Dataset Information

Optimizing patient selection for primary prevention implantable cardioverter-defibrillator implantation: utilizing multimodal machine learning to assess risk of implantable cardioverter-defibrillator non-benefit.

ABSTRACT:

Aims

Left ventricular ejection fraction (LVEF) is suboptimal as a sole marker for predicting sudden cardiac death (SCD). Machine learning (ML) provides new opportunities for personalized predictions using complex, multimodal data. This study aimed to determine if risk stratification for implantable cardioverter-defibrillator (ICD) implantation can be improved by ML models that combine clinical variables with 12-lead electrocardiograms (ECG) time-series features.

Methods and results

A multicentre study of 1010 patients (64.9 ± 10.8 years, 26.8% female) with ischaemic, dilated, or non-ischaemic cardiomyopathy, and LVEF ≤ 35% implanted with an ICD between 2007 and 2021 for primary prevention of SCD in two academic hospitals was performed. For each patient, a raw 12-lead, 10-s ECG was obtained within 90 days before ICD implantation, and clinical details were collected. Supervised ML models were trained and validated on a development cohort (n = 550) from Hospital A to predict ICD non-arrhythmic mortality at three-year follow-up (i.e. mortality without prior appropriate ICD-therapy). Model performance was evaluated on an external patient cohort from Hospital B (n = 460). At three-year follow-up, 16.0% of patients had died, with 72.8% meeting criteria for non-arrhythmic mortality. Extreme gradient boosting models identified patients with non-arrhythmic mortality with an area under the receiver operating characteristic curve (AUROC) of 0.90 [95% confidence intervals (CI) 0.80-1.00] during internal validation. In the external cohort, the AUROC was 0.79 (95% CI 0.75-0.84).

Conclusions

ML models combining ECG time-series features and clinical variables were able to predict non-arrhythmic mortality within three years after device implantation in a primary prevention population, with robust performance in an independent cohort.

SUBMITTER: Kolk MZH

PROVIDER: S-EPMC10516624 | biostudies-literature | 2023 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Optimizing patient selection for primary prevention implantable cardioverter-defibrillator implantation: utilizing multimodal machine learning to assess risk of implantable cardioverter-defibrillator non-benefit.

Kolk Maarten Z H MZH Ruipérez-Campillo Samuel S Deb Brototo B Bekkers Erik J EJ Allaart Cornelis P CP Rogers Albert J AJ Van Der Lingen Anne-Lotte C J ACJ Alvarez Florez Laura L Isgum Ivana I De Vos Bob D BD Clopton Paul P Wilde Arthur A M AAM Knops Reinoud E RE Narayan Sanjiv M SM Tjong Fleur V Y FVY

Europace : European pacing, arrhythmias, and cardiac electrophysiology : journal of the working groups on cardiac pacing, arrhythmias, and cardiac cellular electrophysiology of the European Society of Cardiology 20230801 9

<h4>Aims</h4>Left ventricular ejection fraction (LVEF) is suboptimal as a sole marker for predicting sudden cardiac death (SCD). Machine learning (ML) provides new opportunities for personalized predictions using complex, multimodal data. This study aimed to determine if risk stratification for implantable cardioverter-defibrillator (ICD) implantation can be improved by ML models that combine clinical variables with 12-lead electrocardiograms (ECG) time-series features.<h4>Methods and results</h ...[more]

PMID: 37712675

Similar Datasets

Project description:Background One third of primary prevention implantable cardioverter-defibrillator patients receive appropriate therapy, but all remain at risk of defibrillator complications. Information on these complications in contemporary cohorts is limited. This study assessed complications and their risk factors after defibrillator implantation in a Dutch nationwide prospective registry cohort and forecasts the potential reduction in complications under distinct scenarios of updated indication criteria. Methods and Results Complications in a prospective multicenter registry cohort of 1442 primary implantable cardioverter-defibrillator implant patients were classified as major or minor. The potential for reducing complications was derived from a newly developed prediction model of appropriate therapy to identify patients with a low probability of benefitting from the implantable cardioverter-defibrillator. During a follow-up of 2.2 years (interquartile range, 2.0-2.6 years), 228 complications occurred in 195 patients (13.6%), with 113 patients (7.8%) experiencing at least one major complication. Most common ones were lead related (n=93) and infection (n=18). Minor complications occurred in 6.8% of patients, with lead-related (n=47) and pocket-related (n=40) complications as the most prevailing ones. A surgical reintervention or additional hospitalization was required in 53% or 61% of complications, respectively. Complications were strongly associated with device type. Application of stricter implant indication results in a comparable proportional reduction of (major) complications. Conclusions One in 13 patients experiences at least one major implantable cardioverter-defibrillator-related complication, and many patients undergo a surgical reintervention. Complications are related to defibrillator implantations, and these should be discussed with the patient. Stricter implant indication criteria and careful selection of device type implanted may have significant clinical and financial benefits.

Project description:AimsThe benefit of prophylactic implantable cardioverter-defibrillator (ICD) is not uniform due to differences in the risk of life-threatening ventricular tachycardia (VT)/ventricular fibrillation (VF) and non-arrhythmic mortality. We aimed to develop an ICD benefit prediction score that integrates the competing risks.Methods and resultsThe study population comprised all 4531 patients enrolled in the MADIT trials. Best-subsets Fine and Gray regression analysis was used to develop prognostic models for VT (≥200 b.p.m.)/VF vs. non-arrhythmic mortality (defined as death without prior sustained VT/VF). Eight predictors of VT/VF (male, age < 75 years, prior non-sustained VT, heart rate > 75 b.p.m., systolic blood pressure < 140 mmHg, ejection fraction ≤ 25%, myocardial infarction, and atrialarrhythmia) and 7 predictors of non-arrhythmic mortality (age ≥ 75 years, diabetes mellitus, body mass index < 23 kg/m2, ejection fraction ≤ 25%, New York Heart Association ≥II, ICD vs. cardiac resynchronization therapy with defibrillator, and atrial arrhythmia) were identified. The two scores were combined to create three MADIT-ICD benefit groups. In the highest benefit group, the 3-year predicted risk of VT/VF was three-fold higher than the risk of non-arrhythmic mortality (20% vs. 7%, P < 0.001). In the intermediate benefit group, the difference in the corresponding predicted risks was attenuated (15% vs. 9%, P < 0.01). In the lowest benefit group, the 3-year predicted risk of VT/VF was similar to the risk of non-arrhythmic mortality (11% vs. 12%, P = 0.41). A personalized ICD benefit score was developed based on the distribution of the two competing risks scores in the study population (https://is.gd/madit). Internal and external validation confirmed model stability.ConclusionsWe propose the novel MADIT-ICD benefit score that predicts the likelihood of prophylactic ICD benefit through personalized assessment of the risk of VT/VF weighed against the risk of non-arrhythmic mortality.

Project description:BackgroundNew methods to identify patients who benefit from a primary prophylactic implantable cardioverter-defibrillator (ICD) are needed. T-wave alternans (TWA) has been shown to associate with arrhythmogenesis of the heart and sudden cardiac death. We hypothesized that TWA might be associated with benefit from ICD implantation in primary prevention.Methods and resultsIn the EU-CERT-ICD (European Comparative Effectiveness Research to Assess the Use of Primary Prophylactic Implantable Cardioverter-Defibrillators) study, we prospectively enrolled 2327 candidates for primary prophylactic ICD. A 24-hour Holter monitor reading was taken from all recruited patients at enrollment. TWA was assessed from Holter monitoring using the modified moving average method. Study outcomes were all-cause death, appropriate shock, and survival benefit. TWA was assessed both as a contiguous variable and as a dichotomized variable with cutoff points <47 μV and <60 μV. The final cohort included 1734 valid T-wave alternans samples, 1211 patients with ICD, and 523 control patients with conservative treatment, with a mean follow-up time of 2.3 years. TWA ≥60 μV was a predicter for a higher all-cause death in patients with an ICD on the basis of a univariate Cox regression model (hazard ratio, 1.484 [95% CI, 1.024-2.151]; P=0.0374; concordance statistic, 0.51). In multivariable models, TWA was not prognostic of death or appropriate shocks in patients with an ICD. In addition, TWA was not prognostic of death in control patients. In a propensity score-adjusted Cox regression model, TWA was not a predictor of ICD benefit.ConclusionsT-wave alternans is poorly prognostic in patients with a primary prophylactic ICD. Although it may be prognostic of life-threatening arrhythmias and sudden cardiac death in several patient populations, it does not seem to be useful in assessing benefit from ICD therapy in primary prevention among patients with an ejection fraction of ≤35%.

