QT interval extracted from 30-minute short resting Holter ECG recordings predicts mortality in heart failure

Prediction of heart failure patients with distinct left ventricular ejection fraction levels using circadian ECG features and machine learning

Heart failure (HF) encompasses a diverse clinical spectrum, including instances of transient HF or HF with recovered ejection fraction, alongside persistent cases. This dynamic condition exhibits a growing prevalence and entails substantial healthcare expenditures, with anticipated escalation in the future. It is essential to classify HF patients into three groups based on their ejection fraction: reduced (HFrEF), mid-range (HFmEF), and preserved (HFpEF), such as for diagnosis, risk assessment, treatment choice, and the ongoing monitoring of heart failure. Nevertheless, obtaining a definitive prediction poses challenges, requiring the reliance on echocardiography. On the contrary, an electrocardiogram (ECG) provides a straightforward, quick, continuous assessment of the patient's cardiac rhythm, serving as a cost-effective adjunct to echocardiography. In this research, we evaluate several machine learning (ML)-based classification models, such as K-nearest neighbors (KNN), neural networks (NN), support vector machines (SVM), and decision trees (TREE), to classify left ventricular ejection fraction (LVEF) for three categories of HF patients at hourly intervals, using 24-hour ECG recordings. Information from heterogeneous group of 303 heart failure patients, encompassing HFpEF, HFmEF, or HFrEF classes, was acquired from a multicenter dataset involving both American and Greek populations. Features extracted from ECG data were employed to train the aforementioned ML classification models, with the training occurring in one-hour intervals. To optimize the classification of LVEF levels in coronary artery disease (CAD) patients, a nested cross-validation approach was employed for hyperparameter tuning. HF patients were best classified using TREE and KNN models, with an overall accuracy of 91.2% and 90.9%, and average area under the curve of the receiver operating characteristics (AUROC) of 0.98, and 0.99, respectively. Furthermore, according to the experimental findings, the time periods of midnight-1 am, 8-9 am, and 10-11 pm were the ones that contributed to the highest classification accuracy. The results pave the way for creating an automated screening system tailored for patients with CAD, utilizing optimal measurement timings aligned with their circadian cycles.

Investigating automated regression models for estimating left ventricular ejection fraction levels in heart failure patients using circadian ECG features

Heart Failure (HF) significantly impacts approximately 26 million people worldwide, causing disruptions in the normal functioning of their hearts. The estimation of left ventricular ejection fraction (LVEF) plays a crucial role in the diagnosis, risk stratification, treatment selection, and monitoring of heart failure. However, achieving a definitive assessment is challenging, necessitating the use of echocardiography. Electrocardiogram (ECG) is a relatively simple, quick to obtain, provides continuous monitoring of patient's cardiac rhythm, and cost-effective procedure compared to echocardiography. In this study, we compare several regression models (support vector machine (SVM), extreme gradient boosting (XGBOOST), gaussian process regression (GPR) and decision tree) for the estimation of LVEF for three groups of HF patients at hourly intervals using 24-hour ECG recordings. Data from 303 HF patients with preserved, mid-range, or reduced LVEF were obtained from a multicentre cohort (American and Greek). ECG extracted features were used to train the different regression models in one-hour intervals. To enhance the best possible LVEF level estimations, hyperparameters tuning in nested loop approach was implemented (the outer loop divides the data into training and testing sets, while the inner loop further divides the training set into smaller sets for cross-validation). LVEF levels were best estimated using rational quadratic GPR and fine decision tree regression models with an average root mean square error (RMSE) of 3.83% and 3.42%, and correlation coefficients of 0.92 (p<0.01) and 0.91 (p<0.01), respectively. Furthermore, according to the experimental findings, the time periods of midnight-1 am, 8-9 am, and 10-11 pm demonstrated to be the lowest RMSE values between the actual and predicted LVEF levels. The findings could potentially lead to the development of an automated screening system for patients with coronary artery disease (CAD) by using the best measurement timings during their circadian cycles.

