Machine learning versus classical electrocardiographic criteria for echocardiographic left ventricular hypertrophy in a pre-participation cohort.

Autor:	Lim DY; Medical Classification Centre, Central Manpower Base, Singapore Armed Forces, Singapore., Sng G; Medical Classification Centre, Central Manpower Base, Singapore Armed Forces, Singapore., Ho WH; Medical Classification Centre, Central Manpower Base, Singapore Armed Forces, Singapore., Hankun W; Medical Classification Centre, Central Manpower Base, Singapore Armed Forces, Singapore., Sia CH; Medical Classification Centre, Central Manpower Base, Singapore Armed Forces, Singapore.; Department of Cardiology, National University Heart Centre Singapore, Singapore.; Department of Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore., Lee JS; Medical Classification Centre, Central Manpower Base, Singapore Armed Forces, Singapore., Shen X; Medical Classification Centre, Central Manpower Base, Singapore Armed Forces, Singapore.; Department of Cardiology, National University Heart Centre Singapore, Singapore., Tan BY; Medical Classification Centre, Central Manpower Base, Singapore Armed Forces, Singapore.; HQ Medical Corps, Singapore Armed Forces, Singapore.; University Medicine Cluster, National University Health System, Singapore., Lee EC; Medical Classification Centre, Central Manpower Base, Singapore Armed Forces, Singapore., Dalakoti M; Medical Classification Centre, Central Manpower Base, Singapore Armed Forces, Singapore.; Department of Cardiology, National University Heart Centre Singapore, Singapore., Kang Jie W; Medical Classification Centre, Central Manpower Base, Singapore Armed Forces, Singapore.; University Medicine Cluster, National University Health System, Singapore., Kwan CK; Medical Classification Centre, Central Manpower Base, Singapore Armed Forces, Singapore., Chow W; HQ Medical Corps, Singapore Armed Forces, Singapore., San Tan R; Department of Cardiology, National Heart Centre Singapore, Singapore., Lam CS; Department of Cardiology, National Heart Centre Singapore, Singapore., Chua TS; Department of Cardiology, National Heart Centre Singapore, Singapore., Joo Yeo T; Medical Classification Centre, Central Manpower Base, Singapore Armed Forces, Singapore.; Department of Cardiology, National University Heart Centre Singapore, Singapore., Chong DT; Medical Classification Centre, Central Manpower Base, Singapore Armed Forces, Singapore.; Department of Cardiology, National Heart Centre Singapore, Singapore.
Jazyk:	angličtina
Zdroj:	Kardiologia polska [Kardiol Pol] 2021; Vol. 79 (6), pp. 654-661. Date of Electronic Publication: 2021 May 20.
DOI:	10.33963/KP.15955
Abstrakt:	Background: Classical electrocardiographic (ECG) criteria for left ventricular hypertrophy (LVH) are well studied in older populations and patients with hypertension. Their utility in young pre-participation cohorts is unclear. Aims: We aimed to develop machine learning models for detection of echocardiogram-diagnosed LVH from ECG, and compare these models with classical criteria. Methods: Between November 2009 and December 2014, pre-participation screening ECG and subsequent echocardiographic data was collected from 17 310 males aged 16 to 23, who reported for medical screening prior to military conscription. A final diagnosis of LVH was made during echocardiography, defined by a left ventricular mass index >115 g/m2. The continuous and threshold forms of classical ECG criteria (Sokolow-Lyon, Romhilt-Estes, Modified Cornell, Cornell Product, and Cornell) were compared against machine learning models (Logistic Regression, GLMNet, Random Forests, Gradient Boosting Machines) using receiver-operating characteristics curve analysis. We also compared the important variables identified by machine learning models with the input variables of classical criteria. Results: Prevalence of echocardiographic LVH in this population was 0.82% (143/17310). Classical ECG criteria had poor performance in predicting LVH. Machine learning methods achieved superior performance: Logistic Regression (area under the curve [AUC], 0.811; 95% confidence interval [CI], 0.738-0.884), GLMNet (AUC, 0.873; 95% CI, 0.817-0.929), Random Forest (AUC, 0.824; 95% CI, 0.749-0.898), Gradient Boosting Machines (AUC, 0.800; 95% CI, 0.738-0.862). Conclusions: Machine learning methods are superior to classical ECG criteria in diagnosing echocardiographic LVH in the context of pre-participation screening.
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu