Noseworthy, Peter A.

Background: Many medications, electrolyte perturbations, and several diseases can prolong the QTc beyond its 99 th percentile value resulting in acquired QT prolongation (AQTP). In contrast, approximately 1 in 2,000 people have congenital long QT syndrome (LQTS) hallmarked by pathological QT prolongation. Recently, we developed an AI-ECG model to distinguish these two groups, however this model does not elucidate which ECG segments distinguish LQTS from AQTP. Methods: Using the cohort from our previous study, all patients with LQTS evaluated in the Mayo Clinic Genetic Heart Rhythm Clinic and controls were included. Next, every patient/control with ≥1 ECG above age- and sex-specific 99 th percentile for QTc was selected and matched at 1:100 ratio. Subsequently, 5 ML algorithms (logistic regression, Naïve Bayes, random forest, Gradient boosting and XGBoost) were trained using 52 features representing segments of the 12-lead ECG (e.g. wave peak times, amplitudes, areas under wave, duration; 52x12 features). Training and testing sets were spilt at 80:20 ratio and 5-fold cross validation was performed to prevent overfitting. Following analysis, the top 100 features were re-analyzed to refine results. Results: Among >1,600 patients with LQTS, 690 had ≥ 1 ECG with a QTc above the established threshold compared to 28,186 controls. Following age- and sex-matching and splitting, 22,410 (training), and 5,776 (testing) ECGs were used. Of the 5 ML algorithms, XGBoost demonstrated best performance (AUC 0.913, accuracy 0.836, sensitivity 0.857, specificity 0.835) to distinguish LQTS from AQTP. Following filtering for the top 100 features, performance of the algorithm remained high with AUC of 0.912 (accuracy 0.84, sensitivity 0.841, specificity 0.84). The features with the greatest impact on classification output included time from T wave onset to T wave peak (leads V1, V4, V4), QRS interval duration (leads V1, V3, V4, aVR), and amplitude at end of ST segment (aVF). Conclusions: Distinguishing monogenetically driven LQTS from multi-factorial AQTP is critical in clinical practice for proper management, mitigation of offending QT-prolonging factors, and treatment. Building on our previously developed AI-ECG-LQTS ‘mutation detector’, this model identifies some of the elements within the ‘black box’ that distinguish an ECG and QTc stemming from a patient with LQTS compared to a similar prolonged QTc value that is arising due to non-genetic, acquired QT-prolonging factors.

Background: AI-ECG is a cost-effective tool for left ventricular dysfunction (LVD) screening. However, its cost-effectiveness for other forms of structural heart disease (SHD) is unknown. While AI-ECG is inexpensive, a drawback is low positive predictive value (PPV), which leads to high costs from unnecessary follow-up tests. Therefore, strategies to improve the yield of AI-ECG-based screening are needed. Aim: To evaluate the cost savings of a stepwise approach to SHD screening with AI-ECG followed by POCUS compared to AI-ECG alone. Methods: 286 adult outpatients undergoing AI-ECG were selected at random. Participants received same-day POCUS and had a recent TTE (our gold standard for SHD). We evaluated four SHDs: aortic stenosis (AS), cardiac amyloidosis (CA), HCM, and LVD. The costs of AI-ECG ($75) and TTE ($1,305) were obtained from Healthcare Bluebook. The cost of POCUS ($100) was estimated independently. Cost savings were analyzed for simultaneous screening for all forms of SHD and screening for individual SHDs. Results: AI-ECG identified potential SHD in 125 patients, but only 39 were true positives by TTE (31% PPV). In AI-ECG positive patients, POCUS demonstrated findings of SHD in 52/125. Compared to TTE, this stepwise approach yielded 32 true positives and 20 false positives (62% PPV). The cost per patient diagnosed with SHD was $4,733 with AI-ECG alone but decreased to $3,182 with stepwise screening (33% cost savings). Screening for individual SHDs resulted in cost reduction from $18,724 to $6,315 (66% savings) for AS, $21,023 to $12,230 (42% savings) for CA, $9,883 to $6,175 (38% savings) for HCM, and $4,019 to $3,582 (11% savings) for LVD. Conclusions: Stepwise screening for SHD with AI-ECG followed by POCUS significantly reduces costs compared to AI-ECG alone. We also suggest a model for parallel screening for multiple SHDs, which is likely more cost-effective than screening for individual SHDs.

Background: Guidelines recommend shared decision-making (SDM) for patients with atrial fibrillation (AF) making decisions regarding anticoagulation for stroke prevention. Decision support tools (e.g., Decision Aids [DAs]) facilitate SDM. However, little research has compared the effectiveness of the two most common types of DAs: (1) encounter decision aid (EDA) and (2) pre-encounter patient decision aid (PDA). Our study assessed the comparative effectiveness of PDAs and EDAs on SDM during AF clinical encounters where stroke prevention strategies were discussed. Research Question: Do decision aids (PDA or EDA), alone or in combination, improve patients’ AF decision-making experience compared to usual care? Methods: A cluster randomized multi-center trial in patients with AF comparing usual care (no DA) vs. one DA (EDA or PDA) or both DAs. Clinicians and patients were randomized independently into 4 study arms. Clinicians were randomized to use or not use the EDA for all study visits, and patients were randomized to use or not use the PDA. Co-primary outcome domains were: (1) quality of SDM (2) patient knowledge, and (3) decisional conflict. Secondary outcomes included: (1) treatment choice, (2) treatment initiation, and (3) treatment persistence. Patient characteristics were assessed. We will present comparisons of the randomized DAs on the co-primary and secondary outcomes and subgroup analyses. Results: Between December 2020-July 2023, investigators in 6 U.S. healthcare systems enrolled 1117 patients (mean (M) age 69, 63% male, 89% White) and 107 clinicians. Compared to usual care (no DA, M=31.6), SDM was better in patients receiving PDA (M=35.4) and EDA (44.5) alone or together (M=43.7; p’s<0.001). Knowledge about AF was greatest for those receiving both DAs or the PDA alone (84% accurate responses for PDA and both vs 76% with no DA, p<0.001), followed closely by the EDA alone (82%, p=0.003). Finally, both DAs (M=19.5) and EDA alone (M=20.0) had better decisional conflict scores compared to usual care (M=25.8; p’s<0.001). We will present analyses that assess the impact of DAs on secondary outcomes and interactions with DA, patient, and clinical characteristics across each outcome. Conclusions: In one of the first randomized trials examining the comparative effectiveness of EDAs and PDAs on SDM in clinical medicine, both PDAs and EDAs improved shared decision-making, decisional conflict, and knowledge compared to patients receiving usual care.

Background: Left ventricular diastolic dysfunction (LVDD) predicts mortality in cardiac intensive care unit (CICU) patients. A novel artificial intelligence enhanced electrocardiogram (AIECG) algorithm can predict LVDD and mortality in general populations but has not been examined in the cardiac intensive care unit (CICU). We aim to assess if LVDD by AI-ECG is associated with in-hospital and one-year mortality in CICU patients. Methods: In this retrospective cohort study, we included consecutive unique adults admitted to the Mayo Clinic CICU from 2007 to 2018 with an admission AIECG, which AI assigned LVDD grade (0 to 3). Medial mitral E/e’ ratio >15 on transthoracic echocardiogram (TTE) defined elevated filling pressures. AIECG and TTE assessment of LVDD were used to assign patients to four groups based on TTE as gold standard: true and false negative, and true and false positive. In-hospital mortality was evaluated using multivariable logistic regression. One-year survival was evaluated using Kaplan-Meier curves and multivariable Cox proportional-hazards. Results: We included 11,868 patients (median age 69.5 years, 37.7% females); 48% had heart failure and 44% had acute coronary syndromes. AIECG LVDD grades were: grade 0 (normal), 33%; grade 1, 7%; grade 2, 39%; grade 3, 21%. In-hospital (adjusted OR) and one-year (adjusted HR) mortality increased in each higher AIECG LVDD grade (Figure A/B), before and after adjustment including TTE measurements. Patients with grade 2-3 LVDD by AIECG and medial mitral E/e’ ratio >15 by TTE (true positive) had the highest in-hospital (adjusted OR 2.5 [1.7-3.9]) and one-year (adjusted HR 1.9 [1.5-2.5]) mortality (Figure C/D), and mortality was elevated similarly in patients with either grade 2-3 LVDD by AIECG (false positive) or medial mitral E/e’ ratio >15 by TTE (false negative). Conclusions: The AIECG LVDD grade was strongly associated with in-hospital and one-year mortality in CICU patients, even after adjusting for clinical variables and TTE measurements. Patients with concordant AIECG and TTE for elevated filling pressures (true positive) were at highest risk.