Risk assessment of post-myocardial infarction patients with preserved ejection fraction using 45-min short resting Holter electrocardiographic recordings

BACKGROUND

Risk stratification for sudden cardiac death in post-myocardial infarction (post-MI) patients remains a challenging task. Several electrocardiographic noninvasive risk factors (NIRFs) have been associated with adverse outcomes and were used to refine risk assessment. This study aimed to evaluate the performance of NIRFs extracted from 45-min short resting Holter ECG recordings (SHR), in predicting ventricular tachycardia inducibility with programmed ventricular stimulation (PVS) in post-MI patients with preserved left ventricular ejection fraction (LVEF).

METHODS

We studied 99 post-MI ischemia-free patients (mean age: 60.5 ± 9.5 years, 86.9% men) with LVEF ≥40%, at least 40 days after revascularization. All the patients underwent PVS and a high-resolution SHR. The following parameters were evaluated: mean heart rate, ventricular arrhythmias (premature ventricular complexes, couplets, tachycardias), QTc duration, heart rate variability (HRV), deceleration capacity, heart rate turbulence, late potentials, and T-wave alternans.

RESULTS

PVS was positive in 24 patients (24.2%). HRV, assessed by the standard deviation of normal-to-normal R-R intervals (SDNN), was significantly decreased in the positive PVS group (42 ms vs. 51 ms, p = .039). SDNN values <50 ms were also associated with PVS inducibility (OR 3.081, p = .032 in univariate analysis, and 4.588, p = .013 in multivariate analysis). No significant differences were identified for the other NIRFs. The presence of diabetes, history of ST-elevation MI (STEMI) and LVEF <50% were also important predictors of positive PVS.

CONCLUSIONS

HRV assessed from SHR, combined with other noninvasive clinical and echocardiographic variables (diabetes, STEMI history, LVEF), can provide an initial, practical, and rapid screening tool for arrhythmic risk assessment in post-MI patients with preserved LVEF.

ECG and Biomarker Profile in Patients with Acute Heart Failure: A Pilot Study

Background: Biomarkers, electrocardiogram (ECG) and Holter ECG are basic, accessible and feasible cardiac investigations. The combination of their results may lead to a more complex predictive model that may improve the clinical approach in acute heart failure (AHF). The main objective was to investigate which ECG parameters are correlated with the usual cardiac biomarkers (prohormone N-terminal proBNP, high-sensitive cardiac troponin I) in patients with acute heart failure, in a population from Romania. The relationship between certain ECG parameters and cardiac biomarkers may support future research on their combined prognostic value. Methods: In this prospective case-control study were included 49 patients with acute heart failure and 31 participants in the control group. For all patients we measured levels of prohormone N-terminal proBNP (NT-proBNP), high-sensitive cardiac troponin I (hs-cTnI) and MB isoenzyme of creatine phosphokinase (CK-MB) and evaluated the 12-lead ECG and 24 h Holter monitoring. Complete clinical and paraclinical evaluation was performed. Results: NT-proBNP level was significantly higher in patients with AHF (p < 0.001). In patients with AHF, NT-proBNP correlated with cQTi (p = 0.027), pathological Q wave (p = 0.029), complex premature ventricular contractions (PVCs) (p = 0.034) and ventricular tachycardia (p = 0.048). Hs-cTnI and CK-MB were correlated with ST-segment modification (p = 0.038; p = 0.018) and hs-cTnI alone with complex PVCs (p = 0.031). Conclusions: The statistical relationships found between cardiac biomarkers and ECG patterns support the added value of ECG in the diagnosis of AHF. We emphasize the importance of proper ECG analysis of more subtle parameters that can easily be missed. As a non-invasive technique, ECG can be used in the outpatient setting as a warning signal, announcing the acute decompensation of HF. In addition, the information provided by the ECG complements the biomarker results, supporting the diagnosis of AHF in cases of dyspnea of uncertain etiology. Further studies are needed to confirm long-term prognosis in a multi-marker approach.

Application of 24 h Dynamic Electrocardiography in the Diagnosis of Asymptomatic Myocardial Ischemia with Arrhythmia in Elderly Patients with Coronary Heart Disease

Objective

To investigate the application effect of 24 h dynamic electrocardiogram in the diagnosis of asymptomatic myocardial ischemia with arrhythmia in elderly patients with coronary heart disease.

Methods

A total of 206 elderly patients suspected of coronary heart disease (CHD) with asymptomatic myocardial ischemia and arrhythmia were selected as the research subjects. 24 h dynamic electrocardiogram and conventional electrocardiogram examinations were conducted. Coronary angiography was used as the gold standard to observe the performance of the two examination methods in the diagnosis of asymptomatic myocardial ischemia with arrhythmia in elderly patients with CHD.

Results

Coronary angiography showed 174 positive cases and 32 negative cases among the 206 patients. The diagnostic results of a conventional electrocardiogram showed 150 positive cases and 20 negative cases. Its sensitivity, specificity, accuracy, positive predictive value, and negative predictive value were 86.21%, 62.50%, 82.52%, 92.59%, and 45.45%, respectively. The diagnostic results of 24 h dynamic electrocardiograms showed 168 positive cases and 29 negative cases. Its sensitivity, specificity, accuracy, positive predictive value, and negative predictive value were 96.55%, 96.63%, 95.63%, 98.25%, and 82.86%, respectively. The above results indicated that 24 h dynamic electrocardiogram was significantly better (P < 0.05). The detection rate of arrhythmia types by 24-hour dynamic electrocardiogram was significantly higher than that of conventional electrocardiogram (P < 0.05).

Conclusion

24 h dynamic electrocardiogram is helpful for the diagnosis of asymptomatic myocardial ischemia with arrhythmia in elderly patients with CHD and can improve the detection rate, thereby providing a basis for clinical diagnosis and treatment.

Holter Recordings at Initial Assessment for Long QT Syndrome: Relationship to Genotype Status and Cardiac Events

Background: The relationship of Holter recordings of repolarization length to outcome in long QT syndrome (LQTS) is unknown. Methods: Holter recordings and initial 12 lead ECG QTc were related to outcome in 101 individuals with LQTS and 28 gene-negative relatives. Mean QTc (mQTc) and mean RTPc (R-wave to peak T-wave, mRTPc) using Bazett correction were measured, analyzing heart rates 40 to 120 bpm. Previously reported upper limit of normal (ULN) were: women and children (<15 years), mQTc 454, mRTPc 318 ms; men mQTc 446 ms, mRTPc 314 ms. Results: Measurements in LQTS patients were greatly prolonged; children and women mean mQTc 482 ms (range 406−558), mRTPc 351 ms (259−443); males > 15 years mQTc 469 ms (407−531), mRTPc 338 ms (288−388). Ten patients had cardiac arrest (CA), and 24 had arrhythmic syncope before or after the Holter. Holter values were more closely related to genotype status and symptoms than 12 lead QTc, e.g., sensitivity/specificity for genotype positive status, mRTPc > ULN (89%/86%); CA, mRTPc > 30 ms over ULN (48%/100%). Of 34 symptomatic (CA/syncope) patients, only 9 (26%) had 12 lead QTc > 500 ms, whereas 33/34 (94%) had an mRTPc or mQTc above ULN. In 10 with CA, all Holter measurements were > 15 ms above ULN, but only two had 12 lead QTc > 500 m. Conclusions: Holter average repolarization length, particularly mRTPc, reflects definite LQTS status and clinical risk better than the initial 12 lead QTc. Values below ULN indicate both a low risk of having LQTS and a low risk of cardiac events in the small percentage that do.