Contrasting Time- and Rate-Based Approaches for the Assessment of Drug-Induced QT Changes

Deep learning analysis of electrocardiogram for risk prediction of drug-induced arrhythmias and diagnosis of long QT syndrome

AIMS

Congenital long-QT syndromes (cLQTS) or drug-induced long-QT syndromes (diLQTS) can cause torsade de pointes (TdP), a life-threatening ventricular arrhythmia. The current strategy for the identification of drugs at the high risk of TdP relies on measuring the QT interval corrected for heart rate (QTc) on the electrocardiogram (ECG). However, QTc has a low positive predictive value.

METHODS AND RESULTS

We used convolutional neural network (CNN) models to quantify ECG alterations induced by sotalol, an IKr blocker associated with TdP, aiming to provide new tools (CNN models) to enhance the prediction of drug-induced TdP (diTdP) and diagnosis of cLQTS. Tested CNN models used single or multiple 10-s recordings/patient using 8 leads or single leads in various cohorts: 1029 healthy subjects before and after sotalol intake (n = 14 135 ECGs); 487 cLQTS patients (n = 1083 ECGs: 560 type 1, 456 type 2, 67 type 3); and 48 patients with diTdP (n = 1105 ECGs, with 147 obtained within 48 h of a diTdP episode). CNN models outperformed models using QTc to identify exposure to sotalol [area under the receiver operating characteristic curve (ROC-AUC) = 0.98 vs. 0.72, P ≤ 0.001]. CNN models had higher ROC-AUC using multiple vs. single 10-s ECG (P ≤ 0.001). Performances were comparable for 8-lead vs. single-lead models. CNN models predicting sotalol exposure also accurately detected the presence and type of cLQTS vs. healthy controls, particularly for cLQT2 (AUC-ROC = 0.9) and were greatest shortly after a diTdP event and declining over time (P ≤ 0.001), after controlling for QTc and intake of culprit drugs. ECG segment analysis identified the J-Tpeak interval as the best discriminator of sotalol intake.

CONCLUSION

CNN models applied to ECGs outperform QTc measurements to identify exposure to drugs altering the QT interval, congenital LQTS, and are greatest shortly after a diTdP episode.

Comparative TQT analysis with three fully-automated platforms: comparison to core laboratory semi-automated results

BACKGROUND AND PURPOSE

Technological advances in machine-read QT measurement now enable detailed and precise cardiac repolarization assessments. This study assessed the applicability of three state-of-art ECG measurement applications to provide reliable continuous analyses from data obtained in a positive thorough QT study previously characterized with sparse semi-automated measurements performed by an ECG core laboratory.

METHODS

Continuous RR, QT, QTc measurements, and individual QT/RR relationships and their associated intra- and inter-subject variability were derived in parallel with BioQT, Ponemah PRO, and WinAtrec analysis software.

RESULTS

Despite slight vendor-specific differences in measurement variability and QTc, all machine-read methods demonstrated requisite assay sensitivity and yielded similar conclusions in accordance with SA analysis.

CONCLUSIONS

Three commercially available ECG analytical software applications reliably detected the drug-induced QT prolonging effects and replicated the SA core-laboratory conclusions, with greatly improved temporal resolution and reduced analytical costs. With broader experience, these data suggest that current SA methodologies could be effectively replaced by fully automated ECG analysis.

Gene-specific effect of beta-adrenergic blockade on corrected QT interval in the long QT syndrome

BACKGROUND

In the long QT syndrome (LQTS) the effects of beta-blocker treatment on prevention of cardiac events differs according to the genotype. We aimed to assess the effect of beta-blocker treatment on QT/QTc duration in Type 1 LQTS (LQT1) and Type 2 LQTS (LQT2) patients.

METHODS

24-hour digital Holter ECG were recorded before and after beta-blocking therapy initiation in LQT1 (n = 30) and LQT2 patients (n = 16). QT duration was measured on consecutive 1-minute averaged QRS-T complexes leading to up to 1440 edited QT-RR pairs for each recording. We computed subject- and treatment-specific log/log QT/RR relationships which were used to correct the QT intervals. The QT duration was also evaluated at predefined heart rates and after correction using Bazett and Fridericia coefficients.

