TY - JOUR
T1 - Machine Learning Methods for Identifying Atrial Fibrillation Cases and Their Predictors in Patients With Hypertrophic Cardiomyopathy
T2 - The HCM-AF-Risk Model
AU - Bhattacharya, Moumita
AU - Lu, Dai Yin
AU - Ventoulis, Ioannis
AU - Greenland, Gabriela V.
AU - Yalcin, Hulya
AU - Guan, Yufan
AU - Marine, Joseph E.
AU - Olgin, Jeffrey E.
AU - Zimmerman, Stefan L.
AU - Abraham, Theodore P.
AU - Abraham, M. Roselle
AU - Shatkay, Hagit
N1 - Funding Information:
This work was funded in part by the National Science Foundation (NSF) IIS EAGER grant # 1650851 , and the National Institutes of Health grants R01 LM012527, and U54 GM104941 (to H.S.), an award from the John Taylor Babbitt (JTB) foundation (Chatham, New Jersey), and startup funds from the University of California San Francisco, Division of Cardiology (to M.R.A.).
Publisher Copyright:
© 2021 The Authors
PY - 2021/6
Y1 - 2021/6
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85108700898&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85108700898&partnerID=8YFLogxK
U2 - 10.1016/j.cjco.2021.01.016
DO - 10.1016/j.cjco.2021.01.016
M3 - Article
C2 - 34169259
AN - SCOPUS:85108700898
SN - 2589-790X
VL - 3
SP - 801
EP - 813
JO - CJC Open
JF - CJC Open
IS - 6
ER -