Machine Learning Methods for Identifying Atrial Fibrillation Cases and Their Predictors in Patients With Hypertrophic Cardiomyopathy: The HCM-AF-Risk Model

Prediction of new-onset atrial fibrillation in patients with hypertrophic cardiomyopathy using machine learning

AIMS

Atrial fibrillation (AF) is the most common sustained arrhythmia among patients with hypertrophic cardiomyopathy (HCM), leading to increased symptom burden and risk of thromboembolism. The HCM-AF score was developed to predict new-onset AF in patients with HCM, though sensitivity and specificity of this conventional tool are limited. Thus, there is a need for more accurate tools to predict new-onset AF in HCM. The objective of the present study was to develop a better model to predict new-onset AF in patients with HCM using machine learning (ML).

METHODS AND RESULTS

In this prospective, multicentre cohort study, we enrolled 1069 patients with HCM without a prior history of AF. We built a ML model (logistic regression with Lasso regularization) using clinical variables. We developed the ML model using the cohort from one institution (training set) and applied it to an independent cohort from a separate institution (test set). We used the HCM-AF score as a reference model. We compared the area under the receiver-operating characteristic curve (AUC) between the ML model and the reference model using the DeLong's test. Median follow-up time was 2.1 years, with 128 (12%) patients developing new-onset AF. Using the ML model developed in the training set to predict new-onset AF, the AUC in the test set was 0.84 (95% confidence interval [CI] 0.77-0.91). The ML model outperformed the reference model (AUC 0.64; 95% CI 0.54-0.73; DeLong's p < 0.001). The ML model had higher sensitivity (0.82; 95% CI 0.65-0.93) than that of the reference model (0.67; 95% CI 0.52-0.88). The ML model also had higher specificity (0.76; 95% CI 0.71-0.81) than that of the reference model (0.57; 95% CI 0.41-0.70). Among the most important clinical variables included in the ML-based model were left atrial volume and diameter, left ventricular outflow tract gradient with exercise stress and at rest, late gadolinium enhancement on cardiac magnetic resonance imaging, peak heart rate during exercise stress, age at diagnosis, positive genotype, diabetes mellitus, and end-stage renal disease.

CONCLUSION

Our ML model showed superior performance compared to the conventional HCM-AF score for the prediction of new-onset AF in patients with HCM.

Prediction of incident atrial fibrillation in hypertrophic cardiomyopathy

BACKGROUND AND AIM

Atrial fibrillation (AF) is the most common sustained arrhythmia in hypertrophic cardiomyopathy (HCM) with significant effects on outcome. We aim to compare the left atrial (LA) diameter measurement with HCM-AF Score in predicting atrial fibrillation (AF) development in HCM.

METHODS

From the regional cohort of the Campania Region, Italy, 519 HCM patients (38% women, age45 ± 17 years) without history of AF, were enrolled in the study. The primary clinical endpoint was the development of AF, defined as at least 1 episode documented by ECG.

RESULTS

During the follow-up (mean 8 ± 6, IQ range 2.5-11.2 years), 99 patients (19%) developed AF. Patients who developed AF were more symptomatic, had higher prevalence of ICD implantation, had larger LA diameter, greater left ventricular (LV) maximal wall thickness and LV outflow tract obstruction (p < 0.01). Both LA diameter and HCM-AF score were higher in patients who developed AF versus those who did not (LA diameter 49 ± 7 versus 43 ± 6 mm; HCM-AF score 22 ± 4 versus 19 ± 4; p < 0.0001); however, ROC curve analysis demonstrated that LA diameter had a significant greater area under the curve than HCM-AF Score (p < 0.0001). At 5 years follow-up, a LA diameter > 46 mm, showed a similar accuracy in predicting AF development of HCM-AF score ≥ 22, which identifies patients at high risk to develop AF.

CONCLUSION

Our analysis shows that LA diameter, a worldwide and simple echocardiographic measure, is capable alone to predict AF development in HCM patients.

Systolic blood pressure ≤110 mm Hg is associated with severe coronary microvascular ischemia and higher risk for ventricular arrhythmias in hypertrophic cardiomyopathy

Background

Coronary microvascular dysfunction (CMD) and hypertension (HTN) occur frequently in hypertrophic cardiomyopathy (HCM), but whether blood pressure (BP) influences CMD and outcomes is unknown.

Objective

The purpose of this study was to test the hypothesis that HTN is associated with worse CMD and outcomes.

Methods

This retrospective study included 690 HCM patients. All patients underwent cardiac magnetic resonance imaging, echocardiography, and rhythm monitoring; 127 patients also underwent rest/vasodilator stress 13NH3 positron emission tomography myocardial perfusion imaging. Patients were divided into 3 groups based on their rest systolic blood pressure (SBP) (group 1 ≤110 mm Hg; group 2 111-140; group 3 >140 mm Hg) and were followed for development of ventricular tachycardia (VT)/ventricular fibrillation (VF), heart failure (HF), death, and composite outcome.

Results

Group 1 patients had the lowest age and left ventricular (LV) mass but the highest prevalence of nonobstructive hemodynamics and restrictive diastolic filling. LV scar was similar in the 3 groups. Group 1 had the lowest rest and stress myocardial blood flow (MBF) and highest SDS (summed difference score). Rest SBP was positively correlated with stress MBF and negatively correlated with SDS. Group 1 had the highest incidence of VT/VF, whereas the incidences of HF, death, and composite outcome were similar among the 3 groups. In multivariate analysis, rest SBP ≤110 mm Hg was independently associated with VT/VF (hazard ratio 2.6; 95% confidence interval 1.0-6.7; P = .04).

