AI-enabled detection of QRS fragmentation from 12-lead electrocardiogram and its clinical relevance for predicting malignant arrhythmia onset.

Background: Electrocardiographic markers differentiating between death caused by ventricular arrhythmias and non-arrhythmic death could improve the selection of patients for implantable cardioverter-defibrillator (ICD) implantation. QRS fragmentation (fQRS) is a parameter of interest, but subject to debate. We investigated the association of an automatically quantified probability of fragmentation with the outcome in ICD patients. Methods: From a single-center retrospective registry, all patients implanted with an ICD between January 1996 and December 2018 were eligible for inclusion. Patients with active pacing were excluded. From the electronical medical record, clinical characteristics at implantation were collected and a 12-lead ECG was exported and analyzed by a previously validated machine-learning algorithm to quantify the probability of fQRS. To compare fQRS(+) and fQRS(-) patients, dichotomization was performed using the Youden index. Patients with a high probability of fragmentation in any region (anterior, inferior or lateral), were labeled fQRS(+). The impact of this fQRS probability on outcomes was investigated using Cox regression. Results: A total of 1,242 patients with a mean age of 62.6 ± 11.5 years and a reduced left ventricular ejection fraction of 31 ± 12% were included of which 227 (18.3%) were female. The vast majority suffered from ischemic heart disease (64.3%) and were implanted in primary prevention (63.8%). 538 (43.3%) had a high probability of fragmentation in any region. Patients with a high probability of fragmentation had more frequently dilated cardiomyopathy (39.4% vs. 33.0%, p = 0.019), left bundle branch block (40.8% vs. 32.5%, p = 0.006) and a higher use of cardiac resynchronization therapy with defibrillator (CRT-D) devices (33.9% vs. 26.3%, p = 0.004). After adjustment in a multivariable Cox model, there was no significant association between the probability of global or regional fQRS and appropriate ICD therapy, inappropriate shock and short- or long-term mortality. Conclusion: There was no association between the automatically quantified probability of the presence of fQRS and outcome. This lack of predictive value might be due to the algorithm used, which identifies only the presence but not the severity of fragmentation.

Lateral QRS amplitude is independently associated with outcome after cardiac resynchronization therapy: Advancing patient selection?

BACKGROUND: Cardiac resynchronization therapy (CRT) is a cornerstone in the treatment of selected heart failure patients. However, a relevant proportion of patients do not show beneficial response. Identification of simple, additive, and outcome-relevant selection criteria may improve selection of patients. OBJECTIVE: We sought to determine whether baseline QRS amplitude is associated with outcome in CRT. METHODS: Quantification of intrinsic, pre-CRT implantation QRS amplitude was performed in an observational multinational 2-center retrospective cohort analysis (derivation cohort Zurich, n = 178, 2000-2015; validation cohort Leuven, n = 183, 1999-2016) with a composite end point of all-cause mortality, ventricular assist device implantation, or heart transplantation at 5 years. RESULTS: Higher baseline to peak amplitude in lateral leads (lead I and V6) was associated with a lower risk of reaching the composite end point (lead I: hazard ratio, 0.86 [95% confidence interval, 0.78-0.95] per millivolt, P = .002; lead V6: hazard ratio, 0.94 [95% confidence interval, 0.88-1.00] per millivolt, P = .043). Concordance index-based comparison of quartile, spline, and receiver operating characteristic curve analysis suggested cutoff values of 6 mV for lead I and 3 mV for V6 for optimal discrimination of outcome. External validation confirmed the cutoff of 3 mV in lead V6 as a highly significant discriminator of outcome (P < .001) associated with a risk reduction of 65%. CONCLUSION: Low QRS amplitude in lateral electrocardiogram leads is associated with higher risk of poor outcome in CRT patients. A cutoff of 3 mV in lead V6 proved highly discriminative. Further studies need to confirm the additive value of QRS amplitude in selection of patients for CRT and to assess whether CRT may be made available to more patients.

Determinants of global cardiac implantable electrical device remote monitoring utilization - Results from an international survey.