RESULTS

At baseline, individual QT/RR coefficients were higher in LQT2 than in LQT1 patients (0.53 ± 0.10 vs. 0.40 ± 0.11, P < 0.001) and QT1000 was longer in LQT2 than in LQT1 patients (521 ± 38 vs. 481 ± 39 ms, P < 0.01). Beta-blockers significantly prolonged the mean RR interval (from 827 ± 161 to 939 ± 197 ms, P < 0.0001). The individual QT/RR coefficients were not significantly modified by beta-blockers. Beta-blocker treatment was associated with a prolongation of the QT1000 interval (from 481 ± 39 to 498 ± 43 ms, P < 0.01) in LQT1 patients but with a shortening in LQT2 patients (from 521 ± 38 to 503 ± 32 ms, P < 0.01).

CONCLUSIONS

The effect of beta-adrenergic blockade on QTc duration is different in LQT1 and LQT2 patients. Our data suggest that, in LQT1 patients, the well-known positive effect of beta-blockade might be associated with a prolongation of QTc duration. The mechanisms of beta-blockade protection may be different in LQT1 and in LQT2 patients.

Reference regions for beat-to-beat ECG data

The QT interval is regarded as an important biomarker for the assessment of arrhythmia liability, and evidence of QT prolongation has led to the withdrawal and relabeling of numerous compounds. Traditional methods of assessing QT prolongation correct the QT interval for the length of the RR interval (which varies inversely with heart-rate) in a variety of ways. These methods often disagree with each other and do not take into account changes in autonomic state. Correcting the QT interval for RR reduces a bivariate observation (RR, QT) to a univariate observation (QTc). The development of automatic electrocardiogram (ECG) signal acquisition systems has made it possible to collect continuous (so called 'beat-to-beat') ECG data. ECG data collected prior to administration of a compound allow us to define a region for (RR, QT) values that encompasses typical activity. Such reference regions are used in clinical applications to define the 'normal' region of clinical or laboratory measurements. This paper motivates the need for reference regions of (RR, QT) values from beat-to-beat ECG data, and describes a way of constructing these. We introduce a measure of agreement between two reference regions that points to the reliability of 12-lead digital Holter data. We discuss the use of reference regions in establishing baselines for ECG parameters to assist in the evaluation of cardiac risk and illustrate using data from two methodological studies.

The time course of new T-wave ECG descriptors following single- and double-dose administration of sotalol in healthy subjects

INTRODUCTION

The aim of the study was to assess the time course effect of IKr blockade on ECG biomarkers of ventricular repolarization and to evaluate the accuracy of a fully automatic approach for QT duration evaluation.

METHODS

Twelve-lead digital ECG Holter was recorded in 38 healthy subjects (27 males, mean age = 27.4 + or - 8.0 years) on baseline conditions (day 0) and after administration of 160 mg (day 1) and 320 mg (day 2) of d-l sotalol. For each 24-hour period and each subject, ECGs were extracted every 10 minutes during the 4-hour period following drug dosage. Ventricular repolarization was characterized using three biomarker categories: conventional ECG time intervals, principal component analysis (PCA) analysis on the T wave, and fully automatic biomarkers computed from a mathematical model of the T wave.

RESULTS

QT interval was significantly prolonged starting 1 hour 20 minutes after drug dosing with 160 mg and 1 hour 10 minutes after drug dosing with 320 mg. PCA ventricular repolarization parameters sotalol-induced changes were delayed (>3 hours). After sotalol dosing, the early phase of the T wave changed earlier than the late phase prolongation. Globally, the modeled surrogate QT paralleled manual QT changes. The duration of manual QT and automatic surrogate QT were strongly correlated (R(2) = 0.92, P < 0.001). The Bland and Altman plot revealed a nonstationary systematic bias (bias = 26.5 ms + or - 1.96*SD = 16 ms).

CONCLUSIONS

Changes in different ECG biomarkers of ventricular repolarization display different kinetics after administration of a potent potassium channel blocker. These differences need to be taken into account when designing ventricular repolarization ECG studies.