Conclusion

SBP ≤110 mm Hg is associated with greater severity of CMD and coronary microvascular ischemia and higher incidence of ventricular arrhythmias in HCM.

Clinical Application of the HCM-AF Risk Score in the Prediction of Clinical Outcomes of Polish Patients with Hypertrophic Cardiomyopathy

The recently introduced HCM-AF Risk Calculator allows the prognosis of atrial fibrillation (AF) occurrence in hypertrophic cardiomyopathy (HCM) patients. The aim of this study was to assess the clinical application of the HCM-AF Risk Score in the prediction of the clinical outcomes of Polish patients. The study included 92 patients (50.0% female, median age 55 years), with a baseline sinus rhythm diagnosed between 2013 and 2018. The analysis involved the incidence of clinical characteristics and outcomes, total mortality, rehospitalisation, and the course of heart failure (HF). According to the HCM-AF Risk Score, the HCM population was stratified into three subgroups, with a low (13/14.2%), intermediate (30/32.6%), and high risk of AF (49/53.2%). Subgroups differed significantly: the high-risk subgroup was older, had a higher body mass index (BMI), and more advanced signs of left ventricular (LV) hypertrophy and left atrium (LA) dilatation. The registered AF incidence was 31.5% and 43.5% in the 2- and 5-year follow-ups, and it was significantly higher than in the HCM-AF Risk Score population, which had 4.6% in the 2-year follow-up, and 10.7% in the 5-year follow-up. In the whole population, the AF incidence in both the 2- and 5-year follow-ups revealed a strong correlation with the HCM-AF Risk Score (r = 0.442, p < 0.001; r = 0.346, p < 0.001, respectively). The clinical outcomes differed among the subgroups: the total mortality was 15.4% vs. 20.0% vs. 42.9% (p < 0.05); rehospitalisation was 23.1% vs. 53.3% vs. 71.4% (p < 0.05). The highest HF progression was in the high-risk subgroup (36.7%). Regardless of the high results of the HCM-Risk Score in Polish patients, the score underestimates the real-life high level of AF incidence. The HCM-AF Risk Score seems to be useful in the prediction of the general clinical outcomes in HCM patients.

Toward ECG-based analysis of hypertrophic cardiomyopathy: a novel ECG segmentation method for handling abnormalities

OBJECTIVE

Abnormalities in impulse propagation and cardiac repolarization are frequent in hypertrophic cardiomyopathy (HCM), leading to abnormalities in 12-lead electrocardiograms (ECGs). Computational ECG analysis can identify electrophysiological and structural remodeling and predict arrhythmias. This requires accurate ECG segmentation. It is unknown whether current segmentation methods developed using datasets containing annotations for mostly normal heartbeats perform well in HCM. Here, we present a segmentation method to effectively identify ECG waves across 12-lead HCM ECGs.

METHODS

We develop (1) a web-based tool that permits manual annotations of P, P', QRS, R', S', T, T', U, J, epsilon waves, QRS complex slurring, and atrial fibrillation by 3 experts and (2) an easy-to-implement segmentation method that effectively identifies ECG waves in normal and abnormal heartbeats. Our method was tested on 131 12-lead HCM ECGs and 2 public ECG sets to evaluate its performance in non-HCM ECGs.

RESULTS

Over the HCM dataset, our method obtained a sensitivity of 99.2% and 98.1% and a positive predictive value of 92% and 95.3% when detecting QRS complex and T-offset, respectively, significantly outperforming a state-of-the-art segmentation method previously employed for HCM analysis. Over public ECG sets, it significantly outperformed 3 state-of-the-art methods when detecting P-onset and peak, T-offset, and QRS-onset and peak regarding the positive predictive value and segmentation error. It performed at a level similar to other methods in other tasks.

CONCLUSION

Our method accurately identified ECG waves in the HCM dataset, outperforming a state-of-the-art method, and demonstrated similar good performance as other methods in normal/non-HCM ECG sets.

Inherited and Acquired Rhythm Disturbances in Sick Sinus Syndrome, Brugada Syndrome, and Atrial Fibrillation: Lessons from Preclinical Modeling

Rhythm disturbances are life-threatening cardiovascular diseases, accounting for many deaths annually worldwide. Abnormal electrical activity might arise in a structurally normal heart in response to specific triggers or as a consequence of cardiac tissue alterations, in both cases with catastrophic consequences on heart global functioning. Preclinical modeling by recapitulating human pathophysiology of rhythm disturbances is fundamental to increase the comprehension of these diseases and propose effective strategies for their prevention, diagnosis, and clinical management. In silico, in vivo, and in vitro models found variable application to dissect many congenital and acquired rhythm disturbances. In the copious list of rhythm disturbances, diseases of the conduction system, as sick sinus syndrome, Brugada syndrome, and atrial fibrillation, have found extensive preclinical modeling. In addition, the electrical remodeling as a result of other cardiovascular diseases has also been investigated in models of hypertrophic cardiomyopathy, cardiac fibrosis, as well as arrhythmias induced by other non-cardiac pathologies, stress, and drug cardiotoxicity. This review aims to offer a critical overview on the effective ability of in silico bioinformatic tools, in vivo animal studies, in vitro models to provide insights on human heart rhythm pathophysiology in case of sick sinus syndrome, Brugada syndrome, and atrial fibrillation and advance their safe and successful translation into the cardiology arena.