Electrocardiographic Machine Learning to Predict Left Ventricular Diastolic Dysfunction in Asian Young Male Adults

Abstract

Left ventricular diastolic dysfunction (LVDD) occurs at the initial stage of heart failure. Electrocardiographic (ECG) criteria and machine learning for ECG features have been applied to predict LVDD in middle-and old-aged individuals. The purpose of this study is to clarify the performance of machine learning in young adults. Three machine learning classifiers including random forest (RF), support vector machine (SVM) and gradient boosting decision tree (GBDT) for the input of 26 ECG features with or without 6 other biological features (age, anthropometrics and blood pressures) are compared with the corrected QT (QTc) interval, a traditional ECG criterion for LVDD. The definition of LVDD is based on either one of the following echocardiographic criteria: (1) an E/A ratio of mitral inflow <0.8; (2) a lateral mitral annulus velocity e' <10 cm/s; and (3) an E/e' ratio >14. The best areas under the receiver operating characteristic curve were observed in machine learning of the RF for ECG only (84.1%) and of the SVM for all ECG and biological features (82.1%), both of which were superior to the QTc interval (64.6%). If the specificity is chosen to be approximately 75.0%, the sensitivity of the RF for ECG only reaches 81.0% and that of the SVM for all ECG and biological features is raised to 85.7%, both of which are higher than 47.6% by the QTc interval. This study suggests that using machine learning for ECG features only or with other biological features to predict LVDD in young Asian adults is reliable. The proposed methods provide for the early detection of LVDD for young adults and are helpful for taking preventive action on heart failure.

Association between secondhand smoke exposure and incident heart failure: The Multi‐Ethnic Study of Atherosclerosis (MESA)

“…Then, Cox proportional hazards regression analysis was used to determine the multivariable-adjusted association of SHS exposure time with incident HF (any, HFrEF, HFpEF, and HF of ischaemic and non-ischaemic origins) in the self-report cohort and in the cohort subset. Covariates used in the model were chosen based on previously published associations with active smoking and HF, [30][31][32][33][34][35][36] which included age, sex, race/ethnicity, education level, income status, health insurance status, BMI, tobacco pack-years, alcohol intake status, diabetes status, hypertension status, CKD status, total cholesterol, statin use, physical activity, hs-CRP (log e transformed), NT-proBNP (log e transformed), the use of antipsychotics or tricyclic antidepressants, and urinary creatinine (for the cohort subset only). Since hypertension accounted for more than half of the HF events in the MESA study, 37 and urinary cotinine excretion may be lower in CKD, 38 both hypertension and CKD were crucial confounders of the association.…”

Electrocardiographic and cardiometabolic risk markers of left ventricular diastolic dysfunction in physically active adults: CHIEF heart study

“…Second, since this study had a cross-sectional design, temporal associations for the changes in LV diastolic function could not be assessed. Third, some subjects of LVDD might not be taken into account, since the criteria of greater tricuspid regurgitation velocity and left atrial volume index for LVDD ( 39 , 40 ) were not regarded as inclusion criteria in this study. For instance, there were 384 subjects (19%) with a tricuspid regurgitation velocity > 2.8 m/s, which was possibly due to the effect of athletes' heart.…”

Journey from Electronics to Healthcare Technology – Philips, Healthcare Product Maker

“…Improved early detection and prompt treatment of cardiac diseases can be achieved by the short-term automated machine learning process that can partially replace and promote the long-term specialized training of primary practitioners [59]. Machine learning could be used in routine health checks for young people to detect and prevent heart failure before it becomes a serious problem [60].…”

“…Johnson & Johnson (J&J), an American multinational corporation with its headquarters in New Brunswick, New Jersey, was founded in 1886 and is known for producing consumer packaged products, pharmaceuticals, and medical equipment. A total of 250 of the company's spin-offs operate in60 different nations, while the firm's wares are exported to over 175 different nations. Johnson & Johnson manufactures a wide range of wellknown pharmaceutical and first aid brands.…”