Dataset Information

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

ABSTRACT:

Background

Hypertrophic cardiomyopathy (HCM) patients have a high incidence of atrial fibrillation (AF) and increased stroke risk, even with low CHA₂DS₂-VASc (congestive heart failure, hypertension, age diabetes, previous stroke/transient ischemic attack) scores. Hence, there is a need to understand the pathophysiology of AF/stroke in HCM. In this retrospective study, we develop and apply a data-driven, machine learning-based method to identify AF cases, and clinical/imaging features associated with AF, using electronic health record data.

Methods

HCM patients with documented paroxysmal/persistent/permanent AF (n = 191) were considered AF cases, and the remaining patients in sinus rhythm (n = 640) were tagged as No-AF. We evaluated 93 clinical variables; the most informative variables useful for distinguishing AF from No-AF cases were selected based on the 2-sample t test and the information gain criterion.

Results

We identified 18 highly informative variables that are positively (n = 11) and negatively (n = 7) correlated with AF in HCM. Next, patient records were represented via these 18 variables. Data imbalance resulting from the relatively low number of AF cases was addressed via a combination of oversampling and undersampling strategies. We trained and tested multiple classifiers under this sampling approach, showing effective classification. Specifically, an ensemble of logistic regression and naïve Bayes classifiers, trained based on the 18 variables and corrected for data imbalance, proved most effective for separating AF from No-AF cases (sensitivity = 0.74, specificity = 0.70, C-index = 0.80).

Conclusions

Our model (HCM-AF-Risk Model) is the first machine learning-based method for identification of AF cases in HCM. This model demonstrates good performance, addresses data imbalance, and suggests that AF is associated with a more severe cardiac HCM phenotype.

SUBMITTER: Bhattacharya M

PROVIDER: S-EPMC8209373 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundThe HCMR (Hypertrophic Cardiomyopathy Registry) is a National Heart, Lung, and Blood Institute-funded, prospective registry of 2,755 patients with hypertrophic cardiomyopathy (HCM) recruited from 44 sites in 6 countries.ObjectivesThe authors sought to improve risk prediction in HCM by incorporating cardiac magnetic resonance (CMR), genetic, and biomarker data.MethodsDemographic and echocardiographic data were collected. Patients underwent CMR including cine imaging, late gadolinium enhancement imaging (LGE) (replacement fibrosis), and T1 mapping for measurement of extracellular volume as a measure of interstitial fibrosis. Blood was drawn for the biomarkers N-terminal pro-B-type natriuretic peptide (NT-proBNP) and high-sensitivity cardiac troponin T (cTnT), and genetic analysis.ResultsA total of 2,755 patients were studied. Mean age was 49 ± 11 years, 71% were male, and 17% non-white. Mean ESC (European Society of Cardiology) risk score was 2.48 ± 0.56. Eighteen percent had a resting left ventricular outflow tract (LVOT) gradient ≥30 mm Hg. Thirty-six percent had a sarcomere mutation identified, and 50% had any LGE. Sarcomere mutation-positive patients were more likely to have reverse septal curvature morphology, LGE, and no significant resting LVOT obstruction. Those that were sarcomere mutation negative were more likely to have isolated basal septal hypertrophy, less LGE, and more LVOT obstruction. Interstitial fibrosis was present in segments both with and without LGE. Serum NT-proBNP and cTnT levels correlated with increasing LGE and extracellular volume in a graded fashion.ConclusionsThe HCMR population has characteristics of low-risk HCM. Ninety-three percent had no or only mild functional limitation. Baseline data separated patients broadly into 2 categories. One group was sarcomere mutation positive and more likely had reverse septal curvature morphology, more fibrosis, but less resting obstruction, whereas the other was sarcomere mutation negative and more likely had isolated basal septal hypertrophy with obstruction, but less fibrosis. Further follow-up will allow better understanding of these subgroups and development of an improved risk prediction model incorporating all these markers.