Impact of artificial intelligence arrhythmia mapping on time to first ablation, procedure duration, and fluoroscopy use.

INTRODUCTION: Artificial intelligence (AI) ECG arrhythmia mapping provides arrhythmia source localization using 12-lead ECG data; whether this information impacts procedural efficiency is unknown. We performed a retrospective, case-control study to evaluate the hypothesis that AI ECG mapping may reduce time to ablation, procedural duration, and fluoroscopy. MATERIALS AND METHODS: Cases in which system output was used were retrospectively enrolled according to IRB-approved protocols at each site. Matched control cases were enrolled in reverse chronological order beginning on the last day for which the technology was unavailable. Controls were matched based upon physician, institution, arrhythmia, and a predetermined complexity rating. Procedural metrics, fluoroscopy data, and clinical outcomes were assessed from time-stamped medical records. RESULTS: The study group consisted of 28 patients (age 65 ± 11 years, 46% female, left atrial dimension 4.1 ± 0.9 cm, LVEF 50 ± 18%) and was similar to 28 controls. The most common arrhythmia types were atrial fibrillation (n = 10), premature ventricular complexes (n = 8), and ventricular tachycardia (n = 6). Use of the system was associated with a 19.0% reduction in time to ablation (133 ± 48 vs. 165 ± 49 min, p = 0.02), a 22.6% reduction in procedure duration (233 ± 51 vs. 301 ± 83 min, p < 0.001), and a 43.7% reduction in fluoroscopy (18.7 ± 13.3 vs. 33.2 ± 18.0 min, p < 0.001) versus controls. At 6 months follow-up, arrhythmia-free survival was 73.5% in the study group and 63.3% in the control group (p = 0.56). CONCLUSION: Use of forward-solution AI ECG mapping is associated with reductions in time to first ablation, procedure duration, and fluoroscopy without an adverse impact on procedure outcomes or complications.

Characterizing cardiac contractile motion for noninvasive radioablation of ventricular tachycardia.

Background: Respiratory motion management strategies are used to minimize the effects of breathing on the precision of stereotactic ablative radiotherapy for ventricular tachycardia, but the extent of cardiac contractile motion of the human heart has not been systematically explored. Objective: We aim to assess the magnitude of cardiac contractile motion between different directions and locations in the heart. Methods: Patients with intracardiac leads or valves who underwent 4-dimensional cardiac computed tomography (CT) prior to a catheter ablation procedure for atrial or ventricular arrhythmias at 2 medical centers were studied retrospectively. The displacement of transvenous right atrial appendage, right ventricular (RV) implantable cardioverter-defibrillator, coronary sinus lead tips, and prosthetic cardiac devices across the cardiac cycle were measured in orthogonal 3-dimensional views on a maximal-intensity projection CT reconstruction. Results: A total of 31 preablation cardiac 4-dimensional cardiac CT scans were analyzed. The LV lead tip had significantly greater motion compared with the RV lead in the anterior-posterior direction (6.0 ± 2.2 mm vs 3.8 ± 1.7 mm; P = .01) and superior-inferior direction (4.4 ± 2.9 mm vs 3.5 ± 2.0 mm; P = .049). The prosthetic aortic valves had the least movement of all fiducials, specifically compared with the RV lead tip in the left-right direction (3.2 ± 1.2 mm vs 6.1 ± 3.8 mm, P = .04) and the LV lead tip in the anterior-posterior direction (3.8 ± 1.7 mm vs 6.0 ± 2.2 mm, P = .03). Conclusion: The degree of cardiac contractile motion varies significantly (1 mm to 15.2 mm) across different locations in the heart. The effect of contractile motion on the precision of radiotherapy should be assessed on a patient-specific basis.

Pulsed field ablation versus thermal energy ablation for atrial fibrillation: a systematic review and meta-analysis of procedural efficiency, safety, and efficacy.

BACKGROUND: Pulsed field ablation (PFA) induces cell death through electroporation using ultrarapid electrical pulses. We sought to compare the procedural efficiency characteristics, safety, and efficacy of ablation of atrial fibrillation (AF) using PFA compared with thermal energy ablation. METHODS: We performed an extensive literature search and systematic review of studies that compared ablation of AF with PFA versus thermal energy sources. Risk ratio (RR) 95% confidence intervals (CI) were measured for dichotomous variables and mean difference (MD) 95% CI were measured for continuous variables, where RR < 1 and MD < 0 favor the PFA group. RESULTS: We included 6 comparative studies for a total of 1012 patients who underwent ablation of AF: 43.6% with PFA (n = 441) and 56.4% (n = 571) with thermal energy sources. There were significantly shorter procedures times with PFA despite a protocolized 20-min dwell time (MD - 21.95, 95% CI - 33.77, - 10.14, p = 0.0003), but with significantly longer fluroscopy time (MD 5.71, 95% CI 1.13, 10.30, p = 0.01). There were no statistically significant differences in periprocedural complications (RR 1.20, 95% CI 0.59-2.44) or recurrence of atrial tachyarrhythmias (RR 0.64, 95% CI 0.31, 1.34) between the PFA and thermal ablation cohorts. CONCLUSIONS: Based on the results of this meta-analysis, PFA was associated with shorter procedural times and longer fluoroscopy times, but no difference in periprocedural complications or rates of recurrent AF when compared to ablation with thermal energy sources. However, larger randomized control trials are needed.

Safety and acute efficacy of catheter ablation for atrial fibrillation with pulsed field ablation vs thermal energy ablation: A meta-analysis of single proportions.

Background: Pulsed field ablation (PFA) has emerged as a novel energy source for the ablation of atrial fibrillation (AF) using ultrarapid electrical pulses to induce cell death via electroporation. Objective: The purpose of this study was to compare the safety and acute efficacy of ablation for AF with PFA vs thermal energy sources. Methods: We performed an extensive literature search and systematic review of studies that evaluated the safety and efficacy of ablation for AF with PFA and compared them to landmark clinical trials for ablation of AF with thermal energy sources. Freeman-Tukey double arcsine transformation was used to establish variance of raw proportions followed by the inverse with the random-effects model to combine the transformed proportions and generate the pooled prevalence and 95% confidence interval (CI). Results: We included 24 studies for a total of 5203 patients who underwent AF ablation. Among these patients, 54.6% (n = 2842) underwent PFA and 45.4% (n = 2361) underwent thermal ablation. There were significantly fewer periprocedural complications in the PFA group (2.05%; 95% CI 0.94-3.46) compared to the thermal ablation group (7.75%; 95% CI 5.40-10.47) (P = .001). When comparing AF recurrence up to 1 year, there was a statistically insignificant trend toward a lower prevalence of recurrence in the PFA group (14.24%; 95% CI 6.97-23.35) compared to the thermal ablation group (25.98%; 95% CI 15.75-37.68) (P = .132). Conclusion: Based on the results of this meta-analysis, PFA was associated with lower rates of periprocedural complications and similar rates of acute procedural success and recurrent AF with up to 1 year of follow-up compared to ablation with thermal energy sources.

Safety and efficacy of catheter ablation of atrial fibrillation in the very elderly (≥80 years old): Insights from the UC San Diego AF Ablation Registry.

BACKGROUND: Catheter ablation improves outcomes in symptomatic atrial fibrillation (AF) patients. However, its safety and efficacy in the very elderly (≥80 years old) is not well described. HYPOTHESIS: Ablation of AF in the very elderly is safe and effective. METHODS: We performed a retrospective study of all patients who underwent catheter ablation enrolled in the University of California, San Diego AF Ablation Registry. The primary outcome was freedom from atrial arrhythmias on or off antiarrhythmic drugs (AADs). RESULTS: Of 847 patients, 42 (5.0%) were 80 years of age or greater with a median age of 81.5 (80-82.3) and 805 (95.0%) were less than 80 years of age with a median age of 64.4 (57.6-70.2). Among those who were ≥80 years old, 29 were undergoing de novo ablation (69.0%), whereas in the younger cohort, 518 (64.5%) were undergoing de novo ablation (p = .548). There were no statistically significant differences in fluoroscopy (p = .406) or total procedure times (p = .076), AAD use (p = .611), or procedural complications (p = .500) between groups. After multivariable adjustment, there were no statistically significant differences in recurrence of any atrial arrhythmias on or off AAD (adjusted hazard ratio [AHR]: 0.75; 95% confidence interval [CI]: 0.45-1.23; p = .252), all-cause hospitalizations (AHR: 0.86; 95% CI: 0.46-1.60; p = .626), or all-cause mortality (AHR: 4.48; 95% CI: 0.59-34.07; p = .147) between the very elderly and the younger cohort. CONCLUSION: In this registry analysis, catheter ablation of AF appears similarly effective and safe in patients 80 years or older when compared to a younger cohort.

Successful Noninvasive 12-Lead ECG Mapping-Guided Radiotherapy of Inaccessible Ventricular Tachycardia Substrate Due to Mechanical Valves.

In patients presenting with refractory ventricular tachycardia (VT) and aortic and mitral mechanical prosthetic valves, traditional catheter ablation is challenging. We describe a case in which a novel noninvasive computational electrocardiogram mapping algorithm localized VT sources originating from substrate near the mechanical valves, in which stereotactic ablative radiotherapy eliminated VT in 1.5-year follow-up. (Level of Difficulty: Advanced.).

Association of isoproterenol infusion during catheter ablation of atrial fibrillation with outcomes: insights from the UC San Diego AF Ablation Registry.

BACKGROUND: High-dose isoproterenol infusion is a useful provocative maneuver to elicit triggers of atrial fibrillation (AF) during ablation. We evaluated whether the use of isoproterenol infusion to elicit triggers of AF after ablation is associated with differential outcomes. METHODS: We performed a retrospective study of all patients who underwent de novo radiofrequency catheter ablation of AF enrolled in the University of California, San Diego AF Ablation Registry. The primary outcome was freedom from atrial arrhythmias on or off antiarrhythmic drugs (AAD). RESULTS: Of 314 patients undergoing AF ablation, 235 (74.8%) received isoproterenol while 79 (25.2%) did not. Among those who received isoproterenol, 11 (4.7%) had additional triggers identified. There were no statistically significant differences in procedure time (p = 0.432), antiarrhythmic drug use (p = 0.289), procedural complications (p = 0.279), recurrences of atrial arrhythmias on or off AAD [adjusted hazard ratio (AHR) 0.92 (95% CI 0.58-1.46); p = 0.714], all-cause hospitalizations [AHR 1.00 (95% CI 0.60-1.67); p = 0.986], or all-cause mortality [AHR 0.14 (95% CI 0.01-3.52); p = 0.229] between groups. CONCLUSIONS: In this registry analysis, use of isoproterenol is safe but was not associated with a reduction in recurrence of atrial arrhythmias.

Stochastic termination of spiral wave dynamics in cardiac tissue.

Rotating spiral waves are self-organized features in spatially extended excitable media and may play an important role in cardiac arrhythmias including atrial fibrillation (AF). In homogeneous media, spiral wave dynamics are perpetuated through spiral wave breakup, leading to the continuous birth and death of spiral waves, but have a finite probability of termination. In non-homogeneous media, however, heterogeneities can act as anchoring sources that result in sustained spiral wave activity. It is thus unclear how and if AF may terminate following the removal of putative spiral wave sources in patients. Here, we address this question using computer simulations in which a stable spiral wave is trapped by an heterogeneity and is surrounded by spiral wave breakup. We show that, following ablation of spatial heterogeneity to render that region of the medium unexcitable, termination of spiral wave dynamics is stochastic and Poisson-distributed. Furthermore, we show that the dynamics can be accurately described by a master equation using birth and death rates. To validate these predictions in vivo, we mapped spiral wave activity in patients with AF and targeted the locations of spiral wave sources using radiofrequency ablation. Targeted ablation was indeed able to terminate AF, but only after a variable delay of up to several minutes. Furthermore, and consistent with numerical simulations, termination was not accompanied by gradual temporal or spatial organization. Our results suggest that spiral wave sources and tissue heterogeneities play a critical role in the maintenance of AF and that the removal of sources results in spiral wave dynamics with a finite termination time, which could have important clinical implications.