Background: Etripamil nasal spray (NS) is a fast acting, self-administered calcium channel blocker in development for the termination of AV-nodal-dependent supraventricular tachycardia (SVT). Prior randomized, placebo-controlled and open-label studies have demonstrated favorable safety and efficacy of etripamil in converting paroxysmal supraventricular tachycardia (PSVT) to sinus rhythm (SR) self-administered without direct medical supervision. Research Question/Hypothesis: To assess patterns and annualized PSVT episode frequency among patients opting to self-administer acute treatment with etripamil. Methods: NODE-303 was an event-driven, multi-center, open-label Phase 3 study, conducted in North and South America to evaluate the safety and efficacy of etripamil in patients with documented PSVT over multiple episodes. Test dosing was not performed prior to at-home use. Enrolled patients, upon perceiving symptoms of PSVT: applied an ambulatory ECG monitor, performed a previously trained vagal maneuver and, if symptoms persisted, self-administered etripamil NS 70 mg. During the study, the protocol was amended to allow a repeat dose (70 mg) if symptoms persisted 10 min after the first dose. Each patient could self-treat up to 4 episodes. Results: Of 1,116 enrolled patients, 503 (45.1%) treated ≥1 perceived PSVT episode (safety population). Etripamil achieved conversion to SR in 60% of patients by 30 minutes and 70% by 60 minutes. A total of 220, 118, 62, and 103 patients completed the study with 1, 2, 3, and 4 etripamil-treated perceived episodes of PSVT, respectively, with an average time on study of 440 days. Among these patients, the average number of annualized etripamil-treated PSVT episodes was 3.2 (standard deviation 3.8). Annualized use: etripamil was self-administered for 0-2 PSVT episodes per year, 2-6 episodes, 6-12 episodes, and >12 episodes, in 54%, 32%, 10%, and 4% of patients, respectively (Figure). Conclusions: This analysis aimed to assess the annualized use of etripamil NS in a real-world setting, by analyzing how often patients would self-administer the drug for PSVT episodes. Of patients that self-administered etripamil (n=503), the majority treated >1 episode and the annualized frequency of episodes treated with etripamil was 3.2 episodes/yr.

