Elizabeth L Potter1, Carlos H M Rodrigues2, David B Ascher2, Walter P Abhayaratna3, Partho P Sengupta4, Thomas H Marwick5. 1. Baker Heart and Diabetes Institute, Melbourne, Victoria, Australia; School of Public Health and Preventive Medicine, Monash University, Melbourne, Victoria, Australia. 2. Baker Heart and Diabetes Institute, Melbourne, Victoria, Australia; School of Biomedical Sciences, Melbourne University, Melbourne, Victoria, Australia. 3. Australian National University Medical School, Australian National University, Canberra, Australian Capital Territory, Australia; Division of Medicine, Canberra Hospital, Canberra, Australian Capital Territory, Australia. 4. West Virginia University Heart and Vascular Institute, Morgantown, West Virginia, USA. 5. Baker Heart and Diabetes Institute, Melbourne, Victoria, Australia; School of Public Health and Preventive Medicine, Monash University, Melbourne, Victoria, Australia. Electronic address: tom.marwick@baker.edu.au.
Abstract
OBJECTIVES: To identify whether machine learning from processing of continuous wave transforms (CWTs) to provide an "energy waveform" electrocardiogram (ewECG) could be integrated with echocardiographic assessment of subclinical systolic and diastolic left ventricular dysfunction (LVD). BACKGROUND: Asymptomatic LVD has management implications, but routine echocardiography is not undertaken in subjects at risk of heart failure. Signal processing of the surface ECG with the use of CWT can identify abnormal myocardial relaxation. METHODS: EwECG and echocardiography were undertaken in 398 participants at risk of heart failure (HF). Reduced global longitudinal strain (GLS ≤16%)), diastolic abnormalities (E/e' >15, left atrial enlargement with E/e' >10 or impaired relaxation) or LV hypertrophy defined LVD. EwECG feature selection and supervised machine-learning by random forest (RF) classifier was undertaken with 643 CWT-derived features and the Atherosclerosis Risk in Communities (ARIC) heart failure risk score. RESULTS: The ARIC score and 18 CWT features were selected to build a RF predictive model for LVD in a training dataset (n = 287; 60% female, median age 71 [interquartile range: 68 to 74] years). Model performance was tested in an independent group (n = 111; 49% female, median age 61 years [59 to 66 years]), demonstrating 85% sensitivity and 72% specificity (area under the receiver-operating characteristic curve [AUC]: 0.83; 95% confidence interval [CI]: 0.74 to 0.92). With ARIC score removed, sensitivity was 88% and specificity, 70% (AUC: 0.78; 95% CI: 0.70 to 0.86). RF models for reduced GLS and diastolic abnormalities including similar features had sensitivities that were unsuitable for screening. Conventional candidates for LVD screening (ARIC score, N-terminal pro-B-type natriuretic peptide, and standard automated ECG analysis) had inferior discriminative ability. Integration of ewECG in screening of people at risk of HF would reduce need for echocardiography by 45% while missing 12% of LVD cases. CONCLUSIONS: Machine learning applied to ewECG is a sensitive screening test for LVD, and its integration into screening of patients at risk for HF would reduce the number of echocardiograms by almost one-half.
OBJECTIVES: To identify whether machine learning from processing of continuous wave transforms (CWTs) to provide an "energy waveform" electrocardiogram (ewECG) could be integrated with echocardiographic assessment of subclinical systolic and diastolic left ventricular dysfunction (LVD). BACKGROUND: Asymptomatic LVD has management implications, but routine echocardiography is not undertaken in subjects at risk of heart failure. Signal processing of the surface ECG with the use of CWT can identify abnormal myocardial relaxation. METHODS: EwECG and echocardiography were undertaken in 398 participants at risk of heart failure (HF). Reduced global longitudinal strain (GLS ≤16%)), diastolic abnormalities (E/e' >15, left atrial enlargement with E/e' >10 or impaired relaxation) or LV hypertrophy defined LVD. EwECG feature selection and supervised machine-learning by random forest (RF) classifier was undertaken with 643 CWT-derived features and the Atherosclerosis Risk in Communities (ARIC) heart failure risk score. RESULTS: The ARIC score and 18 CWT features were selected to build a RF predictive model for LVD in a training dataset (n = 287; 60% female, median age 71 [interquartile range: 68 to 74] years). Model performance was tested in an independent group (n = 111; 49% female, median age 61 years [59 to 66 years]), demonstrating 85% sensitivity and 72% specificity (area under the receiver-operating characteristic curve [AUC]: 0.83; 95% confidence interval [CI]: 0.74 to 0.92). With ARIC score removed, sensitivity was 88% and specificity, 70% (AUC: 0.78; 95% CI: 0.70 to 0.86). RF models for reduced GLS and diastolic abnormalities including similar features had sensitivities that were unsuitable for screening. Conventional candidates for LVD screening (ARIC score, N-terminal pro-B-type natriuretic peptide, and standard automated ECG analysis) had inferior discriminative ability. Integration of ewECG in screening of people at risk of HF would reduce need for echocardiography by 45% while missing 12% of LVD cases. CONCLUSIONS: Machine learning applied to ewECG is a sensitive screening test for LVD, and its integration into screening of patients at risk for HF would reduce the number of echocardiograms by almost one-half.
Authors: Anne-Mar Van Ommen; Elise Laura Kessler; Gideon Valstar; N Charlotte Onland-Moret; Maarten Jan Cramer; Frans Rutten; Ruben Coronel; Hester Den Ruijter Journal: Front Cardiovasc Med Date: 2021-12-17