Background: Despite near-global availability of remote monitoring (RM) in patients with cardiac implantable electronic devices (CIED), there is a high geographical variability in the uptake and use of RM. The underlying reasons for this geographic disparity remain largely unknown. Objectives: To study the determinants of worldwide RM utilization and identify locoregional barriers of RM uptake. Methods: An international survey was administered to all CIED clinic personnel using the Heart Rhythm Society global network collecting demographic information, as well as information on the use of RM, the organization of the CIED clinic, and details on local reimbursement and clinic funding. The most complete response from each center was included in the current analysis. Stepwise forward multivariate linear regression was performed to identify determinants of the percentage of patients with a CIED on RM. Results: A total of 302 responses from 47 different countries were included, 61.3% by physicians and 62.3% from hospital-based CIED clinics. The median percentage of CIED patients on RM was 80% (interquartile range, 40-90). Predictors of RM use were gross national income per capita (0.76% per US$1000, 95% CI 0.72-1.00, P < .001), office-based clinics (7.48%, 95% CI 1.53-13.44, P = .014), and presence of clinic funding (per-patient payment model 7.90% [95% CI 0.63-15.17, P = .033); global budget 3.56% (95% CI -6.14 to 13.25, P = .471]). Conclusion: The high variability in RM utilization can partly be explained by economic and structural barriers that may warrant specific efforts by all stakeholders to increase RM utilization.

Arrhythmic Mitral Valve Prolapse Phenotype: An Unsupervised Machine Learning Analysis Using a Multicenter Cardiac MRI Registry.

Purpose To use unsupervised machine learning to identify phenotypic clusters with increased risk of arrhythmic mitral valve prolapse (MVP). Materials and Methods This retrospective study included patients with MVP without hemodynamically significant mitral regurgitation or left ventricular (LV) dysfunction undergoing late gadolinium enhancement (LGE) cardiac MRI between October 2007 and June 2020 in 15 European tertiary centers. The study end point was a composite of sustained ventricular tachycardia, (aborted) sudden cardiac death, or unexplained syncope. Unsupervised data-driven hierarchical k-mean algorithm was utilized to identify phenotypic clusters. The association between clusters and the study end point was assessed by Cox proportional hazards model. Results A total of 474 patients (mean age, 47 years ± 16 [SD]; 244 female, 230 male) with two phenotypic clusters were identified. Patients in cluster 2 (199 of 474, 42%) had more severe mitral valve degeneration (ie, bileaflet MVP and leaflet displacement), left and right heart chamber remodeling, and myocardial fibrosis as assessed with LGE cardiac MRI than those in cluster 1. Demographic and clinical features (ie, symptoms, arrhythmias at Holter monitoring) had negligible contribution in differentiating the two clusters. Compared with cluster 1, the risk of developing the study end point over a median follow-up of 39 months was significantly higher in cluster 2 patients (hazard ratio: 3.79 [95% CI: 1.19, 12.12], P = .02) after adjustment for LGE extent. Conclusion Among patients with MVP without significant mitral regurgitation or LV dysfunction, unsupervised machine learning enabled the identification of two phenotypic clusters with distinct arrhythmic outcomes based primarily on cardiac MRI features. These results encourage the use of in-depth imaging-based phenotyping for implementing arrhythmic risk prediction in MVP. Keywords: MR Imaging, Cardiac, Cardiac MRI, Mitral Valve Prolapse, Cluster Analysis, Ventricular Arrhythmia, Sudden Cardiac Death, Unsupervised Machine Learning Supplemental material is available for this article. © RSNA, 2024.

Serial Cardiac Magnetic Resonance Imaging in Patients with Mitral Valve Prolapse-A Single-Center Retrospective Registry.

Background: Mitral valve prolapse (MVP) and mitral annular disjunction (MAD) are common valvular abnormalities that have been associated with ventricular arrhythmias (VA). Cardiac magnetic resonance imaging (CMR) has a key role in risk stratification of VA, including assessment of late gadolinium enhancement (LGE). Methods: Single-center retrospective analysis of patients with MVP or MAD who had >1 CMR and >1 24 h Holter registration available. Data are presented in detail, including evolution of VA and presence of LGE over time. Results: A total of twelve patients had repeated CMR and Holter registrations available, of which in four (33%) patients, it was conducted before and after minimal invasive mitral valve repair (MVR). After a median of 4.7 years, four out of eight (50%) patients without surgical intervention had new areas of LGE. New LGE was observed in the papillary muscles and the mid to basal inferolateral wall. In four patients, presenting with syncope or high-risk non-sustained ventricular tachycardia (VT), programmed ventricular stimulation was performed and in two (50%), sustained monomorphic VT was easily inducible. In two patients who underwent MVR, new LGE was observed in the basal inferolateral wall of which one presented with an increased burden of VA. Conclusions: In patients with MVP and MAD, repeat CMR may show new LGE in a small subset of patients, even shortly after MVR. A subgroup of patients who presented with an increase in VA burden showed new LGE upon repeat CMR. VA in patients with MVP and MAD are part of a heterogeneous spectrum that requires further investigation to establish risk stratification strategies.

Landmark Evolutions in Time and Indication for Cardiac Resynchronization Therapy: Results from a Multicenter Retrospective Registry.

