ABSTRACT
BACKGROUND: Echocardiography provides complex data on cardiac function that can be integrated into patterns of dysfunction related to the severity of cardiac disease. The aim of this study was to demonstrate the feasibility of applying machine learning (ML) to automate the integration of echocardiographic data from the whole cardiac cycle and to automatically recognize patterns in velocity profiles and deformation curves, allowing the identification of functional phenotypes. METHODS: Echocardiography was performed in 189 clinically managed patients with hypertension and 97 healthy individuals without hypertension. Speckle-tracking analysis of the left ventricle and atrium was performed, and deformation curves were extracted. Aortic and mitral blood pool pulsed-wave Doppler and mitral annular tissue pulsed-wave Doppler velocity profiles were obtained. These whole-cardiac cycle deformation and velocity curves were used as ML input. Unsupervised ML was used to create a representation of patients with hypertension in a virtual space in which patients are positioned on the basis of the similarity of their integrated whole-cardiac cycle echocardiography data. Regression methods were used to explore patterns of echocardiographic traces within this virtual ML-derived space, while clustering was used to define phenogroups. RESULTS: The algorithm captured different patterns in tissue and blood-pool velocity and deformation profiles and integrated the findings, yielding phenotypes related to normal cardiac function and others to advanced remodeling associated with pressure overload in hypertension. The addition of individuals without hypertension into the ML-derived space confirmed the interpretation of normal and remodeled phenotypes. CONCLUSIONS: ML-based pattern recognition is feasible from echocardiographic data obtained during the whole cardiac cycle. Automated algorithms can consistently capture patterns in velocity and deformation data and, on the basis of these patterns, group patients into interpretable, clinically comprehensive phenogroups that describe structural and functional remodeling. Automated pattern recognition may potentially aid interpretation of imaging data and diagnostic accuracy.
Subject(s)
Echocardiography , Pattern Recognition, Automated , Heart Atria/diagnostic imaging , Humans , Machine Learning , PhenotypeABSTRACT
A index of non-invasive myocardial work (MWI) can account for pressure during the assessment of cardiac function, potentially separating the influence of loading conditions from the influence of the underlying tissue remodelling. The aim is to assess LV function accounted for loading and explore hypertensive MWI distribution by comparing healthy individuals to hypertensive patients without and with localized basal septal hypertrophy (BSH). An echocardiogram was performed in 170 hypertensive patients and 20 healthy individuals. BSH was defined by a basal-to-mid septal wall thickness ratio ≥ 1.4. LV speckle-tracking was performed, and the MWI calculated globally and regionally for the apical, mid and basal regions. An apex-to-base gradient, seen in regional strain values, was preserved in the distribution of myocardial work, with the apical region compensating for the impairment of the basal segments. This functional redistribution was further pronounced in patients with localized BSH. In these patients, segmental MWI analysis revealed underlying impairment of regional work unrelated to acute loading conditions. Non-invasive MWI analysis offers the possibility to compare LV function regardless of blood pressure at the time of observation. Changes in MWI distribution can be seen in hypertension unrelated to the load-dependency of strain. Accentuated functional changes affirm the role of BSH as an echocardiographic marker in hypertension.
Subject(s)
Arterial Pressure , Echocardiography , Hypertension/complications , Hypertrophy, Left Ventricular/diagnostic imaging , Ventricular Dysfunction, Left/diagnostic imaging , Ventricular Function, Left , Ventricular Pressure , Case-Control Studies , Europe , Female , Humans , Hypertension/diagnosis , Hypertension/physiopathology , Hypertrophy, Left Ventricular/etiology , Hypertrophy, Left Ventricular/physiopathology , Male , Middle Aged , Predictive Value of Tests , Ventricular Dysfunction, Left/etiology , Ventricular Dysfunction, Left/physiopathology , Ventricular RemodelingABSTRACT
Basal septal hypertrophy (BSH) is commonly seen in patients with systemic hypertension and has been associated with increased afterload. The impact of localized hypertrophy on left ventricular (LV) and left atrial (LA) function is still unclear. Our aim is to investigate if BSH is a marker of a more pronounced impact of hypertension on cardiac function in the early stages of hypertensive heart disease. An echocardiogram was performed in 163 well-controlled hypertensive patients and 22 healthy individuals. BSH was defined by a basal-to-mid septal thickness ratio ≥1.4. LV dimensions and mass were evaluated. LV global and regional deformation was assessed by 2-dimensional (2D) speckle tracking echocardiography, and LV diastolic function by 2D and Doppler imaging. LA function was evaluated with phasic volume indices calculated from 2D and 3-dimensional volumes, as well as speckle tracking echocardiography. The population was 54% men, mean age 57 (53 to 60) years. BSH was seen in 20% (nâ¯=â¯32) of the hypertensive cohort. Patients with BSH showed decreased regional LV systolic deformation, impaired LV relaxation with a higher proportion of indeterminate LV diastolic function, and LA functional impairment defined by a reduction of reservoir strain and a change in LA functional dynamics. In conclusion, in well-controlled hypertension impairment of LV and LA function is present in patients with early LV remodeling and localized hypertrophy. BSH might be useful as an early marker of the burden of hypertensive heart disease.