ECG evaluation of ventricular properties: the importance of cardiac cycle length

Ventricular repolarization properties are dependent on cardiac cycle length. The aim of this article is to emphasize the importance of taking into account heart rate influences on QT duration but also on current and future T-wave morphology parameters. The relationship between QT interval duration and RR interval is a fundamental property of the myocardium that is impaired by the presence of channelopathies such as the LQTS or SQTS, but also by the presence of a cardiomyopathy. Assessing this property is also important when the individual QT/RR relationship is used for individual QT correction in the setting of evaluation of drugs' effect on QT duration. T-wave descriptors such as the relative weight of the terminal part of the T-wave, the amplitude of T-wave apex and Principal Component Analysis parameters are also dependent on heart rate. Assessing ventricular repolarisation ECG parameters at different heart rates avoids the need for difficult rate-correction and helps to better understand and characterize ventricular repolarisation properties.

Automatic extraction of ECG strips from continuous 12-lead holter recordings for QT analysis at prescheduled versus optimized time points

BACKGROUND

Continuous 12-lead ECG monitoring (Holter) in early-phase pharmaceutical studies is today widely used as an ideal platform to extract discrete ECGs for analysis. The extraction process is typically performed manually by trained readers using commercial Holter processing systems.

METHODS

Antares, a novel method for automatic 12-lead extraction from continuous Holter recordings applying minimal noise criteria and heart-rate stability conditions is presented. A set of 12-lead Holter recordings from healthy subjects administered with sotalol is used to compare ECG extractions at fixed time points with ECG extractions generated by Antares optimizing noise and heart rate inside 5 minute windows centered around each expected time point of interest.

RESULTS

Global, low- and high-frequency noise content of extracted ECGs was significantly reduced via optimized approach by Antares. Heart rate was also slightly reduced (from 69 +/- 13 to 64 +/- 13 bpm, P < 0.05). Similarly, the corrected QT interval from optimized extractions was significantly reduced (QTcB from 414 +/- 32 to 402 +/- 30 ms, P < 0.05). Using only baseline data, and after adjusting for intersubject variability, the standard deviation (SD) of QT intervals was highly reduced with optimized extraction (SD of QTcF from 11 +/- 8 to 7 +/- 2 ms, P < 0.05).

CONCLUSIONS

Extraction of discrete 12-lead ECG strips from continuous Holter generates less noisy and more stable ECGs leading to more robust QTc data, thereby potentially facilitating the assessment of ECG effects on clinical trials.

Electrocardiographic biomarkers of ventricular repolarisation in a single family of short QT syndrome and the role of the Bazett correction formula

The definition of the short QT syndrome (SQTS) is based on QT duration, but thorough QT- and T-wave evaluation has not been performed to date. To evaluate the influence of QT rate-correction formulas in SQTS diagnosis, 12-lead electrocardiograms (ECGs) were recorded in 27 subjects from a single family with SQTS. Based on QT duration corrected by Bazett formula (QTc), 4 men were considered to have SQTS (QTc <or=340 ms), and 16 were classified to have "suspected" SQTS (QT <or=320 ms and/or QTc <or=380 ms). Holter ECGs were recorded in the 4 patients with SQTS, 8 with suspected SQTS, and 62 healthy volunteers. We evaluated QT duration at each RR interval and calculated individual alpha coefficient of the QT/RR relation. The QT interval duration at the mean Holter heart rate was corrected using an individual approach and 5 "universal" correction formulas (Bazett, Fridericia, Sagie-Framingham, Hodges, Rautaharju). Patients with SQTS and controls had lower alpha coefficients of the QT/RR relation when compared with Bazett and Fridericia formulas. The QT rate-dependence was lower in patients with SQTS (alpha 0.146 +/- 0.070) when compared with control subjects (alpha 0.203 +/- 0.039, p <0.05). The universal correction-formulas consistently provided higher values of corrected QT interval duration at the mean Holter heart rate than a subject-specific correction formula (p <0.05), which induced false negative diagnoses. In conclusion, the Bazett correction formula is not appropriate for making a diagnosis of SQTS. The subject-specific correction formula may provide a better cut-off value definition for the diagnosis of SQTS.