Background: Cardiac resynchronization therapy (CRT) has evolved into an established therapy for patients with chronic heart failure and a wide QRS complex. Data on long-term outcomes over time are scarce and the criteria for implantation remain a subject of investigation. Methods: An international, multicenter, retrospective registry includes 2275 patients who received CRT between 30 November 2000 and 31 December 2019, with a mean follow-up of 3.6 ± 2.7 years. Four time periods were defined, based on landmark trials and guidelines. The combined endpoint was a composite of all-cause mortality, heart transplantation, or left ventricular assist device implantation. Results: The composite endpoint occurred in 656 patients (29.2%). The mean annual implantation rate tripled from 31.5 ± 17.4/year in the first period to 107.4 ± 62.4/year in the last period. In the adjusted Cox regression analysis, the hazard ratio for the composite endpoint was not statistically different between time periods. When compared to sinus rhythm with left bundle branch block (LBBB), a non-LBBB conduction pattern (sinus rhythm: HR 1.51, 95% CI 1.12-2.03; atrial fibrillation: HR 2.08, 95% CI 1.30-3.33) and a QRS duration below 130 ms (HR 1.64, 95% CI 1.29-2.09) were associated with a higher hazard ratio. Conclusions: Despite innovations, an adjusted regression analysis revealed stable overall survival over time, which can at least partially be explained by a shift in patient characteristics.

Artificial intelligence electrocardiogram as a novel screening tool to detect a newly abnormal left ventricular ejection fraction after anthracycline-based cancer therapy.

AIMS: Cardiotoxicity is a serious side effect of anthracycline treatment, most commonly manifesting as a reduction in left ventricular ejection fraction (EF). Early recognition and treatment have been advocated, but robust, convenient, and cost-effective alternatives to cardiac imaging are missing. Recent developments in artificial intelligence (AI) techniques applied to electrocardiograms (ECGs) may fill this gap, but no study so far has demonstrated its merit for the detection of an abnormal EF after anthracycline therapy. METHODS AND RESULTS: Single centre consecutive cohort study of all breast cancer patients with ECG and transthoracic echocardiography (TTE) evaluation before and after (neo)adjuvant anthracycline chemotherapy. Patients with HER2-directed therapy, metastatic disease, second primary malignancy, or pre-existing cardiovascular disease were excluded from the analyses as were patients with EF decline for reasons other than anthracycline-induced cardiotoxicity. Primary readout was the diagnostic performance of AI-ECG by area under the curve (AUC) for EFs < 50%. Of 989 consecutive female breast cancer patients, 22 developed a decline in EF attributed to anthracycline therapy over a follow-up time of 9.8 ± 4.2 years. After exclusion of patients who did not have ECGs within 90 days of a TTE, 20 cases and 683 controls remained. The AI-ECG model detected an EF < 50% and ≤ 35% after anthracycline therapy with an AUC of 0.93 and 0.94, respectively. CONCLUSION: These data support the use of AI-ECG for cardiotoxicity screening after anthracycline-based chemotherapy. This technology could serve as a gatekeeper to more costly cardiac imaging and could enable patients to monitor themselves over long periods of time.

Artificial intelligence electrocardiogram can be used to screen for an abnormal heart function after anthracycline chemotherapy, opening the door to new ways of cost-effective screening of cancer survivors at risk of cardiotoxicity over long periods of time.

Long-term outcome after upgrade to cardiac resynchronization therapy: A propensity score-matched analysis.

AIM: Cardiac resynchronization therapy (CRT) is a cornerstone in the management of chronic heart failure in patients with a broad or paced QRS. However, data on long-term outcome after upgrade to CRT are scarce. METHODS AND RESULTS: This international, multicentre retrospective registry included 2275 patients who underwent a de novo or upgrade CRT implantation with a mean follow-up of 3.6 ± 2.7 years. The primary composite endpoint included all-cause mortality, heart transplantation, or ventricular assist device implantation. The secondary endpoint was first heart failure admission. Multivariable Cox regression and propensity score matching (PSM) analyses were performed. Patients who underwent CRT upgrade (n = 605, 26.6%) were less likely female (19.7% vs. 28.8%, p < 0.001), more often had ischeemic cardiomyopathy (49.8% vs. 40.2%, p < 0.001), and had worse renal function (median estimated glomerular filtration rate 50.3 ml/min/1.73 m2 [35.8-69.5] vs. 59.9 ml/min/1.73 m2 [43.0-76.5], p < 0.001). The incidence rate of the composite endpoint was 10.8%/year after CRT upgrade versus 7.1%/year for de novo implantations (p < 0.001). PSM for the primary endpoint resulted in 488 pairs. After propensity score matching, upgrade to CRT was associated with a higher chance to reach the composite endpoint (multivariable hazard ratio [HR] 1.35, 95% confidence interval [CI] 1.08-1.70), for both upgrade from pacemaker (multivariable HR 1.33, 95% CI 1.03-1.70) and implantable cardioverter-defibrillator (ICD) (multivariable HR 1.40, 95% CI 1.01-1.95). PSM for the secondary endpoint resulted in 277 pairs. After PSM, upgrade to CRT was associated with a higher chance for heart failure admission (HR 1.74, 95% CI 1.26-2.41). CONCLUSION: In this retrospective analysis, the outcome of patients who underwent upgrades to CRT differed significantly from patients who underwent de novo CRT implantation, particularly for upgrades from ICD. Importantly, this difference in outcome does not imply a causal relation between therapy and outcome but rather a difference between two different patient populations.