AbstractIntroductionLittle is known regarding the prevalence and prognostic implications of non‐sustained ventricular tachycardia (NSVT) in patients with wild‐type transthyretin cardiac amyloidosis (ATTRwt‐CA). We aimed to investigate the prevalence of NSVT in patients with ATTRwr‐CA, and the association of NSVT with sustained ventricular arrhythmias (VA) and all‐cause mortality.MethodsIn a cohort of ATTRwt‐CA patients from 2011 to 2022 without prior sustained VA, we ascertained the presence and characteristics of NSVT during clinically indicated ambulatory Holter monitoring. Patients were stratified based on the presence of NSVT at baseline. The primary and secondary endpoints of sustained VA and all‐cause mortality, respectively, were assessed during follow‐up.ResultsThe cohort included 217 patients with ATTRwt‐CA (95% males, median age 75 years; median NYHA class 2). Baseline Holter monitoring demonstrated NSVT in 116 (53%) patients. During a median follow‐up of 27 months (IQR 16–45) after the index Holter monitor, 11 (5.1%) patients reached the primary endpoint of sustained VA (incidence 1.8 per 100 person‐years, all monomorphic VT), and 46 (21%) patients died. In univariable Cox proportional hazard model, NYHA class 3 or 4 heart failure (p = .048), the presence of NSVT (p = .04), the duration of longest NSVT run (p = .029), and the percentage of ventricular ectopy (p < .001) were associated with the primary outcome. When adjusting for age and NYHA class 3 or 4 heart failure, the presence of NSVT remained associated with the primary outcome (p = .03). All‐cause mortality was not significantly different between patients with and without NSVT. A cutoff for ventricular ectopy burden of 0.5%, the median for all patients in this study, was associated with increased risk in sustained VA (log‐rank p = .004) and mortality (log‐rank p = .02).ConclusionNSVT is highly prevalent among ATTRwt‐CA patients undergoing clinically indicated Holter monitoring and may confer an increased risk of incident sustained VA.

Abstract Background Heart failure (HF) and atrial fibrillation (AF) are intertwined, sharing common risk factors and influencing each other in a reciprocal manner. While left ventricular diastolic dysfunction (LVDD) stands as a hallmark of HF's hemodynamic profile, its direct correlation with heightened AF risk remains uncertain. Our recent validation of an artificial intelligence-enabled electrocardiogram (AI-ECG) algorithm for LVDD detection has opened new avenues. Yet, whether AI-ECG-detected LVDD correlates with long-term AF risk remains unexplored. Methods We performed a retrospective study among all patients with a comprehensive LVDD assessment from the test population of the AI-ECG LVDD study between September 2001 and June 2022. Patients with prior documented AF according to health records or previous ECG were excluded. Patients were classified by AI-ECG as normal diastolic function (DF), grade 1 (G1), grade 2 (G2), or grade 3 (G3) LVDD. We assessed the risk of AF across AI-ECG LVDD grade, with normal DF as reference, with competing risk models. Results Of 97,023 patients free of AF at baseline, 63,533 (65.4%), 10,776 (11.1%), 18,940 (19.5%), and 3,774 (3.9%) were classified as normal DF, G1-LVDD, G2-LVDD, and G3-LVDD, respectively. Worse AI-ECG LVDD was associated with older age, lower left ventricular ejection fraction (LVEF), and higher rates of HF, diabetes, hypertension, chronic pulmonary disease, renal failure, and cardiovascular disease (p-of-trend&lt;0.001 for all). Over a median follow-up of 4.8 years (interquartile range 1.8-9.2 years), new-onset AF occurred in 6,795 (7.0%) patients. In multivariable survival analysis, adjusted to multiple risk factors including LVEF and clinical HF, G2 and G3 LVDD, representing patients with high filling pressures, were independently associated with a higher AF-risk [G2-LVDD: adjusted hazard ratio (aHR) 1.64 (95% confidence interval (95%CI) 1.52-1.73), G3-LVDD: aHR 2.24 (95%CI 2.02-2.48)]. Conclusion The AI-ECG LVDD algorithm independently predicts long-term AF risk, regardless of LVEF and clinical HF status, highlighting its potential for identifying high-risk populations and guiding proactive monitoring and management.

