Author + information
- Marton Tokodi,
- Hemant Kulkarni,
- Lan Hu,
- Ali Hama Amin,
- Muhammad Ashraf,
- Grace Casaclang-Verzosa and
- Partho P. Sengupta
The impairment of myocardial relaxation is a common finding in left ventricular diastolic dysfunction (LVDD) and is a strong predictor of all-cause mortality. We investigated a novel signal-processed electrocardiography (spECG) technique to extract electrophysiological patterns associated with abnormal myocardial relaxation.
Time-frequency-energy displays using continuous wavelet-transformed spECG (Fig. A) was assessed using Random Forest ensemble classifier with Monte Carlo cross-validation in two independent institutional cohorts (n = 188 and 102). Abnormal relaxation was defined using absolute tissue Doppler cut-off and/or cohort-specific z-scores values.
Repolarization energy was significantly lower in patients with abnormal LV relaxation (Fig. B). The area under receiver-operating characteristic curve (AUC) for prediction of myocardial relaxation impairment was 0.90 (95% Confidence interval, CI: 0.85-0.95) in the first cohort. While the second cohort included younger patients, the diagnostic accuracy of spECG was still comparable with an AUC of 0.85 (95% CI 0.77-0.92, Fig. C). For both cohorts, spECG showed significant net reclassification improvement and integrated discrimination improvement over traditional surface ECG for predicting abnormal relaxation (Fig. D).
The spECG provided a robust prediction of abnormal myocardial relaxation and may be a valuable screening strategy for intervening during early stages of LVDD.
Poster Hall, Hall A/B
Sunday, March 11, 2018, 3:45 p.m.-4:30 p.m.
Session Title: Cardiomyopathies: Assessment and Outcomes
Abstract Category: 13. Heart Failure and Cardiomyopathies: Clinical
Presentation Number: 1238-107
- 2018 American College of Cardiology Foundation