Evolution of ventricular and valve function in patients with right ventricular pacing - A randomized controlled trial comparing leadless and conventional pacing.

BACKGROUND: Leadless pacemakers (PMs) were recently introduced to overcome lead-related complications. They showed high safety and efficacy profiles. Prospective studies assessing long-term safety on cardiac structures are still missing. OBJECTIVE: The purpose of this study was to compare the mechanical impact of Micra with conventional PM on heart function. METHODS: We conducted a non-inferiority trial in patients with an indication for single chamber ventricular pacing. Patients were 1:1 randomized to undergo implantation of either Micra or conventional monochamber ventricular pacemaker (PM). Patients underwent echocardiography at baseline, 6 and 12 months after implantation. Analysis included left ventricular ejection fraction (LVEF), global longitudinal strain (GLS) and valve function. N-terminal-pro hormone B-type natriuretic peptide (NT-pro-BNP) levels were measured at baseline and 12 months. RESULTS: Fifty-one patients (27 in Micra group and 24 in conventional group) were included. Baseline characteristics were similar for both groups. At 12 months, (1) the left ventricular function as assessed by LVEF and GLS worsened similarly in both groups (∆LVEF -10 ± 7.3% and ∆GLS +5.7 ± 6.4 in Micra group vs. -13.4 ± 9.9% and +5.2 ± 3.2 in conventional group) (p = 0.218 and 0.778, respectively), (2) the severity of tricuspid valve regurgitation was significantly lower with Micra than conventional pacing (p = 0.009) and (3) median NT-pro-BNP was lower in Micra group (970 pg/dL in Micra group versus 1394 pg/dL in conventional group, p = 0.041). CONCLUSION: Micra is non inferior to conventional PMs concerning the evolution of left ventricular function at 12-month follow-up. Our data suggest that Micra has a comparable mechanical impact on the ventricular systolic function but resulted in less valvular dysfunction.

Effectiveness of the risk stratification proposed by the 2022 European Heart Rhythm Association Expert Consensus statement on arrhythmic mitral valve prolapse.

BACKGROUND: Recently, an expert consensus statement proposed indications where implantation of a primary prevention implantable cardioverter-defibrillator (ICD) may be reasonable in patients with mitral valve prolapse (MVP). The objective was to evaluate the proposed risk stratification by the expert consensus statement. METHODS: Consecutive patients with MVP without alternative arrhythmic substrates with cardiac magnetic resonance imaging (CMR) were included in a single-center retrospective registry. Arrhythmic MVP (AMVP) was defined as a total premature ventricular complex burden ≥5%, non-sustained ventricular tachycardia (VT), VT, or ventricular fibrillation. The end point was a composite of SCD, VT, inducible VT, and appropriate ICD shocks. RESULTS: In total, 169 patients (52.1% male, median age 51.4 years) were included and 99 (58.6%) were classified as AMVP. Multivariate logistic regression identified the presence of late gadolinium enhancement (OR 2.82, 95%CI 1.45-5.50) and mitral annular disjunction (OR 1.98, 95%CI 1.02-3.86) as only predictors of AMVP. According to the EHRA risk stratification, 5 patients with AMVP (5.1%) had a secondary prevention ICD indication, while in 69 patients (69.7%) the implantation of an ICD may be reasonable. During a median follow-up of 8.0 years (IQR 5.0-15.6), the incidence rate for the composite arrhythmic end point was 0.3%/year (95%CI 0.1-0.8). CONCLUSION: More than half of MVP patients referred for CMR met the AMVP diagnostic criteria. Despite low long-term event rates, in 70% of patients with AMVP the implantation of an ICD may be reasonable. Risk stratification of SCD in MVP remains an important knowledge gap and requires urgent investigation.

