Welcome to PracticeUpdate! We hope you are enjoying temporary access to this content.
Please register today for a free account and gain full access
to all of our expert-selected content.
Already Have An Account? Log in Now
Machine Learning Assessment of Left Ventricular Diastolic Function Based on ECG Features
abstract
This abstract is available on the publisher's site.
Access this abstract now Full Text Available for ClinicalKey SubscribersBACKGROUND
Left ventricular (LV) diastolic dysfunction is recognized as playing a major role in the pathophysiology of heart failure; however, clinical tools for identifying diastolic dysfunction before echocardiography remain imprecise.
OBJECTIVES
This study sought to develop machine-learning models that quantitatively estimate myocardial relaxation using clinical and electrocardiography (ECG) variables as a first step in the detection of LV diastolic dysfunction.
METHODS
A multicenter prospective study was conducted at 4 institutions in North America enrolling a total of 1,202 subjects. Patients from 3 institutions (n = 814) formed an internal cohort and were randomly divided into training and internal test sets (80:20). Machine-learning models were developed using signal-processed ECG, traditional ECG, and clinical features and were tested using the test set. Data from the fourth institution was reserved as an external test set (n = 388) to evaluate the model generalizability.
RESULTS
Despite diversity in subjects, the machine-learning model predicted the quantitative values of the LV relaxation velocities (e') measured by echocardiography in both internal and external test sets (mean absolute error: 1.46 and 1.93 cm/s; adjusted R2 = 0.57 and 0.46, respectively). Analysis of the area under the receiver operating characteristic curve (AUC) revealed that the estimated e' discriminated the guideline-recommended thresholds for abnormal myocardial relaxation and diastolic and systolic dysfunction (LV ejection fraction) the internal (area under the curve [AUC]: 0.83, 0.76, and 0.75) and external test sets (0.84, 0.80, and 0.81), respectively. Moreover, the estimated e' allowed prediction of LV diastolic dysfunction based on multiple age- and sex-adjusted reference limits (AUC: 0.88 and 0.94 in the internal and external sets, respectively).
CONCLUSIONS
A quantitative prediction of myocardial relaxation can be performed using easily obtained clinical and ECG features. This cost-effective strategy may be a valuable first clinical step for assessing the presence of LV dysfunction and may potentially aid in the early diagnosis and management of heart failure patients.
Additional Info
Disclosure statements are available on the authors' profiles:
Machine Learning Assessment of Left Ventricular Diastolic Function Based on Electrocardiographic Features
J Am Coll Cardiol 2020 Aug 25;76(8)930-941, N Kagiyama, M Piccirilli, N Yanamala, S Shrestha, PD Farjo, G Casaclang-Verzosa, WM Tarhuni, N Nezarat, MJ Budoff, J Narula, PP SenguptaFrom MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine.
The gold standard for diastolic dysfunction is invasive ventricular pressure–volume loops analysis. Noninvasive diagnosis of diastolic dysfunction is notoriously tricky. Can machine learning create a disruptive technology for noninvasive detection of diastolic dysfunction? The authors of this paper made a bold first step in this direction. Investigators conducted a multicenter cross-sectional study that included more than 1200 patients referred for echocardiography. The model was developed using the data of three US sites and externally validated in the data of the fourth site in Canada. The authors used clinical risk factors (age, hypertension, dyslipidemia) and a widely available, noninvasive, and inexpensive tool—12-lead ECG—to predict one of the echocardiographic markers of diastolic dysfunction—the left ventricular early diastolic relaxation velocity (eˊ) as a continuous variable. Both traditional ECG characteristics and wavelet-transformed ECG features contributed significantly to the final model, highlighting the importance of the ECG signal frequency composition. The study adds to the growing evidence that machine learning and novel ECG signal processing approaches can uncover valuable information about cardiac function, carried by the ECG signal.