Author + information
- Received June 4, 2020
- Accepted June 25, 2020
- Published online August 17, 2020.
- Nobuyuki Kagiyama, MD, PhDa@KagiyamaNobu,
- Marco Piccirilli, PhDa,
- Naveena Yanamala, PhDa,b,
- Sirish Shrestha, MSa,
- Peter D. Farjo, MDa,
- Grace Casaclang-Verzosa, MDa,
- Wadea M. Tarhuni, MDc,
- Negin Nezarat, MDd,
- Matthew J. Budoff, MDd,
- Jagat Narula, MDe and
- Partho P. Sengupta, MDa,∗ (, )@ppsengupta1
- aDivision of Cardiology, Department of Medicine, West Virginia University Heart and Vascular Institute, Morgantown, West Virginia
- bInstitute for Software Research, School of Computer Science, Carnegie Mellon University, Pittsburgh, Pennsylvania
- cWindsor Cardiac Centre, Windsor, Ontario, Canada
- dLundquist Institute, Department of Medicine, Harbor-UCLA Medical Center, Torrance, California
- eZena and Michael A. Wiener Cardiovascular Institute, Icahn School of Medicine at Mount Sinai, New York, New York
- ↵∗Address for correspondence:
Dr. Partho P. Sengupta, West Virginia University Heart and Vascular Institute, 1 Medical Center Drive, Morgantown, West Virginia 26506.
Background 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 eʹ 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 eʹ 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.
- left ventricular diastolic dysfunction
- myocardial relaxation
This study was supported in part by funds from the National Science Foundation (NSF: #1920920) and by Heart Test Laboratories, Inc. d/b/a HeartSciences. HeartSciences provided funding and spECG devices. They had no role in developing the research plan, analysis, drafting the manuscript other than providing necessary resources to collect the information from different site investigators. Dr. Kagiyama has been supported by a research grant from Hitachi Healthcare. Dr. Sengupta has served as a consultant to HeartSciences, Ultromics, and Kencor Health. All other authors have reported that they have no relationships relevant to the contents of this paper to disclose. John Brush, MD, served as Guest Associate Editor for this paper. Deepak L. Bhatt, MD, MPH, served as Guest Editor-in-Chief for this paper.
The authors attest they are in compliance with human studies committees and animal welfare regulations of the authors’ institutions and Food and Drug Administration guidelines, including patient consent where appropriate. For more information, visit the JACC author instructions page.
- Received June 4, 2020.
- Accepted June 25, 2020.
- 2020 American College of Cardiology Foundation
This article requires a subscription or purchase to view the full text. If you are a subscriber or member, click Login or the Subscribe link (top menu above) to access this article.