Successes and challenges of artificial intelligence in cardiology.

In the past decades there has been a substantial evolution in data management and data processing techniques. New data architectures made analysis of big data feasible, healthcare is orienting towards personalized medicine with digital health initiatives, and artificial intelligence (AI) is becoming of increasing importance. Despite being a trendy research topic, only very few applications reach the stage where they are implemented in clinical practice. This review provides an overview of current methodologies and identifies clinical and organizational challenges for AI in healthcare.

Patients with non-ischemic cardiomyopathy and mid-wall striae have similar arrhythmic outcomes as ischemic cardiomyopathy.

PURPOSE: While implantable cardioverter-defibrillator (ICD) therapy provides clear benefit in patients with ischemic cardiomyopathy (ICM), this is less clear in patients with non-ischemic cardiomyopathy (NICM). Mid-wall striae (MWS) fibrosis is an established cardiovascular magnetic resonance (CMR) risk marker observed in patients with NICM. We evaluated whether patients with NICM and MWS have similar risk of arrhythmia-related cardiovascular events as patients with ICM. METHODS: We studied a cohort of patients undergoing CMR. The presence of MWS was adjudicated by experienced physicians. The primary outcome was a composite of implantable cardioverter-defibrillator (ICD) implant, hospitalization for ventricular tachycardia, resuscitated cardiac arrest, or sudden cardiac death. Propensity-matched analysis was performed to compare outcomes for patients NICM with MWS and ICM. RESULTS: A total of 1,732 patients were studied, 972 NICM (706 without MWS, 266 with MWS) and 760 ICM. NICM patients with MWS were more likely to experience the primary outcome versus those without MWS (unadjusted subdistribution hazard ratio (subHR) 2.26, 95% confidence interval [CI] 1.51-3.41) with no difference versus ICM patients (unadjusted subHR 1.32, 95% CI 0.93-1.86). Similar results were seen in a propensity-matched population (adjusted subHR 1.11, 95% CI 0.63-1.98, p = 0.711). CONCLUSION: Patients with NICM and MWS demonstrate significantly higher arrhythmic risk compared to NICM without MWS. After adjustment, the arrhythmia risk of patients with NICM and MWS was similar to patients with ICM. Accordingly, physicians could consider the presence of MWS when making clinical decisions regarding arrhythmia risk management in patients with NICM.

2023 HRS/EHRA/APHRS/LAHRS Expert Consensus Statement on Practical Management of the Remote Device Clinic.

Remote monitoring is beneficial for the management of patients with cardiovascular implantable electronic devices by impacting morbidity and mortality. With increasing numbers of patients using remote monitoring, keeping up with higher volume of remote monitoring transmissions creates challenges for device clinic staff. This international multidisciplinary document is intended to guide cardiac electrophysiologists, allied professionals, and hospital administrators in managing remote monitoring clinics. This includes guidance for remote monitoring clinic staffing, appropriate clinic workflows, patient education, and alert management. This expert consensus statement also addresses other topics such as communication of transmission results, use of third-party resources, manufacturer responsibilities, and programming concerns. The goal is to provide evidence-based recommendations impacting all aspects of remote monitoring services. Gaps in current knowledge and guidance for future research directions are also identified.

Remote Patient Monitoring: What Have We Learned and Where Are We Going?

Purpose of Review: Remote monitoring (RM) of cardiac implantable electronic devices (CIEDs) is an important part of patient follow-up. The increasing number of patients with CIEDs and the recent pandemic pose several challenges for already limited device clinic resources. This review focuses on recent evolutions in RM and identifies future needs to improve RM. Recent Findings: RM has been associated with multiple clinical benefits, including improved survival, early detection of actionable events, reduction in inappropriate shocks, longer battery lives, and more efficient healthcare utilization. The survival benefit was driven by studies using alert-based continuous RM with daily transmissions and fast reaction times. Patients report a high satisfaction rate without significant differences in quality of life between RM and in-office follow-up.The increasing workload, due to the increasing number of CIEDs implanted with daily remote transmissions, results in several challenges for the future of RM. RM requires appropriate reimbursement for RM device clinics to optimize patient/staff ratios, including sufficient non-clinical and administrative support. Universal alert programming and data processing may minimize inter-manufacturer differences, improve the signal-to-noise ratio, and allow the development of standard operating protocols and workflows. In the future, programming by remote control and true remote programming may further improve remote CIED management, patient quality of life, and device clinic workflows. Summary: RM should be considered standard of care in management of patients with CIEDs. The clinical benefits of RM can be maximized by an alert-based continuous RM model. Adapted healthcare policies are required to keep RM manageable for the future.