Forward-Solution Noninvasive Computational Arrhythmia Mapping: The VMAP Study.

BACKGROUND: The accuracy of noninvasive arrhythmia source localization using a forward-solution computational mapping system has not yet been evaluated in blinded, multicenter analysis. This study tested the hypothesis that a computational mapping system incorporating a comprehensive arrhythmia simulation library would provide accurate localization of the site-of-origin for atrial and ventricular arrhythmias and pacing using 12-lead ECG data when compared with the gold standard of invasive electrophysiology study and ablation. METHODS: The VMAP study (Vectorcardiographic Mapping of Arrhythmogenic Probability) was a blinded, multicenter evaluation with final data analysis performed by an independent core laboratory. Eligible episodes included atrial and ventricular: tachycardia, fibrillation, pacing, premature atrial and ventricular complexes, and orthodromic atrioventricular reentrant tachycardia. Mapping system results were compared with the gold standard site of successful ablation or pacing during electrophysiology study and ablation. Mapping time was assessed from time-stamped logs. Prespecified performance goals were used for statistical comparisons. RESULTS: A total of 255 episodes from 225 patients were enrolled from 4 centers. Regional accuracy for ventricular tachycardia and premature ventricular complexes in patients without significant structural heart disease (n=75, primary end point) was 98.7% (95% CI, 96.0%-100%; P<0.001 to reject predefined H0 <0.80). Regional accuracy for all episodes (secondary end point 1) was 96.9% (95% CI, 94.7%-99.0%; P<0.001 to reject predefined H0 <0.75). Accuracy for the exact or neighboring segment for all episodes (secondary end point 2) was 97.3% (95% CI, 95.2%-99.3%; P<0.001 to reject predefined H0 <0.70). Median spatial accuracy was 15 mm (n=255, interquartile range, 7-25 mm). The mapping process was completed in a median of 0.8 minutes (interquartile range, 0.4-1.4 minutes). CONCLUSIONS: Computational ECG mapping using a forward-solution approach exceeded prespecified accuracy goals for arrhythmia and pacing localization. Spatial accuracy analysis demonstrated clinically actionable results. This rapid, noninvasive mapping technology may facilitate catheter-based and noninvasive targeted arrhythmia therapies. REGISTRATION: URL: https://www. CLINICALTRIALS: gov; Unique identifier: NCT04559061.

Characteristics and outcomes of recurrent atrial fibrillation after prior failed pulmonary vein isolation.

BACKGROUND: The mechanisms for atrial fibrillation (AF) recurrence after pulmonary vein isolation (PVI) catheter ablation are unclear. Non-PV organized atrial arrhythmias (PAC, AT, macro-reentrant AFL) are possible contributors; however the prevalence and effect of their ablation on recurrent AF are unknown. We hypothesize that the identification and ablation of non-PV organized atrial arrhythmias were associated with less AF recurrence. METHODS: Patients who underwent repeat ablation for recurrent AF after prior PVI were retrospectively enrolled. The prevalence and characteristics of PV reconnections and non-PV organized atrial arrhythmias were identified. The outcomes of time to clinical AF recurrence, heart failure (HF) hospitalization, and mortality were analyzed in patients using multivariable adjusted Cox regression. RESULTS: In 74 patients with recurrent AF (age 66 ± 9 years, left atrial volume index 38 ± 10 ml/m2, 59% persistent AF), PV reconnections were found in 46 patients (61%), macro-reentrant atrial flutter in 27 patients (36%), and focal tachycardia in 12 patients (16%). Mapping and ablation of non-PV organized atrial arrhythmias were associated with a reduced recurrence of late clinical AF (adjusted HR 0.26, CI 0.08-0.85, p = 0.03) and the composite outcome of recurrence of late AF, HF hospitalization, and mortality (adjusted HR 0.38, CI 0.17-0.85, p = 0.02), with median follow-up of 1.6 (IQR 0.7-6.3) years. The presence of PV reconnections or empiric linear ablation was not associated with reduction in clinical AF or composite endpoints. CONCLUSION: The ablation of non-PV organized atrial arrhythmias resulted in a reduction of late clinical AF recurrence and composite outcome. In this challenging population, alternate mechanisms beyond PV reconnections need to be considered. Prospective studies are needed.