Project description:Background Outcomes data in patients with cardiac amyloidosis after implantable cardioverter-defibrillator (ICD) implantation are limited. We compared outcomes of patients with ICDs implanted for cardiac amyloidosis versus nonischemic cardiomyopathies (NICMs) and evaluated factors associated with mortality among patients with cardiac amyloidosis. Methods and Results Using National Cardiovascular Data Registry's ICD Registry data between April 1, 2010 and December 31, 2015, we created a 1:5 propensity-matched cohort of patients implanted with ICDs with cardiac amyloidosis and NICM. We compared mortality between those with cardiac amyloidosis and matched patients with NICM using Kaplan-Meier survival curves and Cox proportional hazards models. We also evaluated risk factors associated with 1-year mortality in patients with cardiac amyloidosis using multivariable Cox proportional hazards regression models. Among 472 patients with cardiac amyloidosis and 2360 patients with propensity-matched NICMs, 1-year mortality was significantly higher in patients with cardiac amyloidosis compared with patients with NICMs (26.9% versus 11.3%, P<0.001). After adjustment for covariates, cardiac amyloidosis was associated with a significantly higher risk of all-cause mortality (hazard ratio [HR], 1.80; 95% CI, 1.56-2.08). In a multivariable analysis of patients with cardiac amyloidosis, several factors were significantly associated with mortality: syncope (HR, 1.78; 95% CI, 1.22-2.59), ventricular tachycardia (HR, 1.65; 95% CI, 1.15-2.38), cerebrovascular disease (HR, 2.03; 95% CI, 1.28-3.23), diabetes mellitus (HR, 1.55; 95% CI, 1.05-2.27), creatinine = 1.6 to 2.5 g/dL (HR, 1.99; 95% CI, 1.32-3.02), and creatinine >2.5 (HR, 4.34; 95% CI, 2.72-6.93). Conclusions Mortality after ICD implantation is significantly higher in patients with cardiac amyloidosis than in patients with propensity-matched NICMs. Factors associated with death among patients with cardiac amyloidosis include prior syncope, ventricular tachycardia, cerebrovascular disease, diabetes mellitus, and impaired renal function.

Project description:AimsThe MADIT-ICD benefit score is used to stratify the risk of life-threatening arrhythmia and non-arrhythmic mortality. We sought to develop an implantable cardioverter defibrillator (ICD) benefit-prediction score for Japanese patients with ICDs.MethodsPatients who underwent ICD implantation as primary prophylaxis were retrospectively enrolled. Based on their MADIT-ICD benefit scores, we developed a modified MADIT-ICD benefit score adapted to the Japanese population. The primary endpoints were appropriate ICD therapy and all-cause death without appropriate ICD therapy (non-arrhythmic death). We used the Fine and Gray multivariate model and Cox proportional hazard regression to identify factors for adjusting the MADIT-ICD benefit-risk score specifically for the Japanese population. The scoring points for the original MADIT-ICD benefit score were adjusted to optimal points based on the multivariate analysis results in the population.ResultsThe study enrolled 167 patients [age, 61.9 ± 12.3 years; male individuals, 138 (82.6%); cardiac resynchronization therapy, 73 (43.7%); ischaemic cardiomyopathy, 53 (31.7%)]. Fourteen patients received anti-tachycardia pacing (ATP) therapy, and 23 received shock therapy as the initial appropriate ICD therapy. Non-arrhythmic deaths occurred in 37 patients. The original MADIT-ICD benefit score could not stratify non-arrhythmic mortality in the Japanese population. The patients were reclassified into three groups according to the modified MADIT-ICD benefit score. The modified MADIT-ICD benefit score could effectively stratify the incidence of appropriate ICD therapy and non-arrhythmic mortality. In the highest-benefit group, the 10 year cumulative rates of appropriate ICD therapy and non-arrhythmic mortality were 56.8% and 12.9%, respectively (P < 0.01). In the intermediate-benefit group, these rates were 20.2% and 40.2% (P = 0.01). In the lowest-benefit group, the incidence of non-arrhythmic deaths was 68.1%, and no patient received appropriate ICD therapy.ConclusionsThe modified MADIT-ICD benefit score may be useful for stratifying ICD candidates in the Japanese population.

Dataset Information

Optimizing patient selection for primary prevention implantable cardioverter-defibrillator implantation: utilizing multimodal machine learning to assess risk of implantable cardioverter-defibrillator non-benefit.

Aims

Methods and results

Conclusions

Publications

Optimizing patient selection for primary prevention implantable cardioverter-defibrillator implantation: utilizing multimodal machine learning to assess risk of implantable cardioverter-defibrillator non-benefit.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets