Eligibility for subcutaneous implantable cardioverter-defibrillator in congenital heart disease

Abstract

Background: Adult congenital heart disease (ACHD) patients can benefit from a subcutaneous implantable cardioverter-defibrillator (S-ICD).

Objective: The purpose of this study was to assess left- and right-sided S-ICD eligibility in ACHD patients, use machine learning to predict S-ICD eligibility in ACHD patients, and transform 12-lead electrocardiogram (ECG) to S-ICD 3-lead ECG, and vice versa.

Methods: ACHD outpatients (n = 101; age 42 ± 14 years; 52% female; 85% white; left ventricular ejection fraction [LVEF] 56% ± 9%) were enrolled in a prospective study. Supine and standing 12-lead ECG were recorded simultaneously with a right- and left-sided S-ICD 3-lead ECG. Peak-to-peak QRS and T amplitudes; RR, PR, QT, QTc, and QRS intervals; Tmax, and R/Tmax (31 predictor variables) were tested. Model selection, training, and testing were performed using supine ECG datasets. Validation was performed using standing ECG datasets and an out-of-sample non-ACHD population (n = 68; age 54 ± 16 years; 54% female; 94% white; LVEF 61% ± 8%).

Results: Forty percent of participants were ineligible for S-ICD. Tetralogy of Fallot patients passed right-sided screening (57%) more often than left-sided screening (21%; McNemar χ2P = .025). Female participants had greater odds of eligibility (adjusted odds ratio [OR] 5.9; 95% confidence interval [CI] 1.6-21.7; P = .008). Validation of the ridge models was satisfactory for standing left-sided (receiver operating characteristic area under the curve [ROC AUC] 0.687; 95% CI 0.582-0.791) and right-sided (ROC AUC 0.655; 95% CI 0.549-0.762) S-ICD eligibility prediction. Validation of transformation matrices showed satisfactory agreement (<0.1 mV difference).

Conclusion: Nearly half of the contemporary ACHD population is ineligible for S-ICD. The odds of S-ICD eligibility are greater for female than for male ACHD patients. Machine learning prediction of S-ICD eligibility can be used for screening of S-ICD candidates.

Trial registration: ClinicalTrials.gov NCT03209726.

Keywords: Adult congenital heart disease; Electrocardiogram; Eligibility; Machine learning; Subcutaneous implantable cardioverter-defibrillator.

Copyright © 2020 Heart Rhythm Society. Published by Elsevier Inc. All rights reserved.

Figures

Figure 1.

Left-sided (A) and right-sided (B) placement of a1, a2, and a3 electrodes for the 3-lead ECG to mimic the leads A1 (a2-a3), A2 (a1-a3), and A3 (a1-a2) sensing vectors of the S-ICD. (C) Representative examples of S-ICD screening template passing and failing ECG morphologies

Figure 2.

Machine learning steps: S-ICD eligibility prediction development, and validation.

Figure 3.

A. The proportion of patients with transposition of great arteries, Tetralogy of Fallot, and Fontan procedure with passing and failing for right (R)- and left (L)-sided sensing vectors. B. The proportion of study participants who failed all three vectors or passed 1–2 left- and right-sided vectors standing and supine.

Figure 4.

The coefficient paths after (A) lasso, (B) elastic net, (C) ridge models. A line is drawn for each coefficient that traces its value over the searched values of the lasso penalty parameter λ on a reverse logarithmic scale. Lasso is letting variables into the model based on its penalty and the current value of λ. Cross-validation (CV) function (the mean deviance in the CV samples) is plotted over the search grid for the lasso penalty parameter λ on a reverse logarithmic scale for (D) lasso, (E) elastic net, (F) ridge models. The first λ tried is on the left, and the last λ tried is on the right.

Figure 5.

Representative examples of recorded and transformed right-sided 3-lead ECG morphologies and corresponding 12-lead ECG recorded during standing in a Fontan patient.