 2012, and September 30, 2015. The resulting cohort comprised 457,096 patients described by 64 predictor variables relating to demographic/comorbidity characteristics and in-hospital complications. The gradient boosting algorithm eXtreme Gradient Boosting (XGBoost) was used to develop explainable models for in-hospital mortality prediction in the overall cohort and patient subgroups based on MI type and/or sex. Results: The resulting models exhibited an area under the receiver operating characteristic curve (AUC) ranging from 0.876 to 0.942, specificity 82% to 87%, and sensitivity 75% to 87%. All models exhibited high negative predictive value ≥0.974. The SHapley Additive exPlanation (SHAP) framework was applied to explain the models. The top predictor variables of increasing and decreasing mortality were age and undergoing percutaneous coronary intervention, respectively. Other notable findings included a decreased mortality risk associated with certain patient subpopulations with hyperlipidemia and a comparatively greater risk of death among women below age 55 years. Conclusion: The literature lacks explainable ML models predicting in-hospital mortality after an MI. In a national registry, explainable ML models performed best in ruling out in-hospital death post-MI, and their explanation illustrated their potential for guiding hypothesis generation and future study design.

A Tool to Integrate Electrophysiological Mapping for Cardiac Radioablation of Ventricular Tachycardia.

Purpose: Cardiac radioablation is an emerging therapy for recurrent ventricular tachycardia. Electrophysiology (EP) data, including electroanatomic maps (EAM) and electrocardiographic imaging (ECGI), provide crucial information for defining the arrhythmogenic target volume. The absence of standardized workflows and software tools to integrate the EP maps into a radiation planning system limits their use. This study developed a comprehensive software tool to enable efficient utilization of the mapping for cardiac radioablation treatment planning. Methods and Materials: The tool, HeaRTmap, is a Python-scripted plug-in module on the open-source 3D Slicer software platform. HeaRTmap is able to import EAM and ECGI data and visualize the maps in 3D Slicer. The EAM is translated into a 3D space by registration with cardiac magnetic resonance images (MRI) or computed tomography (CT). After the scar area is outlined on the mapping surface, the tool extracts and extends the annotated patch into a closed surface and converts it into a structure set associated with the anatomic images. The tool then exports the structure set and the images as The Digital Imaging and Communications in Medicine Standard in Radiotherapy for a radiation treatment planning system to import. Overlapping the scar structure on simulation CT, a transmural target volume is delineated for treatment planning. Results: The tool has been used to transfer Ensite NavX EAM data into the Varian Eclipse treatment planning system in radioablation on 2 patients with ventricular tachycardia. The ECGI data from CardioInsight was retrospectively evaluated using the tool to derive the target volume for a patient with left ventricular assist device, showing volumetric matching with the clinically used target with a Dice coefficient of 0.71. Conclusions: HeaRTmap smoothly fuses EP information from different mapping systems with simulation CT for accurate definition of radiation target volume. The efficient integration of EP data into treatment planning potentially facilitates the study and adoption of the technique.

Development of an AI-Driven QT Correction Algorithm for Patients in Atrial Fibrillation.

BACKGROUND: Prolongation of the QTc interval is associated with the risk of torsades de pointes. Determination of the QTc interval is therefore of critical importance. There is no reliable method for measuring or correcting the QT interval in atrial fibrillation (AF). OBJECTIVES: The authors sought to evaluate the use of a convolutional neural network (CNN) applied to AF electrocardiograms (ECGs) for accurately estimating the QTc interval and ruling out prolongation of the QTc interval. METHODS: The authors identified patients with a 12-lead ECG in AF within 10 days of a sinus ECG, with similar (±10 ms) QRS durations, between October 23, 2001, and November 5, 2021. A multilayered deep CNN was implemented in TensorFlow 2.5 (Google) to predict the MUSE (GE Healthcare) software-generated sinus QTc value from an AF ECG waveform, demographic characteristics, and software-generated features. RESULTS: The study identified 6,432 patients (44% female) with an average age of 71 years. The CNN predicted sinus QTc values with a mean absolute error of 22.2 ms and root mean squared error of 30.6 ms, similar to the intrinsic variability of the sinus QTc interval. Approximately 84% and 97% of the model's predictions were contained within 1 SD (±30.6 ms) and 2 SD (±61.2 ms) from the sinus QTc interval. The model outperformed the AFQTc method, exhibiting narrower error ranges (mean absolute error comparison P < 0.0001). The model performed best for ruling out QTc prolongation (negative predictive value 0.82 male, 0.92 female; specificity 0.92 male, 0.97 female). CONCLUSIONS: A CNN model applied to AF ECGs accurately predicted the sinus QTc interval, outperforming current alternatives and exhibiting a high negative predictive value.

Comparison of combined substrate-based mapping techniques to identify critical sites for ventricular tachycardia ablation.

BACKGROUND: Established electroanatomic mapping techniques for substrate mapping for ventricular tachycardia (VT) ablation includes voltage mapping, isochronal late activation mapping (ILAM), and fractionation mapping. Omnipolar mapping (Abbott Medical, Inc.) is a novel optimized bipolar electrogram creation technique with integrated local conduction velocity annotation. The relative utilities of these mapping techniques are unknown. OBJECTIVE: The purpose of this study was to evaluate the relative utility of various substrate mapping techniques for the identification of critical sites for VT ablation. METHODS: Electroanatomic substrate maps were created and retrospectively analyzed in 27 patients in whom 33 VT critical sites were identified. RESULTS: Both abnormal bipolar voltage and omnipolar voltage encompassed all critical sites and were observed over a median of 66 cm2 (interquartile range [IQR] 41.3-86 cm2) and 52 cm2 (IQR 37.7-65.5 cm2), respectively. ILAM deceleration zones were observed over a median of 9 cm2 (IQR 5.0-11.1 cm2) and encompassed 22 critical sites (67%), while abnormal omnipolar conduction velocity (CV <1 mm/ms) was observed over 10 cm2 (IQR 5.3-16.6 cm2) and identified 22 critical sites (67%), and fractionation mapping was observed over a median of 4 cm2 (IQR 1.5-7.6 cm2) and encompassed 20 critical sites (61%). The mapping yield was the highest for fractionation + CV (2.1 critical sites/cm2) and least for bipolar voltage mapping (0.5 critical sites/cm2). CV identified 100% of critical sites in areas with a local point density of >50 points/cm2. CONCLUSION: ILAM, fractionation, and CV mapping each identified distinct critical sites and provided a smaller area of interest than did voltage mapping alone. The sensitivity of novel mapping modalities improved with greater local point density.

Catheter ablation of atrioventricular nodal reentrant tachycardia with an irrigated contact-force sensing radiofrequency ablation catheter.

INTRODUCTION: Radiofrequency ablation (RFA) slow pathway modification for catheter ablation of atrioventricular nodal reentrant tachycardia (AVNRT) is traditionally performed using a 4-mm nonirrigated (NI) RF ablation catheter. Slow pathway modification using irrigated, contact-force sensing (ICFS) RFA catheters has been described in case reports, but the outcomes have not been systematically evaluated. METHODS: Acute procedural outcomes of 200 consecutive patients undergoing slow pathway modification for AVNRT were analyzed. A 3.5-mm ICFS RFA catheter (ThermoCool SmartTouch STSF, Biosense Webster, Inc.) was utilized in 134 patients, and a 4-mm NI RFA catheter (EZ Steer, Biosense Webster, Inc.) was utilized in 66 patients. Electroanatomic maps were retrospectively analyzed in a blinded fashion to determine the proximity of ablation lesions to the His region. RESULTS: The baseline characteristics of patients in both groups were similar. Total RF time was significantly lower in the ICFS group compared to the NI group (5.53 ± 4.6 vs. 6.24 ± 4.9 min, p = 0.03). Median procedure time was similar in both groups (ICFS, 108.0 (87.5-131.5) min vs. NI, 100.0 (85.0-125.0) min; p = 0.2). Ablation was required in closer proximity to the His region in the NI group compared to the ICFS group (14.4 ± 5.9 vs. 16.7 ± 6.4 mm, respectively, p = 0.01). AVNRT was rendered noninducible in all patients, and there was no arrhythmia recurrence during follow-up in both groups. Catheter ablation was complicated by AV block in one patient in the NI group. CONCLUSION: Slow pathway modification for catheter ablation of AVNRT using an ICFS RFA catheter is feasible, safe, and may facilitate shorter duration ablation while avoiding ablation in close proximity to the His region.

Temporal trends in atrial fibrillation ablation procedures at an academic medical center: 2011-2021.

INTRODUCTION: Radiofrequency ablation technology for treating atrial fibrillation (AF) has evolved rapidly over the past decade. We investigated the impact of technological and procedural advances on procedure times and ablation outcomes at a major academic medical center over a 10-year period. METHODS: Clinical data was collected from patients who presented to NYU Langone Health between 2011 and 2021 for a first-time AF ablation. Time to redo AF ablation or direct current cardioversion (DCCV) for recurrent AF during a 3-year follow-up period was determined and correlated with ablation technology and practices, antiarrhythmic medications, and patient comorbid conditions. RESULTS: From 2011 to 2021, the cardiac electrophysiology lab adopted irrigated-contact force ablation catheters, high-power short duration ablation lesions, steady-pacing, jet ventilation, and eliminated stepwise linear ablation for AF ablation. During this time the number of first time AF ablations increased from 403 to 1074, the percentage of patients requiring repeat AF-related intervention within 3-years of the index procedure dropped from 22% to 14%, mean procedure time decreased from 271 ± 65 to 135 ± 36 min, and mean annual major adverse event rate remained constant at 1.1 ± 0.5%. Patient comorbid conditions increased during this time period and antiarrhythmic use was unchanged. CONCLUSION: Rates of redo-AF ablation or DCCV following an initial AF ablation at a single center decreased 36% over a 10-year period. Procedural and technological changes likely contributed to this improvement, despite increased AF related comorbidities.

Outcomes and atrial substrate analysis in patients with HIV undergoing atrial fibrillation ablation.

INTRODUCTION: Patients with HIV infection have increased risk of atrial fibrillation, but the pathophysiologic mechanisms and the utility of catheter ablation in this population are not well-studied. We aimed to characterize outcomes of atrial fibrillation ablation and left atrial substrate in patients with HIV. METHODS: The study was a retrospective propensity score-matched analysis of patients with and without HIV undergoing atrial fibrillation ablation. A search was performed in the electronic medical record for all patients with HIV who received initial atrial fibrillation ablation from 2011 to 2020. After calculating propensity scores for HIV, matching was performed with patients without HIV by using nearest-neighbor matching without replacement in a 1:2 ratio. The primary outcome was freedom from atrial arrhythmia and secondary outcomes were freedom from atrial fibrillation, freedom from atrial tachycardia, and freedom from repeat ablation, compared by log-rank analysis. The procedures of patients with HIV who underwent repeat ablation at our institution were further analyzed for etiology of recurrence. To further characterize the left atrial substrate, a subsequent case-control analysis was then performed for a set of randomly chosen 10 patients with HIV matched with 10 without HIV to compare minimum and maximum voltage at nine pre-specified regions of the left atrium. RESULTS: Twenty-seven patients with HIV were identified. All were prescribed antiretroviral therapy at time of ablation. These patients were matched with 54 patients without HIV by propensity score. 86.4% of patients with HIV and 76.9% of controls were free of atrial fibrillation or atrial tachycardia at 1 year (p = .509). Log-rank analysis showed no difference in freedom from atrial arrhythmia (p value .971), atrial fibrillation (p-value .346), atrial tachycardia (p value .306), or repeat ablation (p value .401) after initial atrial fibrillation ablation in patients with HIV compared to patients without HIV. In patients with HIV with recurrent atrial fibrillation, the majority had pulmonary vein reconnection (67%). There were no significant differences in minimum or maximum voltage at any of the nine left atrial regions between the matched patients with and without HIV. CONCLUSIONS: Ablation to treat atrial fibrillation in patients with HIV, but without overt AIDS is frequently successful therapy. The majority of patients with recurrence of atrial fibrillation had pulmonary vein reconnection, suggesting infrequent nonpulmonary vein substrate. In this population, the left atrial voltage in patients with HIV is similar to that of patients without HIV. These findings suggest that the pulmonary veins remain a critical component to the initiation and maintenance of atrial fibrillation in patients with HIV.

Sex differences in outcomes of transvenous lead extraction: insights from National Readmission Database.

BACKGROUND: With the growing use of implantable cardiac devices, the need for transvenous lead extraction has increased, which translates to increased procedural volumes. Sex differences in lead extraction outcomes are not well studied. OBJECTIVE: The present study aims at evaluating the impact of sex on outcomes of lead extraction. METHODS: We identified 71,754 patients who presented between 2016 and 2019 and underwent transvenous lead extraction. Their clinical data were retrospectively accrued from the National Readmission Database (NRD) using the corresponding diagnosis codes. We compared clinical outcomes between male and female patients. Odds ratios (ORs) for the primary and secondary outcomes were calculated, and multivariable regression analysis was utilized to adjust for confounding variables. RESULTS: Compared to male patients, female patients had higher in-hospital complications including pneumothorax (OR 1.26, 95% CI (1.07-1.4), P < 0.01), hemopericardium (OR 1.39, 95% CI (1.02-1.88), P = 0.036), injury to superior vena cava and innominate vein requiring repair (OR 1.88, 95% CI (1.14-3.1), P = 0.014; OR 3.4, 95% CI (1.8-6.5), P < 0.01), need for blood transfusion (OR 1.28, 95% CI (1.18-1.38), P < 0.01), and pericardiocentesis (OR 1.6, 95% CI (1.3-2), P < 0.01). Thirty-day readmission was also significantly higher in female patients (OR 1.09, 95% CI (1.02-1.17), P < 0.01). There was no significant difference regarding in-hospital mortality (OR 0.99, 95% CI (0.87-1.14), P = 0.95). CONCLUSION: In female patients, lead extraction is associated with worse clinical outcomes and higher 30-day readmission rate.