Association between early recurrences of atrial tachyarrhythmias and long-term outcomes in patients after repeat atrial fibrillation ablation.

PURPOSE: Early recurrence of atrial tachyarrhythmia (ER) is predictive of late recurrence of atrial tachyarrhythmia (LR) after first-time atrial fibrillation (AF) ablation, but the association in patients undergoing repeat AF ablation is unknown. We aim to determine the incidence and prognostic significance of ER after repeat ablation. METHODS: A total of 259 consecutive patients (mean age 64 years, 75.3% male) undergoing repeat AF ablation with complete follow-up data were included at a single institution from 2010 to 2015. ER and LR were defined as atrial tachyarrhythmia (AF, atrial flutter or atrial tachycardia) > 30 s within the 3-month blanking period (BP) and after the 3-month BP, respectively. RESULTS: ER occurred in 79/259 (30.5%), and LR occurred in 138/259 (53%) at a median follow-up of 1221 (IQR: 523-1712) days. Four-year freedom from LR was 22% and 56% in patients with and without ER, respectively (p < 0.001). After multivariate adjustment, ER was strongly associated with LR, cardioversion post BP, and repeat ablation, but not associated with hospitalization. Compared to those with no ER, there was a higher risk of LR when ER occurred within the first month of the BP [month 1: hazard ratio (HR) 2.32, confidence interval (CI) 1.57-3.74, p < 0.001; month 2: HR 2.01, CI 1.13-3.83, p = 0.02; month 3: HR 1.46, CI 0.5-3.36, p = 0.37], however the prediction of LR based on timing within the BP was poor (area under curve 0.64). CONCLUSION: Following repeat AF ablation, ER is strongly associated with LR, cardioversion post BP, and repeat ablation.

Ablation of mitral annular flutter ablation utilizing a left atrial anterior line versus a lateral mitral isthmus line: a systematic review and meta-analysis.

PURPOSE: Mitral annular flutter (MAF) is a common arrhythmia after atrial fibrillation ablation. We sought to compare the efficacy and safety of catheter ablation utilizing either a left atrial anterior wall (LAAW) line or a lateral mitral isthmus (LMI) line. METHODS: We performed a systematic review for all studies that compared LAAW versus LMI lines. Risk ratio (RR) and mean difference (MD) 95% confidence intervals were measured for dichotomous and continuous variables, respectively. RESULTS: Four studies with a total of 594 patients were included, one of which was a randomized control trial. In the LMI ablation group, 40% of patients required CS ablation. There were no significant differences in bidirectional block (RR 1.26; 95% CI, 0.94-1.69) or ablation time (MD -1.5; 95% CI, -6.11-3.11), but LAAW ablation was associated with longer ablation line length (MD 11.42; 95% CI, 10.69-12.14) and longer LAA activation delay (MD 67.68; 95% CI, 33.47-101.89.14) when compared to LMI. There was no significant difference in pericardial effusions (RR 0.36; 95% CI, 0.39-20.75) between groups and more patients were maintained sinus rhythm (RR 1.19; 95% CI, 1.03-1.37, p = 0.02) who underwent LAAW compared to LMI. CONCLUSION: Ablation of mitral annular flutter with a LAAW line compared to a LMI line showed no difference in rates of acute bidirectional block, ablation time, or pericardial effusion. However, LAAW ablation required a longer ablation line length, resulted in greater LAA activation delayed and was associated with more sinus rhythm maintenance, with the added advantage of avoiding ablation in the CS.

