Electrocardiogram-Based Machine Learning Emulator Model for Predicting Novel Echocardiography-Derived Phenogroups for Cardiac Risk-Stratification: A Prospective Multicenter Cohort Study

Authors

Heenaben B. Patel, West Virginia University Heart and Vascular InstituteFollow
Naveena Yanamala, West Virginia University Heart and Vascular Institute; Carnegie Mellon UniversityFollow
Brijesh Patel, West Virginia University Heart and Vascular InstituteFollow
Sameer Raina, West Virginia University Heart and Vascular InstituteFollow
Peter D. Farjo, West Virginia University Heart and Vascular InstituteFollow
Srinidhi Sunkara, West Virginia University Heart and Vascular InstituteFollow
Márton Tokodi, West Virginia University Heart and Vascular Institute; Semmelweis UniversityFollow
Nobuyuki Kagiyama, West Virginia University Heart and Vascular Institute; Juntendo UniversityFollow
Grace Casaclang-Verzosa, West Virginia University Heart and Vascular InstituteFollow
Partho P. Sengupta, West Virginia University Heart and Vascular InstituteFollow

Publication Date

4-18-2022

Keywords

surface electrocardiography, echocardiography, diastolic dysfunction, machine learning, topological data analysis

Abstract

Purpose: Electrocardiography (ECG)-derived machine learning models can predict echocardiography (echo)-derived indices of systolic or diastolic function. However, systolic and diastolic dysfunction frequently coexists, which necessitates an integrated assessment for optimal risk-stratification. We explored an ECG-derived model that emulates an echo-derived model that combines multiple parameters for identifying patient phenogroups at risk for major adverse cardiac events (MACE).

Methods: In this substudy of a prospective, multicenter study, patients from 3 institutions (n = 727) formed an internal cohort, and the fourth institution was reserved as an external test set (n = 518). A previously validated patient similarity analysis model was used for labeling the patients as low-/high-risk phenogroups. These labels were utilized for training an ECG-derived deep neural network model to predict MACE risk per phenogroup. After 5-fold cross-validation training, the model was tested on the reserved external dataset.

Results: Our ECG-derived model showed robust classification of patients, with area under the receiver operating characteristic curve of 0.86 (95% CI: 0.79–0.91) and 0.84 (95% CI: 0.80–0.87), sensitivity of 80% and 76%, and specificity of 88% and 75% for the internal and external test sets, respectively. The ECG-derived model demonstrated an increased probability for MACE in high-risk vs low-risk patients (21% vs 3%; P < 0.001), which was similar to the echo-trained model (21% vs 5%; P < 0.001), suggesting comparable utility.

Conclusions: This novel ECG-derived machine learning model provides a cost-effective strategy for predicting patient subgroups in whom an integrated milieu of systolic and diastolic dysfunction is associated with a high risk of MACE.

Recommended Citation

Patel HB, Yanamala N, Patel B, Raina S, Farjo PD, Sunkara S, Tokodi M, Kagiyama N, Casaclang-Verzosa G, Sengupta PP. Electrocardiogram-based machine learning emulator model for predicting novel echocardiography-derived phenogroups for cardiac risk-stratification: a prospective multicenter cohort study. J Patient Cent Res Rev. 2022;9:98-107. doi: 10.17294/2330-0698.1893