Abstract Background Etripamil nasal spray (NS) is a fast-acting, self-administered calcium-channel blocker in development for the conversion of AV-nodal dependent paroxysmal supraventricular tachycardia (PSVT) in a medically unsupervised setting. Prior studies show favorable safety and efficacy in converting single episodes of PSVT to sinus rhythm (SR). Purpose In NODE-303, patient-reported outcome (PRO) instruments assessed quality of life (QoL) over multiple etripamil-treated episodes of PSVT. Methods NODE-303 was an event-driven, multi-center, open-label Phase 3 study in North and South American patients with documented PSVT that evaluated the safety and efficacy of etripamil in PSVT termination, over multiple episodes and without the need for prior test dosing. Enrolled patients who perceived PSVT symptoms applied an ambulatory ECG cardiac monitoring system (CMS), performed a pre-trained vagal maneuver and, if symptoms persisted, self-administered etripamil NS 70 mg. A study amendment allowed a repeat dose (etripamil NS, 70 mg) if symptoms persisted 10 min after the first dose. Each patient could self-treat up to 4 episodes. Safety was assessed through adverse events, clinical data, and ECG CMS recordings. The Treatment Satisfaction Questionnaire for Medication (TSQM; validated for acute episodic assessments) and other PROs were administered, and healthcare utilization data were acquired. Patients completed PROs at baseline (BL), monthly, and per PSVT episode, which collected information on symptoms, episode characteristics, rescue medications, and emergency room visits. Additional PROs were the Brief Illness Perception Questionnaire (BIPQ), Cardiac Anxiety Questionnaire (CAQ), and 36-Item Short Form Health Survey (SF-36). Results There were higher proportions of patients reporting mild, minimal or no disease severity, every 6 months, than at BL; extremely severe, severe, and moderate disease severity was reported by smaller proportions of patients than at BL, though incomplete surveys at later visits may limit this analysis. Anxiety and stress about future PSVT episodes were consistently reduced from BL. Measures of treatment satisfaction, effectiveness, and convenience were consistent across multiple episodes, and were at levels considered favorable for the TSQM instrument (Table 1). Rates of emergency-room visits and hospital admissions across multiple, treated PSVT episodes were similar to those observed in trials assessing single episodes (Table 2). The BIPQ, CAQ or SF-36 had no notable changes from BL. Conclusions Etripamil self-administration was associated with patient-reported improvements in degree of disease severity, decreased anxiety and stress over future PSVT episodes, and levels of treatment satisfaction, effectiveness, and convenience considered favorable for respective PRO instrument. Using a symptom-prompted, self-administered treatment for PSVT could potentially improve QoL measures and reduce healthcare resource utilization.

Abstract Background The determination of left ventricular diastolic dysfunction (LVDD) and filling pressure in patients with significant (&gt;moderate) mitral regurgitation (MR) poses a complex challenge. We recently validated an artificial intelligence-enabled electrocardiogram (AI-ECG) algorithm to detect LVDD and estimate LV filling pressures. Methods This retrospective study sought to examine the risk of all-cause mortality across AI-ECG LVDD grades. Patients from the AI-ECG LVDD study test cohort who underwent transthoracic echocardiography confirming significant MR and an ECG within fourteen days of each other at Mayo Clinic between 09/2001 and 06/2022 were included. LVDD status was determined based on the index ECG, and patients were categorized into groups representing normal diastolic function (NDF) or LVDD grades 1 (G1), 2 (G2), or 3 (G3). Results Of 4,019 patients with significant MR (mean age 69.8, 49.0% women), 1,175 (29.2%), 1,881 (46.8%), and 963 (24.0%) were classified by AI-ECG as NDF/G1-LVDD, G2-LVDD, and G3-LVDD, respectively. The median mitral effective regurgitant orifice area was 26 mm² (interquartile range 20-36 mm²). Over a median follow-up of 3.5 years, 1,636 (40.7%) patients died. In multivariable survival analysis adjusted for multiple risk factors, a worse AI-ECG LVDD grade was independently associated with an increased death risk [G2DD: adjusted hazard ratio (aHR) 1.98 (95% confidence interval (95% CI) 1.63-2.40), G3DD: aHR 2.59 (95% CI 2.09-3.20)]. These findings were consistent when accounting for mitral valve intervention and among patients with &gt;moderate MR or after mitral valve intervention. Conclusion In patients with significant MR, the grading of LVDD by AI-ECG is independently associated with all-cause mortality.