Computational ECG mapping and respiratory gating to optimize stereotactic ablative radiotherapy workflow for refractory ventricular tachycardia.

BACKGROUND: Stereotactic ablative radiotherapy (SAbR) is an emerging therapy for refractory ventricular tachycardia (VT). However, the current workflow is complicated, and the precision and safety in patients with significant cardiorespiratory motion and VT targets near the stomach may be suboptimal. OBJECTIVE: We hypothesized that automated 12-lead electrocardiogram (ECG) mapping and respiratory-gated therapy may improve the ease and precision of SAbR planning and facilitate safe radiation delivery in patients with refractory VT. METHODS: Consecutive patients with refractory VT were studied at 2 hospitals. VT exit sites were localized using a 3-D computational ECG algorithm noninvasively and compared to available prior invasive mapping. Radiotherapy (25 Gy) was delivered at end-expiration when cardiac respiratory motion was ≥0.6 cm or targets were ≤2 cm from the stomach. RESULTS: In 6 patients (ejection fraction 29% ± 13%), 4.2 ± 2.3 VT morphologies per patient were mapped. Overall, 7 out of 7 computational ECG mappings (100%) colocalized to the identical cardiac segment when prior invasive electrophysiology study was available. Respiratory gating was associated with smaller planning target volumes compared to nongated volumes (71 ± 7 vs 153 ± 35 cc, P < .01). In 2 patients with inferior wall VT targets close to the stomach (6 mm proximity) or significant respiratory motion (22 mm excursion), no GI complications were observed at 9- and 12-month follow-up. Implantable cardioverter-defibrillator shocks decreased from 23 ± 12 shocks/patient to 0.67 ± 1.0 (P < .001) post-SAbR at 6.0 ± 4.9 months follow-up. CONCLUSIONS: A workflow including computational ECG mapping and protocol-guided respiratory gating is feasible, is safe, and may improve the ease of SAbR planning. Studies to validate this workflow in larger populations are required.

Association between specific antiarrhythmic drug prescription in the post-procedural blanking period and recurrent atrial arrhythmias after catheter ablation for atrial fibrillation.

PURPOSE: To evaluate if specific AADs prescribed in the blanking period (BP) after catheter ablation of atrial fibrillation (AF) may be associated with reduced risk of early recurrence (ER) and/or late recurrence (LR) of atrial arrhythmias. METHODS: A total of 478 patients undergoing first-time ablation at a single institution were included. Outcomes were: ER, LR, discontinuation of AAD less than 90 days post-ablation, and second ablation. ER was defined as AF, atrial flutter (AFL), or atrial tachycardia (AT) > 30 seconds within BP. LR was defined as AF/AFL/AT > 30 seconds after BP. RESULTS: Of 478 patients, 14.9% were prescribed no AAD, 26.4% propafenone/flecainide, 34.5% sotalol/dofetilide, 10.7% dronedarone, and 13.6% amiodarone. Patients prescribed amiodarone were more likely to have persistent AF, hypertension, diabetes, and other comorbidities. In unadjusted analyses, there were no differences between groups in relation to ER (log rank P = 0.171), discontinuation of AAD before ninety days post-ablation (log rank P = 0.235), or freedom from second ablation (log rank P = 0.147). After multivariable adjustment, patients prescribed amiodarone or dronedarone were more likely to experience LR than those prescribed no AAD [Adjusted Hazard Ratio (AHR) 1.83, 95% CI 1.10-3.04, p = 0.02; AHR 1.79, 95% CI 1.05-3.05, p = 0.03, respectively]. CONCLUSION: Following first-time catheter ablation, there were no differences between specific AAD prescription and risk of ER, while those prescribed amiodarone or dronedarone in the BP were more likely to experience LR than those prescribed no AAD, which may represent an association due to confounding by indication.

Electrical Substrate Ablation for Refractory Ventricular Fibrillation: Results of the AVATAR Study.

[Figure: see text].

Effect of closed loop stimulation versus accelerometer on outcomes with cardiac resynchronization therapy: the CLASS trial.

PURPOSE: Chronotropic incompetence (CI) in patients with heart failure is common and associated with impaired exercise intolerance and adverse outcomes. This study sought to determine the effects of closed loop stimulation (CLS) rate-adaptive pacing on functional capacity in patients with heart failure with reduced ejection fraction (HFrEF) and CI implanted with cardiac resynchronization therapy (CRT) devices. METHODS: A randomized, blinded, cross-over designed trial enrolled patients with HFrEF and CI implanted with a Biotronik CRT-D to complete a quality of life questionnaire, 6-min walk distance (6MWD), and cardiopulmonary exercise testing after two programmed periods: 1-week period of CLS and 1-week period of standard accelerometer (DDDR). RESULTS: Nine patients (6 males, mean age 71.4 years, 7 with New York Heart Association Class III, mean ejection fraction 39 ± 8%) were enrolled. Quality of life trended higher in CLS as compared to DDDR (550.8 ± 123.9 vs 489.3 ± 164.9, p = 0.06). There were no differences between CLS and DDDR in 6MWD (293.1 ± 90.2 m vs 315.1 ± 95.5 m, p = 0.52), peak heart rate (HR) 110.7 ± 14.7 bpm vs 109.7 bpm ± 14.1, p = 0.67), or peak VO2 (12.3 ± 4.9 ml/kg/min vs 12.9 ± 5.9, p = 0.47). As tests were submaximal as indicated by low respiratory exchange ratios (0.98 ± 0.11 vs 1.0 ± 0.8, p = 0.35), VE/VCO2 slope also showed no difference between CLS and DDDR (35.8 ± 5.6 vs 35.4 ± 5.7, p = 0.65). Five patients (56%) preferred CLS programming (p = 1.0). CONCLUSIONS: In patients with HFrEF and CI implanted with a CRT-D, peak HR, peak VO2, and 6MWD were equivalent, while there was a trend toward improved quality of life in CLS as compared to DDDR. CLINICAL TRIAL REGISTRATION: URL: https://www.clinicaltrials.gov . Unique identifier: NCT02693262.

Machine Learned Cellular Phenotypes in Cardiomyopathy Predict Sudden Death.

RATIONALE: Susceptibility to VT/VF (ventricular tachycardia/fibrillation) is difficult to predict in patients with ischemic cardiomyopathy either by clinical tools or by attempting to translate cellular mechanisms to the bedside. OBJECTIVE: To develop computational phenotypes of patients with ischemic cardiomyopathy, by training then interpreting machine learning of ventricular monophasic action potentials (MAPs) to reveal phenotypes that predict long-term outcomes. METHODS AND RESULTS: We recorded 5706 ventricular MAPs in 42 patients with coronary artery disease and left ventricular ejection fraction ≤40% during steady-state pacing. Patients were randomly allocated to independent training and testing cohorts in a 70:30 ratio, repeated K=10-fold. Support vector machines and convolutional neural networks were trained to 2 end points: (1) sustained VT/VF or (2) mortality at 3 years. Support vector machines provided superior classification. For patient-level predictions, we computed personalized MAP scores as the proportion of MAP beats predicting each end point. Patient-level predictions in independent test cohorts yielded c-statistics of 0.90 for sustained VT/VF (95% CI, 0.76-1.00) and 0.91 for mortality (95% CI, 0.83-1.00) and were the most significant multivariate predictors. Interpreting trained support vector machine revealed MAP morphologies that, using in silico modeling, revealed higher L-type calcium current or sodium-calcium exchanger as predominant phenotypes for VT/VF. CONCLUSIONS: Machine learning of action potential recordings in patients revealed novel phenotypes for long-term outcomes in ischemic cardiomyopathy. Such computational phenotypes provide an approach which may reveal cellular mechanisms for clinical outcomes and could be applied to other conditions.